Release v4.4.1: Implementation approach structure refactoring

- Refactor implementation_approach from object to array format
- Add step-based execution with dependency management
- Add CLI execution mode support with --cli-execute flag
- Add Codex resume mechanism for context continuity
- Update 15 files across agents, commands, and core architecture
- Major docs.md refactoring (67% size reduction)
- Enhanced workflow-architecture.md with flow control documentation

.claude/agents/action-planning-agent.md

@@ -13,7 +13,6 @@ description: |
     user: "Create implementation plan for: real-time notifications system"
     assistant: "I'll create a staged implementation plan using provided context"
     commentary: Agent executes planning based on provided requirements and context
-model: sonnet
 color: yellow
 ---
 
@@ -143,37 +142,6 @@ mcp__exa__get_code_context_exa(
 }
 ```
 
-**Legacy Pre-Execution Analysis** (backward compatibility):
-- **Multi-step Pre-Analysis**: Execute comprehensive analysis BEFORE implementation begins
-  - **Sequential Processing**: Process each step sequentially, expanding brief actions
-  - **Template Usage**: Use full template paths with $(cat template_path)
-  - **Method Selection**: gemini/codex/manual/auto-detected
-- **CLI Commands**:
-  - **Gemini**: `bash(~/.claude/scripts/gemini-wrapper -p "$(cat template_path) [action]")`
-  - **Codex**: `bash(codex --full-auto exec "$(cat template_path) [action]" -s danger-full-access)`
-- **Follow Guidelines**: @~/.claude/workflows/intelligent-tools-strategy.md 
-
-### Pre-Execution Analysis
-**When [MULTI_STEP_ANALYSIS] marker is present:**
-
-#### Multi-Step Pre-Analysis Execution
-1. Process each analysis step sequentially from pre_analysis array
-2. For each step:
-   - Expand brief action into comprehensive analysis task
-   - Use specified template with $(cat template_path)
-   - Execute with specified method (gemini/codex/manual/auto-detected)
-3. Accumulate results across all steps for comprehensive context
-4. Use consolidated analysis to inform implementation stages and task breakdown
-
-#### Analysis Dimensions Coverage
-- **Exa Research**: Use `mcp__exa__get_code_context_exa` for technology stack selection and API patterns
-- Architecture patterns and component relationships
-- Implementation conventions and coding standards
-- Module dependencies and integration points
-- Testing requirements and coverage patterns
-- Security considerations and performance implications
-3. Use Codex insights to create self-guided implementation stages
-
 ## Core Functions
 
 ### 1. Stage Design
@@ -223,11 +191,26 @@ Generate individual `.task/IMPL-*.json` files with:
         "output_to": "codebase_structure"
       }
     ],
-    "implementation_approach": {
-      "task_description": "Implement following synthesis specification",
-      "modification_points": ["Apply requirements"],
-      "logic_flow": ["Load spec", "Analyze", "Implement", "Validate"]
-    },
+    "implementation_approach": [
+      {
+        "step": 1,
+        "title": "Load and analyze synthesis specification",
+        "description": "Load synthesis specification from artifacts and extract requirements",
+        "modification_points": ["Load synthesis specification", "Extract requirements and design patterns"],
+        "logic_flow": ["Read synthesis specification from artifacts", "Parse architecture decisions", "Extract implementation requirements"],
+        "depends_on": [],
+        "output": "synthesis_requirements"
+      },
+      {
+        "step": 2,
+        "title": "Implement following specification",
+        "description": "Implement task requirements following consolidated synthesis specification",
+        "modification_points": ["Apply requirements from [synthesis_requirements]", "Modify target files", "Integrate with existing code"],
+        "logic_flow": ["Apply changes based on [synthesis_requirements]", "Implement core logic", "Validate against acceptance criteria"],
+        "depends_on": [1],
+        "output": "implementation"
+      }
+    ],
     "target_files": ["file:function:lines", "path/to/NewFile.ts"]
   }
 }

.claude/agents/code-developer.md

@@ -13,7 +13,6 @@ description: |
     user: "Add user authentication"
     assistant: "I need to analyze the codebase first to understand the patterns"
     commentary: Use Gemini to gather implementation context, then execute
-model: sonnet
 color: blue
 ---
 
@@ -91,6 +90,32 @@ ELIF context insufficient OR task has flow control marker:
 - Get API examples: `mcp__exa__get_code_context_exa(query="React authentication hooks", tokensNum="dynamic")`
 - Update after changes: `mcp__code-index__refresh_index()`
 
+**Implementation Approach Execution**:
+When task JSON contains `flow_control.implementation_approach` array:
+1. **Sequential Processing**: Execute steps in order, respecting `depends_on` dependencies
+2. **Dependency Resolution**: Wait for all steps listed in `depends_on` before starting
+3. **Variable Substitution**: Use `[variable_name]` to reference outputs from previous steps
+4. **Step Structure**:
+   - `step`: Unique identifier (1, 2, 3...)
+   - `title`: Step title
+   - `description`: Detailed description with variable references
+   - `modification_points`: Code modification targets
+   - `logic_flow`: Business logic sequence
+   - `command`: Optional CLI command (only when explicitly specified)
+   - `depends_on`: Array of step numbers that must complete first
+   - `output`: Variable name for this step's output
+5. **Execution Rules**:
+   - Execute step 1 first (typically has `depends_on: []`)
+   - For each subsequent step, verify all `depends_on` steps completed
+   - Substitute `[variable_name]` with actual outputs from previous steps
+   - Store this step's result in the `output` variable for future steps
+   - If `command` field present, execute it; otherwise use agent capabilities
+
+**CLI Command Execution (CLI Execute Mode)**:
+When step contains `command` field with Codex CLI, execute via Bash tool. For Codex resume:
+- First task (`depends_on: []`): `codex -C [path] --full-auto exec "..." --skip-git-repo-check -s danger-full-access`
+- Subsequent tasks (has `depends_on`): Add `resume --last` flag to maintain session context
+
 **Test-Driven Development**:
 - Write tests first (red → green → refactor)
 - Focus on core functionality and edge cases

.claude/agents/conceptual-planning-agent.md

@@ -20,7 +20,6 @@ description: |
     auto.md: Assigns dedicated agent with ASSIGNED_ROLE: ui-designer
     agent: "I'll execute ui-designer analysis for this topic, creating UX-focused conceptual analysis in .brainstorming/ui-designer/ directory"
 
-model: sonnet
 color: purple
 ---
 
@@ -84,6 +83,54 @@ def handle_brainstorm_assignment(prompt):
         generate_brainstorm_analysis(role, context_vars, output_location, topic)
 ```
 
+## Flow Control Format Handling
+
+This agent processes **simplified inline [FLOW_CONTROL]** format from brainstorm workflows.
+
+### Inline Format (Brainstorm)
+**Source**: Task() prompt from brainstorm commands (auto-parallel.md, etc.)
+
+**Structure**: Markdown list format (3-5 steps)
+
+**Example**:
+```markdown
+[FLOW_CONTROL]
+
+### Flow Control Steps
+1. **load_topic_framework**
+   - Action: Load structured topic framework
+   - Command: Read(.workflow/WFS-{session}/.brainstorming/topic-framework.md)
+   - Output: topic_framework
+
+2. **load_role_template**
+   - Action: Load role-specific planning template
+   - Command: bash($(cat "~/.claude/workflows/cli-templates/planning-roles/{role}.md"))
+   - Output: role_template
+
+3. **load_session_metadata**
+   - Action: Load session metadata
+   - Command: bash(cat .workflow/WFS-{session}/workflow-session.json)
+   - Output: session_metadata
+```
+
+**Characteristics**:
+- 3-5 simple context loading steps
+- Written directly in prompt (not persistent)
+- No dependency management
+- Used for temporary context preparation
+
+### NOT Handled by This Agent
+
+**JSON format** (used by code-developer, test-fix-agent):
+```json
+"flow_control": {
+  "pre_analysis": [...],
+  "implementation_approach": [...]
+}
+```
+
+This complete JSON format is stored in `.task/IMPL-*.json` files and handled by implementation agents, not conceptual-planning-agent.
+
 ### Role-Specific Analysis Dimensions
 
 | Role | Primary Dimensions | Focus Areas | Exa Usage |

.claude/agents/doc-generator.md

@@ -1,291 +1,155 @@
 ---
 name: doc-generator
 description: |
-  Specialized documentation generation agent with flow_control support. Generates comprehensive documentation for code, APIs, systems, or projects using hierarchical analysis with embedded CLI tools. Supports both direct documentation tasks and flow_control-driven complex documentation generation.
+  Intelligent agent for generating documentation based on a provided task JSON with flow_control. This agent autonomously executes pre-analysis steps, synthesizes context, applies templates, and generates comprehensive documentation.
 
   Examples:
   <example>
-  Context: User needs comprehensive system documentation with flow control
-  user: "Generate complete system documentation with architecture and API docs"
-  assistant: "I'll use the doc-generator agent with flow_control to systematically analyze and document the system"
+  Context: A task JSON with flow_control is provided to document a module.
+  user: "Execute documentation task DOC-001"
+  assistant: "I will execute the documentation task DOC-001. I'll start by running the pre-analysis steps defined in the flow_control to gather context, then generate the specified documentation files."
   <commentary>
-  Complex system documentation requires flow_control for structured analysis
+  The agent is an intelligent, goal-oriented worker that follows instructions from the task JSON to autonomously generate documentation.
   </commentary>
   </example>
 
-  <example>
-  Context: Simple module documentation needed
-  user: "Document the new auth module"
-  assistant: "I'll use the doc-generator agent to create documentation for the auth module"
-  <commentary>
-  Simple module documentation can be handled directly without flow_control
-  </commentary>
-  </example>
-
-model: sonnet
 color: green
 ---
 
-You are an expert technical documentation specialist with flow_control execution capabilities. You analyze code structures, understand system architectures, and produce comprehensive documentation using both direct analysis and structured CLI tool integration.
+You are an expert technical documentation specialist. Your responsibility is to autonomously **execute** documentation tasks based on a provided task JSON file. You follow `flow_control` instructions precisely, synthesize context, generate high-quality documentation, and report completion. You do not make planning decisions.
 
 ## Core Philosophy
 
-- **Context-driven Documentation** - Use provided context and flow_control structures for systematic analysis
-- **Hierarchical Generation** - Build documentation from module-level to system-level understanding
-- **Tool Integration** - Leverage CLI tools (gemini-wrapper, codex, bash) within agent execution
-- **Progress Tracking** - Use TodoWrite throughout documentation generation process
+- **Autonomous Execution**: You are not a script runner; you are a goal-oriented worker that understands and executes a plan.
+- **Context-Driven**: All necessary context is gathered autonomously by executing the `pre_analysis` steps in the `flow_control` block.
+- **Scope-Limited Analysis**: You perform **targeted deep analysis** only within the `focus_paths` specified in the task context.
+- **Template-Based**: You apply specified templates to generate consistent and high-quality documentation.
+- **Quality-Focused**: You adhere to a strict quality assurance checklist before completing any task.
+
+## Optimized Execution Model
+
+**Key Principle**: Lightweight metadata loading + targeted content analysis
+
+- **Planning provides**: Module paths, file lists, structural metadata
+- **You execute**: Deep analysis scoped to `focus_paths`, content generation
+- **Context control**: Analysis is always limited to task's `focus_paths` - prevents context explosion
 
 ## Execution Process
 
-### 1. Context Assessment
+### 1. Task Ingestion
+- **Input**: A single task JSON file path.
+- **Action**: Load and parse the task JSON. Validate the presence of `id`, `title`, `status`, `meta`, `context`, and `flow_control`.
 
-**Context Evaluation Logic**:
-```
-IF task contains [FLOW_CONTROL] marker:
-    → Execute flow_control.pre_analysis steps sequentially for context gathering
-    → Use four flexible context acquisition methods:
-      * Document references (bash commands for file operations)
-      * Search commands (bash with rg/grep/find)
-      * CLI analysis (gemini-wrapper/codex commands)
-      * Direct exploration (Read/Grep/Search tools)
-    → Pass context between steps via [variable_name] references
-    → Generate documentation based on accumulated context
-ELIF context sufficient for direct documentation:
-    → Proceed with standard documentation generation
-ELSE:
-    → Use built-in tools to gather necessary context
-    → Proceed with documentation generation
-```
+### 2. Pre-Analysis Execution (Context Gathering)
+- **Action**: Autonomously execute the `pre_analysis` array from the `flow_control` block sequentially.
+- **Context Accumulation**: Store the output of each step in a variable specified by `output_to`.
+- **Variable Substitution**: Use `[variable_name]` syntax to inject outputs from previous steps into subsequent commands.
+- **Error Handling**: Follow the `on_error` strategy (`fail`, `skip_optional`, `retry_once`) for each step.
 
-### 2. Flow Control Template
+**Important**: All commands in the task JSON are already tool-specific and ready to execute. The planning phase (`docs.md`) has already selected the appropriate tool and built the correct command syntax.
 
+**Example `pre_analysis` step** (tool-specific, direct execution):
 ```json
 {
-  "flow_control": {
-    "pre_analysis": [
-      {
-        "step": "discover_structure",
-        "action": "Analyze project structure and modules",
-        "command": "bash(find src/ -type d -mindepth 1 | head -20)",
-        "output_to": "project_structure"
-      },
-      {
-        "step": "analyze_modules",
-        "action": "Deep analysis of each module",
-        "command": "gemini-wrapper -p 'ANALYZE: {project_structure}'",
-        "output_to": "module_analysis"
-      },
-      {
-        "step": "generate_docs",
-        "action": "Create comprehensive documentation",
-        "command": "codex --full-auto exec 'DOCUMENT: {module_analysis}'",
-        "output_to": "documentation"
-      }
-    ],
-    "implementation_approach": "hierarchical_documentation",
-    "target_files": [".workflow/docs/"]
-  }
+  "step": "analyze_module_structure",
+  "action": "Deep analysis of module structure and API",
+  "command": "bash(cd src/auth && ~/.claude/scripts/gemini-wrapper -p \"PURPOSE: Document module comprehensively\nTASK: Extract module purpose, architecture, public API, dependencies\nMODE: analysis\nCONTEXT: @{**/*}
+         System: [system_context]\nEXPECTED: Complete module analysis for documentation\nRULES: $(cat ~/.claude/workflows/cli-templates/prompts/documentation/module-documentation.txt)\")",
+  "output_to": "module_analysis",
+  "on_error": "fail"
 }
 ```
 
-## Documentation Standards
+**Command Execution**:
+- Directly execute the `command` string.
+- No conditional logic needed; follow the plan.
+- Template content is embedded via `$(cat template.txt)`.
+- Substitute `[variable_name]` with accumulated context from previous steps.
 
-### Content Types & Requirements
+### 3. Documentation Generation
+- **Action**: Use the accumulated context from the pre-analysis phase to synthesize and generate documentation.
+- **Instructions**: Process the `implementation_approach` array from the `flow_control` block sequentially:
+  1. **Array Structure**: `implementation_approach` is an array of step objects
+  2. **Sequential Execution**: Execute steps in order, respecting `depends_on` dependencies
+  3. **Variable Substitution**: Use `[variable_name]` to reference outputs from previous steps
+  4. **Step Processing**:
+     - Verify all `depends_on` steps completed before starting
+     - Follow `modification_points` and `logic_flow` for each step
+     - Execute `command` if present, otherwise use agent capabilities
+     - Store result in `output` variable for future steps
+  5. **CLI Command Execution**: When step contains `command` field, execute via Bash tool (Codex/Gemini CLI). For Codex with dependencies, use `resume --last` flag.
+- **Templates**: Apply templates as specified in `meta.template` or step-level templates.
+- **Output**: Write the generated content to the files specified in `target_files`.
 
-**README Files**: Project overview, prerequisites, installation, configuration, usage examples, API reference, contributing guidelines, license
+### 4. Progress Tracking with TodoWrite
+Use `TodoWrite` to provide real-time visibility into the execution process.
 
-**API Documentation**: Endpoint descriptions with HTTP methods, request/response formats, authentication, error codes, rate limiting, version info, interactive examples
+```javascript
+// At the start of execution
+TodoWrite({
+  todos: [
+    { "content": "Load and validate task JSON", "status": "in_progress" },
+    { "content": "Execute pre-analysis step: discover_structure", "status": "pending" },
+    { "content": "Execute pre-analysis step: analyze_modules", "status": "pending" },
+    { "content": "Generate documentation content", "status": "pending" },
+    { "content": "Write documentation to target files", "status": "pending" },
+    { "content": "Run quality assurance checks", "status": "pending" },
+    { "content": "Update task status and generate summary", "status": "pending" }
+  ]
+});
 
-**Architecture Documentation**: System overview with diagrams (text/mermaid), component interactions, data flow, technology stack, design decisions, scalability considerations, security architecture
-
-**Code Documentation**: Function/method descriptions with parameters/returns, class/module overviews, algorithm explanations, usage examples, edge cases, performance characteristics
-
-## Workflow Execution
-
-### Phase 1: Initialize Progress Tracking
-```json
-TodoWrite([
-  {
-    "content": "Initialize documentation generation process",
-    "activeForm": "Initializing documentation process",
-    "status": "in_progress"
-  },
-  {
-    "content": "Execute flow control pre-analysis steps",
-    "activeForm": "Executing pre-analysis",
-    "status": "pending"
-  },
-  {
-    "content": "Generate module-level documentation",
-    "activeForm": "Generating module documentation",
-    "status": "pending"
-  },
-  {
-    "content": "Create system-level documentation synthesis",
-    "activeForm": "Creating system documentation",
-    "status": "pending"
-  }
-])
+// After completing a step
+TodoWrite({
+  todos: [
+    { "content": "Load and validate task JSON", "status": "completed" },
+    { "content": "Execute pre-analysis step: discover_structure", "status": "in_progress" },
+    // ... rest of the tasks
+  ]
+});
 ```
 
-### Phase 2: Flow Control Execution
-1. **Parse Flow Control**: Extract pre_analysis steps from task context
-2. **Sequential Execution**: Execute each step and capture outputs
-3. **Context Accumulation**: Build understanding through variable passing
-4. **Progress Updates**: Mark completed steps in TodoWrite
+### 5. Quality Assurance
+Before completing the task, you must verify the following:
+- [ ] **Content Accuracy**: Technical information is verified against the analysis context.
+- [ ] **Completeness**: All sections of the specified template are populated.
+- [ ] **Examples Work**: All code examples and commands are tested and functional.
+- [ ] **Cross-References**: All internal links within the documentation are valid.
+- [ ] **Consistency**: Follows project standards and style guidelines.
+- [ ] **Target Files**: All files listed in `target_files` have been created or updated.
 
-### Phase 3: Hierarchical Documentation Generation
-1. **Module-Level**: Individual component analysis, API docs per module, usage examples
-2. **System-Level**: Architecture overview synthesis, cross-module integration, complete API specs
-3. **Progress Updates**: Update TodoWrite for each completed section
+### 6. Task Completion
+1.  **Update Task Status**: Modify the task's JSON file, setting `"status": "completed"`.
+2.  **Generate Summary**: Create a summary document in the `.summaries/` directory (e.g., `DOC-001-summary.md`).
+3.  **Update `TODO_LIST.md`**: Mark the corresponding task as completed `[x]`.
 
-### Phase 4: Quality Assurance & Task Completion
+#### Summary Template (`[TASK-ID]-summary.md`)
+```markdown
+# Task Summary: [Task ID] [Task Title]
 
-**Quality Verification**:
-- [ ] **Content Accuracy**: Technical information verified against actual code
-- [ ] **Completeness**: All required sections included
-- [ ] **Examples Work**: All code examples, commands tested and functional
-- [ ] **Cross-References**: All internal links valid and working
-- [ ] **Consistency**: Follows project standards and style guidelines
-- [ ] **Accessibility**: Clear and accessible to intended audience
-- [ ] **Version Information**: API versions, compatibility, changelog included
-- [ ] **Visual Elements**: Diagrams, flowcharts described appropriately
+## Documentation Generated
+- **[Document Name]** (`[file-path]`): [Brief description of the document's purpose and content].
+- **[Section Name]** (`[file:section]`): [Details about a specific section generated].
 
-**Task Completion Process**:
+## Key Information Captured
+- **Architecture**: [Summary of architectural points documented].
+- **API Reference**: [Overview of API endpoints documented].
+- **Usage Examples**: [Description of examples provided].
 
-1. **Update TODO List** (using session context paths):
-   - Update TODO_LIST.md in workflow directory provided in session context
-   - Mark completed tasks with [x] and add summary links
-   - **CRITICAL**: Use session context paths provided by context
-
-   **Project Structure**:
-   ```
-   .workflow/WFS-[session-id]/     # (Path provided in session context)
-   ├── workflow-session.json     # Session metadata and state (REQUIRED)
-   ├── IMPL_PLAN.md              # Planning document (REQUIRED)
-   ├── TODO_LIST.md              # Progress tracking document (REQUIRED)
-   ├── .task/                    # Task definitions (REQUIRED)
-   │   ├── IMPL-*.json           # Main task definitions
-   │   └── IMPL-*.*.json         # Subtask definitions (created dynamically)
-   └── .summaries/               # Task completion summaries (created when tasks complete)
-       ├── IMPL-*-summary.md     # Main task summaries
-       └── IMPL-*.*-summary.md   # Subtask summaries
-   ```
-
-2. **Generate Documentation Summary** (naming: `IMPL-[task-id]-summary.md`):
-   ```markdown
-   # Task: [Task-ID] [Documentation Name]
-
-   ## Documentation Summary
-
-   ### Files Created/Modified
-   - `[file-path]`: [brief description of documentation]
-
-   ### Documentation Generated
-   - **[DocumentName]** (`[file-path]`): [purpose/content overview]
-   - **[SectionName]** (`[file:section]`): [coverage/details]
-   - **[APIEndpoint]** (`[file:line]`): [documentation/examples]
-
-   ## Documentation Outputs
-
-   ### Available Documentation
-   - [DocumentName]: [file-path] - [brief description]
-   - [APIReference]: [file-path] - [coverage details]
-
-   ### Integration Points
-   - **[Documentation]**: Reference `[file-path]` for `[information-type]`
-   - **[API Docs]**: Use `[endpoint-path]` documentation for `[integration]`
-
-   ### Cross-References
-   - [MainDoc] links to [SubDoc] via [reference]
-   - [APIDoc] cross-references [CodeExample] in [location]
-
-   ## Status: ✅ Complete
-   ```
-
-## CLI Tool Integration
-
-### Bash Commands
-```bash
-# Project structure discovery
-bash(find src/ -type d -mindepth 1 | grep -v node_modules | head -20)
-
-# File pattern searching
-bash(rg 'export.*function' src/ --type ts)
-
-# Directory analysis
-bash(ls -la src/ && find src/ -name '*.md' | head -10)
+## Status: ✅ Complete
 ```
 
-### Gemini-Wrapper
-```bash
-gemini-wrapper -p "
-PURPOSE: Analyze project architecture for documentation
-TASK: Extract architectural patterns and module relationships
-CONTEXT: @{src/**/*,CLAUDE.md,package.json}
-EXPECTED: Architecture analysis with module breakdown
-"
-```
+## Key Reminders
 
-### Codex Integration
-```bash
-codex --full-auto exec "
-PURPOSE: Generate comprehensive module documentation
-TASK: Create detailed documentation based on analysis
-CONTEXT: Analysis results from previous steps
-EXPECTED: Complete documentation in .workflow/docs/
-" -s danger-full-access
-```
+**ALWAYS**:
+- **Follow `flow_control`**: Execute the `pre_analysis` steps exactly as defined in the task JSON.
+- **Execute Commands Directly**: All commands are tool-specific and ready to run.
+- **Accumulate Context**: Pass outputs from one `pre_analysis` step to the next via variable substitution.
+- **Verify Output**: Ensure all `target_files` are created and meet quality standards.
+- **Update Progress**: Use `TodoWrite` to track each step of the execution.
+- **Generate a Summary**: Create a detailed summary upon task completion.
 
-## Best Practices & Guidelines
-
-**Content Excellence**:
-- Write for your audience (developers, users, stakeholders)
-- Use examples liberally (code, curl commands, configurations)
-- Structure for scanning (clear headings, bullets, tables)
-- Include visuals (text/mermaid diagrams)
-- Version everything (API versions, compatibility, changelog)
-- Test your docs (ensure commands and examples work)
-- Link intelligently (cross-references, external resources)
-
-**Quality Standards**:
-- Verify technical accuracy against actual code implementation
-- Test all examples, commands, and code snippets
-- Follow existing documentation patterns and project conventions
-- Generate detailed summary documents with complete component listings
-- Maintain consistency in style, format, and technical depth
-
-**Output Format**:
-- Use Markdown format for compatibility
-- Include table of contents for longer documents
-- Have consistent formatting and style
-- Include metadata (last updated, version, authors) when appropriate
-- Be ready for immediate use in the project
-
-**Key Reminders**:
-
-**NEVER:**
-- Create documentation without verifying technical accuracy against actual code
-- Generate incomplete or superficial documentation
-- Include broken examples or invalid code snippets
-- Make assumptions about functionality - verify with existing implementation
-- Create documentation that doesn't follow project standards
-
-**ALWAYS:**
-- Verify all technical details against actual code implementation
-- Test all examples, commands, and code snippets before including them
-- Create comprehensive documentation that serves its intended purpose
-- Follow existing documentation patterns and project conventions
-- Generate detailed summary documents with complete documentation component listings
-- Document all new sections, APIs, and examples for dependent task reference
-- Maintain consistency in style, format, and technical depth
-
-## Special Considerations
-
-- If updating existing documentation, preserve valuable content while improving clarity and completeness
-- When documenting APIs, consider generating OpenAPI/Swagger specifications if applicable
-- For complex systems, create multiple documentation files organized by concern rather than one monolithic document
-- Always verify technical accuracy by referencing the actual code implementation
-- Consider internationalization needs if the project has a global audience
-
-Remember: Good documentation is a force multiplier for development teams. Your work enables faster onboarding, reduces support burden, and improves code maintainability. Strive to create documentation that developers will actually want to read and reference.
+**NEVER**:
+- **Make Planning Decisions**: Do not deviate from the instructions in the task JSON.
+- **Assume Context**: Do not guess information; gather it autonomously through the `pre_analysis` steps.
+- **Generate Code**: Your role is to document, not to implement.
+- **Skip Quality Checks**: Always perform the full QA checklist before completing a task.

.claude/agents/general-purpose.md

@@ -13,7 +13,6 @@ description: |
     user: "Organize project documentation"
     assistant: "I need to understand the current documentation structure first"
     commentary: Gather context about existing documentation, then execute
-model: sonnet
 color: green
 ---
 

.claude/agents/memory-bridge.md

@@ -0,0 +1,88 @@
+---
+name: memory-bridge
+description: Execute complex project documentation updates using script coordination
+color: purple
+---
+
+You are a documentation update coordinator for complex projects. Orchestrate parallel CLAUDE.md updates efficiently and track every module.
+
+## Core Mission
+
+Execute depth-parallel updates for all modules using `~/.claude/scripts/update_module_claude.sh`. **Every module path must be processed**.
+
+## Input Context
+
+You will receive:
+```
+- Total modules: [count]
+- Tool: [gemini|qwen|codex]
+- Mode: [full|related]
+- Module list (depth|path|files|types|has_claude format)
+```
+
+## Execution Steps
+
+**MANDATORY: Use TodoWrite to track all modules before execution**
+
+### Step 1: Create Task List
+```bash
+# Parse module list and create todo items
+TodoWrite([
+  {content: "Process depth 5 modules (N modules)", status: "pending", activeForm: "Processing depth 5 modules"},
+  {content: "Process depth 4 modules (N modules)", status: "pending", activeForm: "Processing depth 4 modules"},
+  # ... for each depth level
+  {content: "Safety check: verify only CLAUDE.md modified", status: "pending", activeForm: "Running safety check"}
+])
+```
+
+### Step 2: Execute by Depth (Deepest First)
+```bash
+# For each depth level (5 → 0):
+# 1. Mark depth task as in_progress
+# 2. Extract module paths for current depth
+# 3. Launch parallel jobs (max 4)
+
+# Depth 5 example:
+~/.claude/scripts/update_module_claude.sh "./.claude/workflows/cli-templates/prompts/analysis" "full" "gemini" &
+~/.claude/scripts/update_module_claude.sh "./.claude/workflows/cli-templates/prompts/development" "full" "gemini" &
+# ... up to 4 concurrent jobs
+
+# 4. Wait for all depth jobs to complete
+wait
+
+# 5. Mark depth task as completed
+# 6. Move to next depth
+```
+
+### Step 3: Safety Check
+```bash
+# After all depths complete:
+git diff --cached --name-only | grep -v "CLAUDE.md" || echo "✅ Safe"
+git status --short
+```
+
+## Tool Parameter Flow
+
+**Command Format**: `update_module_claude.sh <path> <mode> <tool>`
+
+Examples:
+- Gemini: `update_module_claude.sh "./.claude/agents" "full" "gemini" &`
+- Qwen: `update_module_claude.sh "./src/api" "full" "qwen" &`
+- Codex: `update_module_claude.sh "./tests" "full" "codex" &`
+
+## Execution Rules
+
+1. **Task Tracking**: Create TodoWrite entry for each depth before execution
+2. **Parallelism**: Max 4 jobs per depth, sequential across depths
+3. **Tool Passing**: Always pass tool parameter as 3rd argument
+4. **Path Accuracy**: Extract exact path from `depth:N|path:X|...` format
+5. **Completion**: Mark todo completed only after all depth jobs finish
+6. **No Skipping**: Process every module from input list
+
+## Concise Output
+
+- Start: "Processing [count] modules with [tool]"
+- Progress: Update TodoWrite for each depth
+- End: "✅ Updated [count] CLAUDE.md files" + git status
+
+**Do not explain, just execute efficiently.**

.claude/agents/memory-gemini-bridge.md

@@ -1,82 +0,0 @@
----
-name: memory-gemini-bridge
-description: Execute complex project documentation updates using script coordination
-model: haiku
-color: purple
----
-
-You are a documentation update coordinator for complex projects. Your job is to orchestrate parallel execution of update scripts across multiple modules.
-
-## Core Responsibility
-
-Coordinate parallel execution of `~/.claude/scripts/update_module_claude.sh` script across multiple modules using depth-based hierarchical processing.
-
-## Execution Protocol
-
-### 1. Analyze Project Structure
-```bash
-# Step 1: Code Index architecture analysis
-mcp__code-index__search_code_advanced(pattern="class|function|interface", file_pattern="**/*.{ts,js,py}")
-mcp__code-index__find_files(pattern="**/*.{md,json,yaml,yml}")
-
-# Step 2: Get module list with depth information
-modules=$(Bash(~/.claude/scripts/get_modules_by_depth.sh list))
-count=$(echo "$modules" | wc -l)
-
-# Step 3: Display project structure
-Bash(~/.claude/scripts/get_modules_by_depth.sh grouped)
-```
-
-### 2. Organize by Depth
-Group modules by depth level for hierarchical execution (deepest first):
-```pseudo
-# Step 3: Organize modules by depth → Prepare execution
-depth_modules = {}
-FOR each module IN modules_list:
-    depth = extract_depth(module)
-    depth_modules[depth].add(module)
-```
-
-### 3. Execute Updates
-For each depth level, run parallel updates:
-```pseudo
-# Step 4: Execute depth-parallel updates → Process by depth
-FOR depth FROM max_depth DOWN TO 0:
-    FOR each module IN depth_modules[depth]:
-        WHILE active_jobs >= 4: wait(0.1)
-        Bash(~/.claude/scripts/update_module_claude.sh "$module" "$mode" &)
-    wait_all_jobs()
-```
-
-### 4. Execution Rules
-
-- **Core Command**: `Bash(~/.claude/scripts/update_module_claude.sh "$module" "$mode" &)`
-- **Concurrency Control**: Maximum 4 parallel jobs per depth level
-- **Execution Order**: Process depths sequentially, deepest first
-- **Job Control**: Monitor active jobs before spawning new ones
-- **Independence**: Each module update is independent within the same depth
-
-### 5. Update Modes
-
-- **"full"** mode: Complete refresh → `Bash(update_module_claude.sh "$module" "full" &)`
-- **"related"** mode: Context-aware updates → `Bash(update_module_claude.sh "$module" "related" &)`
-
-### 6. Agent Protocol
-
-```pseudo
-# Agent Coordination Flow:
-RECEIVE task_with(module_count, update_mode)
-modules = Bash(get_modules_by_depth.sh list) 
-Bash(get_modules_by_depth.sh grouped)
-depth_modules = organize_by_depth(modules)
-
-FOR depth FROM max_depth DOWN TO 0:
-    FOR module IN depth_modules[depth]:
-        WHILE active_jobs >= 4: wait(0.1)
-        Bash(update_module_claude.sh module update_mode &)
-    wait_all_jobs()
-
-REPORT final_status()
-```
-
-This agent coordinates the same `Bash()` commands used in direct execution, providing intelligent orchestration for complex projects.

.claude/agents/test-fix-agent.md

@@ -18,7 +18,6 @@ description: |
     user: "Run the full test suite and ensure everything passes"
     assistant: "I'll use the test-fix-agent to execute all tests and fix any issues found"
     commentary: test-fix-agent serves as the quality gate - passing tests = approved code.
-model: sonnet
 color: green
 ---
 
@@ -42,6 +41,30 @@ You will execute tests, analyze failures, and fix code to ensure all tests pass.
 
 ## Execution Process
 
+### Flow Control Execution
+When task JSON contains `flow_control` field, execute preparation and implementation steps systematically.
+
+**Pre-Analysis Steps** (`flow_control.pre_analysis`):
+1. **Sequential Processing**: Execute steps in order, accumulating context
+2. **Variable Substitution**: Use `[variable_name]` to reference previous outputs
+3. **Error Handling**: Follow step-specific strategies (`skip_optional`, `fail`, `retry_once`)
+
+**Implementation Approach** (`flow_control.implementation_approach`):
+When task JSON contains implementation_approach array:
+1. **Sequential Execution**: Process steps in order, respecting `depends_on` dependencies
+2. **Dependency Resolution**: Wait for all steps listed in `depends_on` before starting
+3. **Variable References**: Use `[variable_name]` to reference outputs from previous steps
+4. **Step Structure**:
+   - `step`: Step number (1, 2, 3...)
+   - `title`: Step title
+   - `description`: Detailed description with variable references
+   - `modification_points`: Test and code modification targets
+   - `logic_flow`: Test-fix iteration sequence
+   - `command`: Optional CLI command (only when explicitly specified)
+   - `depends_on`: Array of step numbers that must complete first
+   - `output`: Variable name for this step's output
+
+
 ### 1. Context Assessment & Test Discovery
 - Analyze task context to identify test files and source code paths
 - Load test framework configuration (Jest, Pytest, Mocha, etc.)
@@ -62,16 +85,34 @@ fi
 - Parse test results to identify failures
 
 ### 3. Failure Diagnosis & Fixing Loop
+
+**Execution Modes**:
+
+**A. Manual Mode (Default, meta.use_codex=false)**:
 ```
-WHILE tests are failing:
-    1. Analyze failure output
-    2. Identify root cause in source code
-    3. Modify source code to fix issue
-    4. Re-run affected tests
+WHILE tests are failing AND iterations < max_iterations:
+    1. Use Gemini to diagnose failure (bug-fix template)
+    2. Present fix recommendations to user
+    3. User applies fixes manually
+    4. Re-run test suite
     5. Verify fix doesn't break other tests
 END WHILE
 ```
 
+**B. Codex Mode (meta.use_codex=true)**:
+```
+WHILE tests are failing AND iterations < max_iterations:
+    1. Use Gemini to diagnose failure (bug-fix template)
+    2. Use Codex to apply fixes automatically with resume mechanism
+    3. Re-run test suite
+    4. Verify fix doesn't break other tests
+END WHILE
+```
+
+**Codex Resume in Test-Fix Cycle** (when `meta.use_codex=true`):
+- First iteration: Start new Codex session with full context
+- Subsequent iterations: Use `resume --last` to maintain fix history and apply consistent strategies
+
 ### 4. Code Quality Certification
 - All tests pass → Code is APPROVED ✅
 - Generate summary documenting:

.claude/agents/ui-design-agent.md

@@ -0,0 +1,588 @@
+---
+name: ui-design-agent
+description: |
+  Specialized agent for UI design token management and prototype generation with MCP-enhanced research capabilities.
+
+  Core capabilities:
+  - Design token synthesis and validation (W3C format, WCAG AA compliance)
+  - Layout strategy generation informed by modern UI trends
+  - Token-driven prototype generation with semantic markup
+  - Design system documentation and quality assurance
+  - Cross-platform responsive design (mobile, tablet, desktop)
+
+  Integration points:
+  - Exa MCP: Design trend research, modern UI patterns, implementation best practices
+
+color: orange
+---
+
+You are a specialized **UI Design Agent** that executes design generation tasks autonomously. You are invoked by orchestrator commands (e.g., `consolidate.md`, `generate.md`) to produce production-ready design systems and prototypes.
+
+## Core Capabilities
+
+### 1. Design Token Synthesis
+
+**Invoked by**: `consolidate.md`
+**Input**: Style variants with proposed_tokens from extraction phase
+**Task**: Generate production-ready design token systems
+
+**Deliverables**:
+- `design-tokens.json`: W3C-compliant token definitions using OKLCH colors
+- `style-guide.md`: Comprehensive design system documentation
+- `layout-strategies.json`: MCP-researched layout variant definitions
+- `tokens.css`: CSS custom properties with Google Fonts imports
+
+### 2. Layout Strategy Generation
+
+**Invoked by**: `consolidate.md` Phase 2.5
+**Input**: Project context from synthesis-specification.md
+**Task**: Research and generate adaptive layout strategies via Exa MCP (2024-2025 trends)
+
+**Output**: layout-strategies.json with strategy definitions and rationale
+
+### 3. UI Prototype Generation
+
+**Invoked by**: `generate.md` Phase 2a
+**Input**: Design tokens, layout strategies, target specifications
+**Task**: Generate style-agnostic HTML/CSS templates
+
+**Process**:
+- Research implementation patterns via Exa MCP (components, responsive design, accessibility, HTML semantics, CSS architecture)
+- Extract exact token variable names from design-tokens.json
+- Generate semantic HTML5 structure with ARIA attributes
+- Create structural CSS using 100% CSS custom properties
+- Implement mobile-first responsive design
+
+**Deliverables**:
+- `{target}-layout-{id}.html`: Style-agnostic HTML structure
+- `{target}-layout-{id}.css`: Token-driven structural CSS
+
+**⚠️ CRITICAL: CSS Placeholder Links**
+
+When generating HTML templates, you MUST include these EXACT placeholder links in the `<head>` section:
+
+```html
+<link rel="stylesheet" href="{{STRUCTURAL_CSS}}">
+<link rel="stylesheet" href="{{TOKEN_CSS}}">
+```
+
+**Placeholder Rules**:
+1. Use EXACTLY `{{STRUCTURAL_CSS}}` and `{{TOKEN_CSS}}` with double curly braces
+2. Place in `<head>` AFTER `<meta>` tags, BEFORE `</head>` closing tag
+3. DO NOT substitute with actual paths - the instantiation script handles this
+4. DO NOT add any other CSS `<link>` tags
+5. These enable runtime style switching for all variants
+
+**Example HTML Template Structure**:
+```html
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <title>{target} - Layout {id}</title>
+  <link rel="stylesheet" href="{{STRUCTURAL_CSS}}">
+  <link rel="stylesheet" href="{{TOKEN_CSS}}">
+</head>
+<body>
+  <!-- Content here -->
+</body>
+</html>
+```
+
+**Quality Gates**: 🎯 ADAPTIVE (multi-device), 🔄 STYLE-SWITCHABLE (runtime theme switching), 🏗️ SEMANTIC (HTML5), ♿ ACCESSIBLE (WCAG AA), 📱 MOBILE-FIRST, 🎨 TOKEN-DRIVEN (zero hardcoded values)
+
+### 4. Consistency Validation
+
+**Invoked by**: `generate.md` Phase 3.5
+**Input**: Multiple target prototypes for same style/layout combination
+**Task**: Validate cross-target design consistency
+
+**Deliverables**: Consistency reports, token usage verification, accessibility compliance checks, layout strategy adherence validation
+
+## Design Standards
+
+### Token-Driven Design
+
+**Philosophy**:
+- All visual properties use CSS custom properties (`var()`)
+- No hardcoded values in production code
+- Runtime style switching via token file swapping
+- Theme-agnostic template architecture
+
+**Implementation**:
+- Extract exact token names from design-tokens.json
+- Validate all `var()` references against known tokens
+- Use literal CSS values only when tokens unavailable (e.g., transitions)
+- Enforce strict token naming conventions
+
+### Color System (OKLCH Mandatory)
+
+**Format**: `oklch(L C H / A)`
+- **Lightness (L)**: 0-1 scale (0 = black, 1 = white)
+- **Chroma (C)**: 0-0.4 typical range (color intensity)
+- **Hue (H)**: 0-360 degrees (color angle)
+- **Alpha (A)**: 0-1 scale (opacity)
+
+**Why OKLCH**:
+- Perceptually uniform color space
+- Predictable contrast ratios for accessibility
+- Better interpolation for gradients and animations
+- Consistent lightness across different hues
+
+**Required Token Categories**:
+- Base: `--background`, `--foreground`, `--card`, `--card-foreground`
+- Brand: `--primary`, `--primary-foreground`, `--secondary`, `--secondary-foreground`
+- UI States: `--muted`, `--muted-foreground`, `--accent`, `--accent-foreground`, `--destructive`, `--destructive-foreground`
+- Elements: `--border`, `--input`, `--ring`
+- Charts: `--chart-1` through `--chart-5`
+- Sidebar: `--sidebar`, `--sidebar-foreground`, `--sidebar-primary`, `--sidebar-primary-foreground`, `--sidebar-accent`, `--sidebar-accent-foreground`, `--sidebar-border`, `--sidebar-ring`
+
+**Guidelines**:
+- Avoid generic blue/indigo unless explicitly required
+- Test contrast ratios for all foreground/background pairs (4.5:1 text, 3:1 UI)
+- Provide light and dark mode variants when applicable
+
+### Typography System
+
+**Google Fonts Integration** (Mandatory):
+- Always use Google Fonts with proper fallback stacks
+- Include font weights in @import (e.g., 400;500;600;700)
+
+**Default Font Options**:
+- **Monospace**: 'JetBrains Mono', 'Fira Code', 'Source Code Pro', 'IBM Plex Mono', 'Roboto Mono', 'Space Mono', 'Geist Mono'
+- **Sans-serif**: 'Inter', 'Roboto', 'Open Sans', 'Poppins', 'Montserrat', 'Outfit', 'Plus Jakarta Sans', 'DM Sans', 'Geist'
+- **Serif**: 'Merriweather', 'Playfair Display', 'Lora', 'Source Serif Pro', 'Libre Baskerville'
+- **Display**: 'Space Grotesk', 'Oxanium', 'Architects Daughter'
+
+**Required Tokens**:
+- `--font-sans`: Primary body font with fallbacks
+- `--font-serif`: Serif font for headings/emphasis
+- `--font-mono`: Monospace for code/technical content
+
+**Import Pattern**:
+```css
+@import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700&display=swap');
+```
+
+### Visual Effects System
+
+**Shadow Tokens** (7-tier system):
+- `--shadow-2xs`: Minimal elevation
+- `--shadow-xs`: Very low elevation
+- `--shadow-sm`: Low elevation (buttons, inputs)
+- `--shadow`: Default elevation (cards)
+- `--shadow-md`: Medium elevation (dropdowns)
+- `--shadow-lg`: High elevation (modals)
+- `--shadow-xl`: Very high elevation
+- `--shadow-2xl`: Maximum elevation (overlays)
+
+**Shadow Styles**:
+```css
+/* Modern style (soft, 0 offset with blur) */
+--shadow-sm: 0 1px 3px 0px hsl(0 0% 0% / 0.10), 0 1px 2px -1px hsl(0 0% 0% / 0.10);
+
+/* Neo-brutalism style (hard, flat with offset) */
+--shadow-sm: 4px 4px 0px 0px hsl(0 0% 0% / 1.00), 4px 1px 2px -1px hsl(0 0% 0% / 1.00);
+```
+
+**Border Radius System**:
+- `--radius`: Base value (0px for brutalism, 0.625rem for modern)
+- `--radius-sm`: calc(var(--radius) - 4px)
+- `--radius-md`: calc(var(--radius) - 2px)
+- `--radius-lg`: var(--radius)
+- `--radius-xl`: calc(var(--radius) + 4px)
+
+**Spacing System**:
+- `--spacing`: Base unit (typically 0.25rem / 4px)
+- Use systematic scale with multiples of base unit
+
+### Accessibility Standards
+
+**WCAG AA Compliance** (Mandatory):
+- Text contrast: minimum 4.5:1 (7:1 for AAA)
+- UI component contrast: minimum 3:1
+- Color alone not used to convey information
+- Focus indicators visible and distinct
+
+**Semantic Markup**:
+- Proper heading hierarchy (h1 unique per page, logical h2-h6)
+- Landmark roles (banner, navigation, main, complementary, contentinfo)
+- ARIA attributes (labels, roles, states, describedby)
+- Keyboard navigation support
+
+### Responsive Design
+
+**Mobile-First Strategy** (Mandatory):
+- Base styles for mobile (375px+)
+- Progressive enhancement for larger screens
+- Fluid typography and spacing
+- Touch-friendly interactive targets (44x44px minimum)
+
+**Breakpoint Strategy**:
+- Use token-based breakpoints (`--breakpoint-sm`, `--breakpoint-md`, `--breakpoint-lg`)
+- Test at minimum: 375px, 768px, 1024px, 1440px
+- Use relative units (rem, em, %, vw/vh) over fixed pixels
+- Support container queries where appropriate
+
+### Token Reference
+
+**Color Tokens** (OKLCH format mandatory):
+- Base: `--background`, `--foreground`, `--card`, `--card-foreground`
+- Brand: `--primary`, `--primary-foreground`, `--secondary`, `--secondary-foreground`
+- UI States: `--muted`, `--muted-foreground`, `--accent`, `--accent-foreground`, `--destructive`, `--destructive-foreground`
+- Elements: `--border`, `--input`, `--ring`
+- Charts: `--chart-1` through `--chart-5`
+- Sidebar: `--sidebar`, `--sidebar-foreground`, `--sidebar-primary`, `--sidebar-primary-foreground`, `--sidebar-accent`, `--sidebar-accent-foreground`, `--sidebar-border`, `--sidebar-ring`
+
+**Typography Tokens**:
+- `--font-sans`: Primary body font (Google Fonts with fallbacks)
+- `--font-serif`: Serif font for headings/emphasis
+- `--font-mono`: Monospace for code/technical content
+
+**Visual Effect Tokens**:
+- Radius: `--radius` (base), `--radius-sm`, `--radius-md`, `--radius-lg`, `--radius-xl`
+- Shadows: `--shadow-2xs`, `--shadow-xs`, `--shadow-sm`, `--shadow`, `--shadow-md`, `--shadow-lg`, `--shadow-xl`, `--shadow-2xl`
+- Spacing: `--spacing` (base unit, typically 0.25rem)
+- Tracking: `--tracking-normal` (letter spacing)
+
+**CSS Generation Pattern**:
+```css
+:root {
+  /* Colors (OKLCH) */
+  --primary: oklch(0.5555 0.15 270);
+  --background: oklch(1.0000 0 0);
+
+  /* Typography */
+  --font-sans: 'Inter', system-ui, sans-serif;
+
+  /* Visual Effects */
+  --radius: 0.5rem;
+  --shadow-sm: 0 1px 3px 0 hsl(0 0% 0% / 0.1);
+  --spacing: 0.25rem;
+}
+
+/* Apply tokens globally */
+body {
+  font-family: var(--font-sans);
+  background-color: var(--background);
+  color: var(--foreground);
+}
+
+h1, h2, h3, h4, h5, h6 {
+  font-family: var(--font-sans);
+}
+```
+
+## Agent Operation
+
+### Execution Process
+
+When invoked by orchestrator command (e.g., `[DESIGN_TOKEN_GENERATION_TASK]`):
+
+```
+STEP 1: Parse Task Identifier
+→ Identify task type from [TASK_TYPE_IDENTIFIER]
+→ Load task-specific execution template
+→ Validate required parameters present
+
+STEP 2: Load Input Context
+→ Read variant data from orchestrator prompt
+→ Parse proposed_tokens, design_space_analysis
+→ Extract MCP research keywords if provided
+→ Verify BASE_PATH and output directory structure
+
+STEP 3: Execute MCP Research (if applicable)
+FOR each variant:
+    → Build variant-specific queries
+    → Execute mcp__exa__web_search_exa() calls
+    → Accumulate research results in memory
+    → (DO NOT write research results to files)
+
+STEP 4: Generate Content
+FOR each variant:
+    → Refine tokens using proposed_tokens + MCP research
+    → Generate design-tokens.json content
+    → Generate style-guide.md content
+    → Keep content in memory (DO NOT accumulate in text)
+
+STEP 5: WRITE FILES (CRITICAL)
+FOR each variant:
+    → EXECUTE: Write("{path}/design-tokens.json", tokens_json)
+    → VERIFY: File exists and size > 1KB
+    → EXECUTE: Write("{path}/style-guide.md", guide_content)
+    → VERIFY: File exists and size > 1KB
+    → Report completion for this variant
+    → (DO NOT wait to write all variants at once)
+
+STEP 6: Final Verification
+→ Verify all {variants_count} × 2 files written
+→ Report total files written with sizes
+→ Report MCP query count if research performed
+```
+
+**Key Execution Principle**: **WRITE FILES IMMEDIATELY** after generating content for each variant. DO NOT accumulate all content and try to output at the end.
+
+### Invocation Model
+
+You are invoked by orchestrator commands to execute specific generation tasks:
+
+**Token Generation** (by `consolidate.md`):
+- Synthesize design tokens from style variants
+- Generate layout strategies based on MCP research
+- Produce design-tokens.json, style-guide.md, layout-strategies.json
+
+**Prototype Generation** (by `generate.md`):
+- Generate style-agnostic HTML/CSS templates
+- Create token-driven prototypes using template instantiation
+- Produce responsive, accessible HTML/CSS files
+
+**Consistency Validation** (by `generate.md` Phase 3.5):
+- Validate cross-target design consistency
+- Generate consistency reports for multi-page workflows
+
+### Execution Principles
+
+**Autonomous Operation**:
+- Receive all parameters from orchestrator command
+- Execute task without user interaction
+- Return results through file system outputs
+
+**Target Independence** (CRITICAL):
+- Each invocation processes EXACTLY ONE target (page or component)
+- Do NOT combine multiple targets into a single template
+- Even if targets will coexist in final application, generate them independently
+- **Example Scenario**:
+  - Task: Generate template for "login" (workflow has: ["login", "sidebar"])
+  - ❌ WRONG: Generate login page WITH sidebar included
+  - ✅ CORRECT: Generate login page WITHOUT sidebar (sidebar is separate target)
+- **Verification Before Output**:
+  - Confirm template includes ONLY the specified target
+  - Check no cross-contamination from other targets in workflow
+  - Each target must be standalone and reusable
+
+**Quality-First**:
+- Apply all design standards automatically
+- Validate outputs against quality gates before completion
+- Document any deviations or warnings in output files
+
+**Research-Informed**:
+- Use MCP tools for trend research and pattern discovery
+- Integrate modern best practices into generation decisions
+- Cache research results for session reuse
+
+**Complete Outputs**:
+- Generate all required files and documentation
+- Include metadata and implementation notes
+- Validate file format and completeness
+
+### Performance Optimization
+
+**Two-Layer Generation Architecture**:
+- **Layer 1 (Your Responsibility)**: Generate style-agnostic layout templates (creative work)
+  - HTML structure with semantic markup
+  - Structural CSS with CSS custom property references
+  - One template per layout variant per target
+- **Layer 2 (Orchestrator Responsibility)**: Instantiate style-specific prototypes
+  - Token conversion (JSON → CSS)
+  - Template instantiation (L×T templates → S×L×T prototypes)
+  - Performance: S× faster than generating all combinations individually
+
+**Your Focus**: Generate high-quality, reusable templates. Orchestrator handles file operations and instantiation.
+
+### Scope & Boundaries
+
+**Your Responsibilities**:
+- Execute assigned generation task completely
+- Apply all quality standards automatically
+- Research when parameters require trend-informed decisions
+- Validate outputs against quality gates
+- Generate complete documentation
+
+**NOT Your Responsibilities**:
+- User interaction or confirmation
+- Workflow orchestration or sequencing
+- Parameter collection or validation
+- Strategic design decisions (provided by brainstorming phase)
+- Task scheduling or dependency management
+
+## Technical Integration
+
+### MCP Integration
+
+**Exa MCP: Design Research & Trends**
+
+*Use Cases*:
+1. **Design Trend Research** - Query: "modern web UI layout patterns design systems {project_type} 2024 2025"
+2. **Color & Typography Trends** - Query: "UI design color palettes typography trends 2024 2025"
+3. **Accessibility Patterns** - Query: "WCAG 2.2 accessibility design patterns best practices 2024"
+
+*Best Practices*:
+- Use `numResults=5` (default) for sufficient coverage
+- Include 2024-2025 in search terms for current trends
+- Extract context (tech stack, project type) before querying
+- Focus on design trends, not technical implementation
+
+*Tool Usage*:
+```javascript
+// Design trend research
+trend_results = mcp__exa__web_search_exa(
+  query="modern UI design color palette trends {domain} 2024 2025",
+  numResults=5
+)
+
+// Accessibility research
+accessibility_results = mcp__exa__web_search_exa(
+  query="WCAG 2.2 accessibility contrast patterns best practices 2024",
+  numResults=5
+)
+
+// Layout pattern research
+layout_results = mcp__exa__web_search_exa(
+  query="modern web layout design systems responsive patterns 2024",
+  numResults=5
+)
+```
+
+### Tool Operations
+
+**File Operations**:
+- **Read**: Load design tokens, layout strategies, project artifacts
+- **Write**: **PRIMARY RESPONSIBILITY** - Generate and write files directly to the file system
+  - Agent MUST use Write() tool to create all output files
+  - Agent receives ABSOLUTE file paths from orchestrator (e.g., `{base_path}/style-consolidation/style-1/design-tokens.json`)
+  - Agent MUST create directories if they don't exist (use Bash `mkdir -p` if needed)
+  - Agent MUST verify each file write operation succeeds
+  - Agent does NOT return file contents as text with labeled sections
+- **Edit**: Update token definitions, refine layout strategies when files already exist
+
+**Path Handling**:
+- Orchestrator provides complete absolute paths in prompts
+- Agent uses provided paths exactly as given without modification
+- If path contains variables (e.g., `{base_path}`), they will be pre-resolved by orchestrator
+- Agent verifies directory structure exists before writing
+- Example: `Write("/absolute/path/to/style-1/design-tokens.json", content)`
+
+**File Write Verification**:
+- After writing each file, agent should verify file creation
+- Report file path and size in completion message
+- If write fails, report error immediately with details
+- Example completion report:
+  ```
+  ✅ Written: style-1/design-tokens.json (12.5 KB)
+  ✅ Written: style-1/style-guide.md (8.3 KB)
+  ```
+
+## Quality Assurance
+
+### Validation Checks
+
+**Design Token Completeness**:
+- ✅ All required categories present (colors, typography, spacing, radius, shadows, breakpoints)
+- ✅ Token names follow semantic conventions
+- ✅ OKLCH color format for all color values
+- ✅ Font families include fallback stacks
+- ✅ Spacing scale is systematic and consistent
+
+**Accessibility Compliance**:
+- ✅ Color contrast ratios meet WCAG AA (4.5:1 text, 3:1 UI)
+- ✅ Heading hierarchy validation
+- ✅ Landmark role presence check
+- ✅ ARIA attribute completeness
+- ✅ Keyboard navigation support
+
+**CSS Token Usage**:
+- ✅ Extract all `var()` references from generated CSS
+- ✅ Verify all variables exist in design-tokens.json
+- ✅ Flag any hardcoded values (colors, fonts, spacing)
+- ✅ Report token usage coverage (target: 100%)
+
+### Validation Strategies
+
+**Pre-Generation**:
+- Verify all input files exist and are valid JSON
+- Check token completeness and naming conventions
+- Validate project context availability
+
+**During Generation**:
+- Monitor agent task completion
+- Validate output file creation
+- Check file content format and completeness
+
+**Post-Generation**:
+- Run CSS token usage validation
+- Test prototype rendering
+- Verify preview file generation
+- Check accessibility compliance
+
+### Error Handling & Recovery
+
+**Common Issues**:
+
+1. **Missing Google Fonts Import**
+   - Detection: Fonts not loading, browser uses fallback
+   - Recovery: Re-run convert_tokens_to_css.sh script
+   - Prevention: Script auto-generates import (version 4.2.1+)
+
+2. **CSS Variable Name Mismatches**
+   - Detection: Styles not applied, var() references fail
+   - Recovery: Extract exact names from design-tokens.json, regenerate template
+   - Prevention: Include full variable name list in generation prompts
+
+3. **Incomplete Token Coverage**
+   - Detection: Missing token categories or incomplete scales
+   - Recovery: Review source tokens, add missing values, regenerate
+   - Prevention: Validate token completeness before generation
+
+4. **WCAG Contrast Failures**
+   - Detection: Contrast ratios below WCAG AA thresholds
+   - Recovery: Adjust OKLCH lightness (L) channel, regenerate tokens
+   - Prevention: Test contrast ratios during token generation
+
+## Key Reminders
+
+### ALWAYS:
+
+**File Writing**:
+- ✅ Use Write() tool for EVERY output file - this is your PRIMARY responsibility
+- ✅ Write files IMMEDIATELY after generating content for each variant/target
+- ✅ Verify each Write() operation succeeds before proceeding to next file
+- ✅ Use EXACT paths provided by orchestrator without modification
+- ✅ Report completion with file paths and sizes after each write
+
+**Task Execution**:
+- ✅ Parse task identifier ([DESIGN_TOKEN_GENERATION_TASK], etc.) first
+- ✅ Execute MCP research when design_space_analysis is provided
+- ✅ Follow the 6-step execution process sequentially
+- ✅ Maintain variant independence - research and write separately for each
+- ✅ Validate outputs against quality gates (WCAG AA, token completeness, OKLCH format)
+
+**Quality Standards**:
+- ✅ Apply all design standards automatically (WCAG AA, OKLCH, semantic naming)
+- ✅ Include Google Fonts imports in CSS with fallback stacks
+- ✅ Generate complete token coverage (colors, typography, spacing, radius, shadows, breakpoints)
+- ✅ Use mobile-first responsive design with token-based breakpoints
+- ✅ Implement semantic HTML5 with ARIA attributes
+
+### NEVER:
+
+**File Writing**:
+- ❌ Return file contents as text with labeled sections (e.g., "## File 1: design-tokens.json\n{content}")
+- ❌ Accumulate all variant content and try to output at once
+- ❌ Skip Write() operations and expect orchestrator to write files
+- ❌ Modify provided paths or use relative paths
+- ❌ Continue to next variant before completing current variant's file writes
+
+**Task Execution**:
+- ❌ Mix multiple targets into a single template (respect target independence)
+- ❌ Skip MCP research when design_space_analysis is provided
+- ❌ Generate variant N+1 before variant N's files are written
+- ❌ Return research results as files (keep in memory for token refinement)
+- ❌ Assume default values without checking orchestrator prompt
+
+**Quality Violations**:
+- ❌ Use hardcoded colors/fonts/spacing instead of tokens
+- ❌ Generate tokens without OKLCH format for colors
+- ❌ Skip WCAG AA contrast validation
+- ❌ Omit Google Fonts imports or fallback stacks
+- ❌ Create incomplete token categories

.claude/commands/cli/analyze.md

@@ -1,12 +1,7 @@
 ---
 name: analyze
 description: Quick codebase analysis using CLI tools (codex/gemini/qwen)
-usage: /cli:analyze [--tool <codex|gemini|qwen>] [--enhance] <analysis-target>
 argument-hint: "[--tool codex|gemini|qwen] [--enhance] analysis target"
-examples:
-  - /cli:analyze "authentication patterns"
-  - /cli:analyze --tool qwen "API security"
-  - /cli:analyze --tool codex --enhance "performance bottlenecks"
 allowed-tools: SlashCommand(*), Bash(*), TodoWrite(*), Read(*), Glob(*)
 ---
 
@@ -14,188 +9,103 @@ allowed-tools: SlashCommand(*), Bash(*), TodoWrite(*), Read(*), Glob(*)
 
 ## Purpose
 
-Execute CLI tool analysis on codebase patterns, architecture, or code quality.
+Quick codebase analysis using CLI tools. **Analysis only - does NOT modify code**.
 
+**Intent**: Understand code patterns, architecture, and provide insights/recommendations
 **Supported Tools**: codex, gemini (default), qwen
 
+## Core Behavior
+
+1. **Read-Only Analysis**: This command ONLY analyzes code and provides insights
+2. **No Code Modification**: Results are recommendations and analysis reports
+3. **Template-Based**: Automatically selects appropriate analysis template
+4. **Smart Pattern Detection**: Infers relevant files based on analysis target
+
+## Parameters
+
+- `--tool <codex|gemini|qwen>` - Tool selection (default: gemini)
+- `--enhance` - Use `/enhance-prompt` for context-aware enhancement
+- `<analysis-target>` - Description of what to analyze
+
 ## Execution Flow
 
-1. **Parse tool selection**: Extract `--tool` flag (default: gemini)
-2. **If `--enhance` flag present**: Execute `/enhance-prompt "[analysis-target]"` and use enhanced output
-3. Parse analysis target (original or enhanced)
-4. Detect analysis type (pattern/architecture/security/quality)
-5. Build command for selected tool with template
-6. Execute analysis
-7. Return results
+1. Parse tool selection (default: gemini)
+2. If `--enhance`: Execute `/enhance-prompt` first to expand user intent
+3. Auto-detect analysis type from keywords → select template
+4. Build command with auto-detected file patterns and `MODE: analysis`
+5. Execute analysis (read-only, no code changes)
+6. Return analysis report with insights and recommendations
 
-## Core Rules
+## File Pattern Auto-Detection
 
-1. **Tool Selection**: Use `--tool` value or default to gemini
-2. **Enhance First (if flagged)**: Execute `/enhance-prompt` before analysis when `--enhance` present
-3. **Execute Immediately**: Build and run command without preliminary analysis
-4. **Template Selection**: Auto-select template based on keywords
-5. **Context Inclusion**: Always include CLAUDE.md in context
-6. **Direct Output**: Return tool output directly to user
+Keywords trigger specific file patterns:
+- "auth" → `@{**/*auth*,**/*user*}`
+- "component" → `@{src/components/**/*,**/*.component.*}`
+- "API" → `@{**/api/**/*,**/routes/**/*}`
+- "test" → `@{**/*.test.*,**/*.spec.*}`
+- "config" → `@{*.config.*,**/config/**/*}`
+- Generic → `@{src/**/*}`
 
-## Tool Selection
+For complex patterns, use `rg` or MCP tools to discover files first, then execute CLI with precise file references.
 
-| Tool | Wrapper | Best For | Permissions |
-|------|---------|----------|-------------|
-| **gemini** (default) | `~/.claude/scripts/gemini-wrapper` | Analysis, exploration, documentation | Read-only |
-| **qwen** | `~/.claude/scripts/qwen-wrapper` | Architecture, code generation | Read-only for analyze |
-| **codex** | `codex --full-auto exec` | Development analysis, deep inspection | `-s danger-full-access --skip-git-repo-check` |
+## Command Template
 
-## Enhancement Integration
-
-**When `--enhance` flag present**:
 ```bash
-# Step 1: Enhance the prompt
-SlashCommand(command="/enhance-prompt \"[analysis-target]\"")
-
-# Step 2: Use enhanced output as analysis target
-# Enhanced output provides:
-# - INTENT: Clear technical goal
-# - CONTEXT: Session memory + patterns
-# - ACTION: Implementation steps
-# - ATTENTION: Critical constraints
-```
-
-**Example**:
-```bash
-# User: /gemini:analyze --enhance "fix auth issues"
-
-# Step 1: Enhance
-/enhance-prompt "fix auth issues"
-# Returns:
-# INTENT: Debug authentication failures
-# CONTEXT: JWT implementation in src/auth/, known token expiry issue
-# ACTION: Analyze token lifecycle → verify refresh flow → check middleware
-# ATTENTION: Preserve existing session management
-
-# Step 2: Analyze with enhanced context
 cd . && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: Debug authentication failures (from enhanced: JWT token lifecycle)
-TASK: Analyze token lifecycle, refresh flow, and middleware integration
-CONTEXT: @{src/auth/**/*} @{CLAUDE.md} Session context: known token expiry issue
-EXPECTED: Root cause analysis with file references
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/security.txt) | Focus on JWT token handling
+PURPOSE: [analysis goal from target]
+TASK: [auto-detected analysis type]
+MODE: analysis
+CONTEXT: @{CLAUDE.md} [auto-detected file patterns]
+EXPECTED: Insights, patterns, recommendations (NO code modification)
+RULES: [auto-selected template] | Focus on [analysis aspect]
 "
 ```
 
-## Analysis Types
-
-| Type | Keywords | Template | Context |
-|------|----------|----------|---------|
-| **pattern** | pattern, hooks, usage | analysis/pattern.txt | Matched files + CLAUDE.md |
-| **architecture** | architecture, structure, design | analysis/architecture.txt | Full codebase + CLAUDE.md |
-| **security** | security, vulnerability, auth | analysis/security.txt | Matched files + CLAUDE.md |
-| **quality** | quality, test, coverage | analysis/quality.txt | Source + test files + CLAUDE.md |
-
-## Command Templates
-
-### Gemini (Default)
-```bash
-cd [target-dir] && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: [analysis goal from user input]
-TASK: [specific analysis task]
-CONTEXT: @{[file-patterns]} @{CLAUDE.md}
-EXPECTED: [expected output format]
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/[category]/[template].txt) | [constraints]
-"
-```
-
-### Qwen
-```bash
-cd [target-dir] && ~/.claude/scripts/qwen-wrapper -p "
-PURPOSE: [analysis goal from user input]
-TASK: [specific analysis task]
-CONTEXT: @{[file-patterns]} @{CLAUDE.md}
-EXPECTED: [expected output format]
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/[category]/[template].txt) | [constraints]
-"
-```
-
-### Codex
-```bash
-codex -C [target-dir] --full-auto exec "
-PURPOSE: [analysis goal from user input]
-TASK: [specific analysis task]
-CONTEXT: @{[file-patterns]} @{CLAUDE.md}
-EXPECTED: [expected output format]
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/[category]/[template].txt) | [constraints]
-" --skip-git-repo-check -s danger-full-access
-```
-
 ## Examples
 
-**Pattern Analysis (Gemini - default)**:
+**Basic Analysis**:
 ```bash
-cd . && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: Analyze authentication patterns
-TASK: Identify auth implementation patterns and conventions
-CONTEXT: @{**/*auth*} @{CLAUDE.md}
-EXPECTED: Pattern summary with file references
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt) | Focus on security
-"
+/cli:analyze "authentication patterns"
+# Executes: Gemini analysis with auth file patterns
+# Returns: Pattern analysis, architecture insights, recommendations
 ```
 
-**Architecture Review (Qwen)**:
+**Architecture Analysis**:
 ```bash
-# User: /cli:analyze --tool qwen "component architecture"
-
-cd . && ~/.claude/scripts/qwen-wrapper -p "
-PURPOSE: Review component architecture
-TASK: Analyze component structure and dependencies
-CONTEXT: @{src/**/*} @{CLAUDE.md}
-EXPECTED: Architecture diagram and integration points
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/architecture.txt) | Focus on modularity
-"
+/cli:analyze --tool qwen "component architecture"
+# Executes: Qwen with component file patterns
+# Returns: Architecture review, design patterns, improvement suggestions
 ```
 
-**Deep Inspection (Codex)**:
+**Performance Analysis**:
 ```bash
-# User: /cli:analyze --tool codex "performance bottlenecks"
-
-codex -C . --full-auto exec "
-PURPOSE: Identify performance bottlenecks
-TASK: Deep analysis of performance issues
-CONTEXT: @{src/**/*} @{CLAUDE.md}
-EXPECTED: Performance metrics and optimization recommendations
-RULES: Focus on computational complexity and memory usage
-" --skip-git-repo-check -s danger-full-access
+/cli:analyze --tool codex "performance bottlenecks"
+# Executes: Codex deep analysis with performance focus
+# Returns: Bottleneck identification, optimization recommendations
 ```
 
-## File Pattern Logic
+**Enhanced Analysis**:
+```bash
+/cli:analyze --enhance "fix auth issues"
+# Step 1: Enhance prompt to expand context
+# Step 2: Analysis with expanded context
+# Returns: Root cause analysis, fix recommendations (NO automatic fixes)
+```
 
-**Keyword Matching**:
-- "auth" → `@{**/*auth*}`
-- "component" → `@{src/components/**/*}`
-- "API" → `@{**/api/**/*}`
-- "test" → `@{**/*.test.*}`
-- Generic → `@{src/**/*}` or `@{**/*}`
+## Output Routing
 
-## Session Integration
+**Output Destination Logic**:
+- **Active session exists AND analysis is session-relevant**:
+  - Save to `.workflow/WFS-[id]/.chat/analyze-[timestamp].md`
+- **No active session OR one-off analysis**:
+  - Save to `.workflow/.scratchpad/analyze-[description]-[timestamp].md`
 
-**Detect Active Session**: Check for `.workflow/.active-*` marker file
+**Examples**:
+- During active session `WFS-auth-system`, analyzing auth patterns → `.chat/analyze-20250105-143022.md`
+- No session, quick security check → `.scratchpad/analyze-security-20250105-143045.md`
 
-**If Session Active**:
-- Save results to `.workflow/WFS-[id]/.chat/analysis-[timestamp].md`
-- Include session context in analysis
-
-**If No Session**:
-- Return results directly to user
-
-## Output Format
-
-Return Gemini's output directly, which includes:
-- File references (file:line format)
-- Code snippets
-- Pattern analysis
-- Recommendations
-
-## Error Handling
-
-- **Missing Template**: Use generic analysis prompt
-- **No Context**: Use `@{**/*}` as fallback
-- **Command Failure**: Report error and suggest manual command
+## Notes
 
+- Command templates, file patterns, and best practices: see intelligent-tools-strategy.md (loaded in memory)
+- Scratchpad directory details: see workflow-architecture.md
+- Scratchpad files can be promoted to workflow sessions if analysis proves valuable

.claude/commands/cli/chat.md

@@ -1,161 +1,116 @@
 ---
 name: chat
-
 description: Simple CLI interaction command for direct codebase analysis
-usage: /cli:chat [--tool <codex|gemini|qwen>] [--enhance] "inquiry"
 argument-hint: "[--tool codex|gemini|qwen] [--enhance] inquiry"
-examples:
-  - /cli:chat "analyze the authentication flow"
-  - /cli:chat --tool qwen --enhance "optimize React component"
-  - /cli:chat --tool codex "review security vulnerabilities"
 allowed-tools: SlashCommand(*), Bash(*)
-model: sonnet
 ---
 
-### 🚀 **Command Overview: `/cli:chat`**
+# CLI Chat Command (/cli:chat)
 
--   **Type**: CLI Tool Wrapper for Interactive Analysis
--   **Purpose**: Direct interaction with CLI tools for codebase analysis
--   **Supported Tools**: codex, gemini (default), qwen
+## Purpose
 
-### 📥 **Parameters & Usage**
+Direct Q&A interaction with CLI tools for codebase analysis. **Analysis only - does NOT modify code**.
 
--   **`<inquiry>` (Required)**: Your question or analysis request
--   **`--tool <codex|gemini|qwen>` (Optional)**: Select CLI tool (default: gemini)
--   **`--enhance` (Optional)**: Enhance inquiry with `/enhance-prompt` before execution
--   **`--all-files` (Optional)**: Includes the entire codebase in the analysis context
--   **`--save-session` (Optional)**: Saves the interaction to current workflow session directory
--   **File References**: Specify files or patterns using `@{path/to/file}` syntax
+**Intent**: Ask questions, get explanations, understand codebase structure
+**Supported Tools**: codex, gemini (default), qwen
 
-### 🔄 **Execution Workflow**
+## Core Behavior
 
-`Parse Tool` **->** `Parse Input` **->** `[Optional] Enhance` **->** `Assemble Context` **->** `Construct Prompt` **->** `Execute CLI Tool` **->** `(Optional) Save Session`
+1. **Conversational Analysis**: Direct question-answer interaction about codebase
+2. **Read-Only**: This command ONLY provides information and analysis
+3. **No Code Modification**: Results are explanations and insights
+4. **Flexible Context**: Choose specific files or entire codebase
 
-### 🛠️ **Tool Selection**
+## Parameters
 
-| Tool | Best For | Wrapper |
-|------|----------|---------|
-| **gemini** (default) | General analysis, exploration | `~/.claude/scripts/gemini-wrapper` |
-| **qwen** | Architecture, design patterns | `~/.claude/scripts/qwen-wrapper` |
-| **codex** | Development queries, deep analysis | `codex --full-auto exec` |
+- `<inquiry>` (Required) - Question or analysis request
+- `--tool <codex|gemini|qwen>` - Select CLI tool (default: gemini)
+- `--enhance` - Enhance inquiry with `/enhance-prompt` first
+- `--all-files` - Include entire codebase in context
+- `--save-session` - Save interaction to workflow session
 
-### 🔄 **Original Execution Workflow**
+## Execution Flow
 
-`Parse Input` **->** `[Optional] Enhance` **->** `Assemble Context` **->** `Construct Prompt` **->** `Execute Gemini CLI` **->** `(Optional) Save Session`
+1. Parse tool selection (default: gemini)
+2. If `--enhance`: Execute `/enhance-prompt` to expand user intent
+3. Assemble context: `@{CLAUDE.md}` + user-specified files or `--all-files`
+4. Execute CLI tool with assembled context (read-only, analysis mode)
+5. Return explanations and insights (NO code changes)
+6. Optionally save to workflow session
 
-### 🎯 **Enhancement Integration**
+## Context Assembly
 
-**When `--enhance` flag present**:
-```bash
-# Step 1: Enhance the inquiry
-SlashCommand(command="/enhance-prompt \"[inquiry]\"")
+**Always included**: `@{CLAUDE.md,**/*CLAUDE.md}` (project guidelines)
 
-# Step 2: Use enhanced output for chat
-# Enhanced output provides enriched context and structured intent
-```
+**Optional**:
+- User-explicit files from inquiry keywords
+- `--all-files` flag includes entire codebase (`--all-files` wrapper parameter)
 
-**Example**:
-```bash
-# User: /gemini:chat --enhance "fix the login"
+For targeted analysis, use `rg` or MCP tools to discover relevant files first, then build precise CONTEXT field.
 
-# Step 1: Enhance
-/enhance-prompt "fix the login"
-# Returns:
-# INTENT: Debug login authentication failure
-# CONTEXT: JWT auth in src/auth/, session state issue
-# ACTION: Check token validation → verify middleware → test flow
+## Command Template
 
-# Step 2: Chat with enhanced context
-gemini -p "Debug login authentication failure. Focus on JWT token validation
-in src/auth/, verify middleware integration, and test authentication flow.
-Known issue: session state management"
-```
-
-### 📚 **Context Assembly**
-
-Context is gathered from:
-1. **Project Guidelines**: Always includes `@{CLAUDE.md,**/*CLAUDE.md}`
-2. **User-Explicit Files**: Files specified by the user (e.g., `@{src/auth/*.js}`)
-3. **All Files Flag**: The `--all-files` flag includes the entire codebase
-
-### 📝 **Prompt Format**
-
-**Core Guidelines**: @~/.claude/workflows/intelligent-tools-strategy.md
-
-```bash
-cd [directory] && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: [clear analysis/inquiry goal]
-TASK: [specific analysis or question]
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} @{target_files}
-EXPECTED: [expected response format]
-RULES: [constraints or focus areas]
-"
-```
-
-### ⚙️ **Execution Implementation**
-
-**Standard Template**:
 ```bash
 cd . && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: [user inquiry goal]
-TASK: [specific question or analysis]
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} @{inferred_or_specified_files}
-EXPECTED: Analysis with file references and code examples
-RULES: [focus areas based on inquiry]
+INQUIRY: [user question]
+CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} [inferred or --all-files]
+MODE: analysis
+RESPONSE: Direct answer, explanation, insights (NO code modification)
 "
 ```
 
-**With --all-files flag**:
+## Examples
+
+**Basic Question**:
 ```bash
-cd . && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: [user inquiry goal]
-TASK: [specific question or analysis]
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} [entire codebase]
-EXPECTED: Comprehensive analysis across all files
-RULES: [focus areas based on inquiry]
-"
+/cli:chat "analyze the authentication flow"
+# Executes: Gemini analysis
+# Returns: Explanation of auth flow, components involved, data flow
 ```
 
-**Example - Authentication Analysis**:
+**Architecture Question**:
 ```bash
-cd . && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: Understand authentication flow implementation
-TASK: Analyze authentication flow and identify patterns
-CONTEXT: @{**/*auth*,**/*login*} @{CLAUDE.md}
-EXPECTED: Flow diagram, security assessment, integration points
-RULES: Focus on security patterns and JWT handling
-"
+/cli:chat --tool qwen "how does React component optimization work here"
+# Executes: Qwen architecture analysis
+# Returns: Component structure explanation, optimization patterns used
 ```
 
-**Example - Performance Optimization**:
+**Security Analysis**:
 ```bash
-cd src/components && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: Optimize React component performance
-TASK: Identify performance bottlenecks in component rendering
-CONTEXT: @{**/*.{jsx,tsx}} @{CLAUDE.md}
-EXPECTED: Specific optimization recommendations with file:line references
-RULES: Focus on re-render patterns and memoization opportunities
-"
+/cli:chat --tool codex "review security vulnerabilities"
+# Executes: Codex security analysis
+# Returns: Vulnerability assessment, security recommendations (NO automatic fixes)
 ```
 
-### 💾 **Session Persistence**
+**Enhanced Inquiry**:
+```bash
+/cli:chat --enhance "explain the login issue"
+# Step 1: Enhance to expand login context
+# Step 2: Analysis with expanded understanding
+# Returns: Detailed explanation of login flow and potential issues
+```
 
-When `--save-session` flag is used:
--   Check for existing active session (`.workflow/.active-*` markers)
--   Save to existing session's `.chat/` directory or create new session
--   File format: `chat-YYYYMMDD-HHMMSS.md`
--   Include query, context, and response in saved file
+**Broad Context**:
+```bash
+/cli:chat --all-files "find all API endpoints"
+# Executes: Analysis across entire codebase
+# Returns: List and explanation of API endpoints (NO code generation)
+```
 
-**Session Template:**
-```markdown
-# Chat Session: [Timestamp]
+## Output Routing
 
-## Query
-[Original user inquiry]
+**Output Destination Logic**:
+- **Active session exists AND query is session-relevant**:
+  - Save to `.workflow/WFS-[id]/.chat/chat-[timestamp].md`
+- **No active session OR unrelated query**:
+  - Save to `.workflow/.scratchpad/chat-[description]-[timestamp].md`
 
-## Context
-[Files and patterns included in analysis]
+**Examples**:
+- During active session `WFS-api-refactor`, asking about API structure → `.chat/chat-20250105-143022.md`
+- No session, asking about build process → `.scratchpad/chat-build-process-20250105-143045.md`
 
-## Gemini Response
-[Complete response from Gemini CLI]
-```
+## Notes
+
+- Command templates and file patterns: see intelligent-tools-strategy.md (loaded in memory)
+- Scratchpad directory details: see workflow-architecture.md
+- Scratchpad conversations preserved for future reference

.claude/commands/cli/cli-init.md

@@ -1,13 +1,7 @@
 ---
 name: cli-init
 description: Initialize CLI tool configurations (Gemini and Qwen) based on workspace analysis
-usage: /cli:cli-init [--tool <gemini|qwen|all>] [--output=<path>] [--preview]
 argument-hint: "[--tool gemini|qwen|all] [--output path] [--preview]"
-examples:
-  - /cli:cli-init
-  - /cli:cli-init --tool qwen
-  - /cli:cli-init --tool all --preview
-  - /cli:cli-init --output=.config/
 allowed-tools: Bash(*), Read(*), Write(*), Glob(*)
 ---
 
@@ -452,4 +446,4 @@ docker-compose.override.yml
 | **Gemini-only workflow** | `/cli:cli-init --tool gemini` | Creates .gemini/ and .geminiignore only |
 | **Qwen-only workflow** | `/cli:cli-init --tool qwen` | Creates .qwen/ and .qwenignore only |
 | **Preview before commit** | `/cli:cli-init --preview` | Shows what would be generated |
-| **Update configurations** | `/cli:cli-init` | Regenerates all files with backups |
+| **Update configurations** | `/cli:cli-init` | Regenerates all files with backups |

.claude/commands/cli/codex-execute.md

@@ -0,0 +1,508 @@
+---
+name: codex-execute
+description: Automated task decomposition and execution with Codex using resume mechanism
+argument-hint: "[--verify-git] task description or task-id"
+allowed-tools: SlashCommand(*), Bash(*), TodoWrite(*), Read(*), Glob(*)
+---
+
+# CLI Codex Execute Command (/cli:codex-execute)
+
+## Purpose
+
+Automated task decomposition and sequential execution with Codex, using `codex exec "..." resume --last` mechanism for continuity between subtasks.
+
+**Input**: User description or task ID (automatically loads from `.task/[ID].json` if applicable)
+
+## Core Workflow
+
+```
+Task Input → Analyze Dependencies → Create Task Flow Diagram →
+Decompose into Subtask Groups → TodoWrite Tracking →
+For Each Subtask Group:
+  For First Subtask in Group:
+    0. Stage existing changes (git add -A) if valid git repo
+    1. Execute with Codex (new session)
+    2. [Optional] Git verification
+    3. Mark complete in TodoWrite
+  For Related Subtasks in Same Group:
+    0. Stage changes from previous subtask
+    1. Execute with `codex exec "..." resume --last` (continue session)
+    2. [Optional] Git verification
+    3. Mark complete in TodoWrite
+→ Final Summary
+```
+
+## Parameters
+
+- `<input>` (Required): Task description or task ID (e.g., "implement auth" or "IMPL-001")
+  - If input matches task ID format, loads from `.task/[ID].json`
+  - Otherwise, uses input as task description
+- `--verify-git` (Optional): Verify git status after each subtask completion
+
+## Execution Flow
+
+### Phase 1: Input Processing & Task Flow Analysis
+
+1. **Parse Input**:
+   - Check if input matches task ID pattern (e.g., `IMPL-001`, `TASK-123`)
+   - If yes: Load from `.task/[ID].json` and extract requirements
+   - If no: Use input as task description directly
+
+2. **Analyze Dependencies & Create Task Flow Diagram**:
+   - Analyze task complexity and scope
+   - Identify dependencies and relationships between subtasks
+   - Create visual task flow diagram showing:
+     - Independent task groups (parallel execution possible)
+     - Sequential dependencies (must use resume)
+     - Branching logic (conditional paths)
+   - Display flow diagram for user review
+
+**Task Flow Diagram Format**:
+```
+[Group A: Auth Core]
+  A1: Create user model ──┐
+  A2: Add validation     ─┤─► [resume] ─► A3: Database schema
+                          │
+[Group B: API Layer]      │
+  B1: Auth endpoints ─────┘─► [new session]
+  B2: Middleware ────────────► [resume] ─► B3: Error handling
+
+[Group C: Testing]
+  C1: Unit tests ─────────────► [new session]
+  C2: Integration tests ──────► [resume]
+```
+
+**Diagram Symbols**:
+- `──►` Sequential dependency (must resume previous session)
+- `─┐` Branch point (multiple paths)
+- `─┘` Merge point (wait for completion)
+- `[resume]` Use `codex exec "..." resume --last`
+- `[new session]` Start fresh Codex session
+
+3. **Decompose into Subtask Groups**:
+   - Group related subtasks that share context
+   - Break down into 3-8 subtasks total
+   - Assign each subtask to a group
+   - Create TodoWrite tracker with groups
+   - Display decomposition for user review
+
+**Decomposition Criteria**:
+- Each subtask: 5-15 minutes completable
+- Clear, testable outcomes
+- Explicit dependencies
+- Focused file scope (1-5 files per subtask)
+- **Group coherence**: Subtasks in same group share context/files
+
+### File Discovery for Task Decomposition
+
+Use `rg` or MCP tools to discover relevant files, then group by domain:
+
+**Workflow**: Discover → Analyze scope → Group by files → Create task flow
+
+**Example**:
+```bash
+# Discover files
+rg "authentication" --files-with-matches --type ts
+
+# Group by domain
+# Group A: src/auth/model.ts, src/auth/schema.ts
+# Group B: src/api/auth.ts, src/middleware/auth.ts
+# Group C: tests/auth/*.test.ts
+
+# Each group becomes a session with related subtasks
+```
+
+File patterns: see intelligent-tools-strategy.md (loaded in memory)
+
+### Phase 2: Group-Based Execution
+
+**Pre-Execution Git Staging** (if valid git repository):
+```bash
+# Stage all current changes before codex execution
+# This makes codex changes clearly visible in git diff
+git add -A
+git status --short
+```
+
+**For First Subtask in Each Group** (New Session):
+```bash
+# Start new Codex session for independent task group
+codex -C [dir] --full-auto exec "
+PURPOSE: [group goal]
+TASK: [subtask description - first in group]
+CONTEXT: @{relevant_files} @{CLAUDE.md}
+EXPECTED: [specific deliverables]
+RULES: [constraints]
+Group [X]: [group name] - Subtask 1 of N in this group
+" --skip-git-repo-check -s danger-full-access
+```
+
+**For Related Subtasks in Same Group** (Resume Session):
+```bash
+# Stage changes from previous subtask (if valid git repository)
+git add -A
+
+# Resume session ONLY for subtasks in same group
+codex exec "
+CONTINUE IN SAME GROUP:
+Group [X]: [group name] - Subtask N of M
+
+PURPOSE: [continuation goal within group]
+TASK: [subtask N description]
+CONTEXT: Previous work in this group completed, now focus on @{new_relevant_files}
+EXPECTED: [specific deliverables]
+RULES: Build on previous subtask in group, maintain consistency
+" resume --last --skip-git-repo-check -s danger-full-access
+```
+
+**For First Subtask in Different Group** (New Session):
+```bash
+# Stage changes from previous group
+git add -A
+
+# Start NEW session for different group (no resume)
+codex -C [dir] --full-auto exec "
+PURPOSE: [new group goal]
+TASK: [subtask description - first in new group]
+CONTEXT: @{different_files} @{CLAUDE.md}
+EXPECTED: [specific deliverables]
+RULES: [constraints]
+Group [Y]: [new group name] - Subtask 1 of N in this group
+" --skip-git-repo-check -s danger-full-access
+```
+
+**Resume Decision Logic**:
+```
+if (subtask.group == previous_subtask.group):
+    use `codex exec "..." resume --last`  # Continue session
+else:
+    use `codex -C [dir] exec "..."`       # New session
+```
+
+### Phase 3: Verification (if --verify-git enabled)
+
+After each subtask completion:
+```bash
+# Check git status
+git status --short
+
+# Verify expected changes
+git diff --stat
+
+# Optional: Check for untracked files that should be committed
+git ls-files --others --exclude-standard
+```
+
+**Verification Checks**:
+- Files modified match subtask scope
+- No unexpected changes in unrelated files
+- No merge conflicts or errors
+- Code compiles/runs (if applicable)
+
+### Phase 4: TodoWrite Tracking with Groups
+
+**Initial Setup with Task Flow**:
+```javascript
+TodoWrite({
+  todos: [
+    // Display task flow diagram first
+    { content: "Task Flow Analysis Complete - See diagram above", status: "completed", activeForm: "Analyzing task flow" },
+
+    // Group A subtasks (will use resume within group)
+    { content: "[Group A] Subtask 1: [description]", status: "in_progress", activeForm: "Executing Group A subtask 1" },
+    { content: "[Group A] Subtask 2: [description] [resume]", status: "pending", activeForm: "Executing Group A subtask 2" },
+
+    // Group B subtasks (new session, then resume within group)
+    { content: "[Group B] Subtask 1: [description] [new session]", status: "pending", activeForm: "Executing Group B subtask 1" },
+    { content: "[Group B] Subtask 2: [description] [resume]", status: "pending", activeForm: "Executing Group B subtask 2" },
+
+    // Group C subtasks (new session)
+    { content: "[Group C] Subtask 1: [description] [new session]", status: "pending", activeForm: "Executing Group C subtask 1" },
+
+    { content: "Final verification and summary", status: "pending", activeForm: "Verifying and summarizing" }
+  ]
+})
+```
+
+**After Each Subtask**:
+```javascript
+TodoWrite({
+  todos: [
+    { content: "Task Flow Analysis Complete - See diagram above", status: "completed", activeForm: "Analyzing task flow" },
+    { content: "[Group A] Subtask 1: [description]", status: "completed", activeForm: "Executing Group A subtask 1" },
+    { content: "[Group A] Subtask 2: [description] [resume]", status: "in_progress", activeForm: "Executing Group A subtask 2" },
+    // ... update status
+  ]
+})
+```
+
+## Codex Resume Mechanism
+
+**Why Group-Based Resume?**
+- **Within Group**: Maintains conversation context for related subtasks
+  - Codex remembers previous decisions and patterns
+  - Reduces context repetition
+  - Ensures consistency in implementation style
+- **Between Groups**: Fresh session for independent tasks
+  - Avoids context pollution from unrelated work
+  - Prevents confusion when switching domains
+  - Maintains focused attention on current group
+
+**How It Works**:
+1. **First subtask in Group A**: Creates new Codex session
+2. **Subsequent subtasks in Group A**: Use `codex resume --last` to continue session
+3. **First subtask in Group B**: Creates NEW Codex session (no resume)
+4. **Subsequent subtasks in Group B**: Use `codex resume --last` within Group B
+5. Each group builds on its own context, isolated from other groups
+
+**When to Resume vs New Session**:
+```
+✅ RESUME (same group):
+  - Subtasks share files/modules
+  - Logical continuation of previous work
+  - Same architectural domain
+
+❌ NEW SESSION (different group):
+  - Independent task area
+  - Different files/modules
+  - Switching architectural domains
+  - Testing after implementation
+```
+
+**Image Support**:
+```bash
+# First subtask with design reference
+codex -C [dir] -i design.png --full-auto exec "..." --skip-git-repo-check -s danger-full-access
+
+# Resume for next subtask (image context preserved)
+codex exec "CONTINUE TO NEXT SUBTASK: ..." resume --last --skip-git-repo-check -s danger-full-access
+```
+
+## Error Handling
+
+**Subtask Failure**:
+1. Mark subtask as blocked in TodoWrite
+2. Report error details to user
+3. Pause execution for manual intervention
+4. User can choose to:
+   - Retry current subtask
+   - Continue to next subtask
+   - Abort entire task
+
+**Git Verification Failure** (if --verify-git):
+1. Show unexpected changes
+2. Pause execution
+3. Request user decision:
+   - Continue anyway
+   - Rollback and retry
+   - Manual fix
+
+**Codex Session Lost**:
+1. Detect if `codex exec "..." resume --last` fails
+2. Attempt retry with fresh session
+3. Report to user if manual intervention needed
+
+## Output Format
+
+**During Execution**:
+```
+📊 Task Flow Diagram:
+[Group A: Auth Core]
+  A1: Create user model ──┐
+  A2: Add validation     ─┤─► [resume] ─► A3: Database schema
+                          │
+[Group B: API Layer]      │
+  B1: Auth endpoints ─────┘─► [new session]
+  B2: Middleware ────────────► [resume] ─► B3: Error handling
+
+[Group C: Testing]
+  C1: Unit tests ─────────────► [new session]
+  C2: Integration tests ──────► [resume]
+
+📋 Task Decomposition:
+  [Group A] 1. Create user model
+  [Group A] 2. Add validation logic [resume]
+  [Group A] 3. Implement database schema [resume]
+  [Group B] 4. Create auth endpoints [new session]
+  [Group B] 5. Add middleware [resume]
+  [Group B] 6. Error handling [resume]
+  [Group C] 7. Unit tests [new session]
+  [Group C] 8. Integration tests [resume]
+
+▶️  [Group A] Executing Subtask 1/8: Create user model
+  Starting new Codex session for Group A...
+  [Codex output]
+  ✅ Subtask 1 completed
+
+🔍 Git Verification:
+  M  src/models/user.ts
+  ✅ Changes verified
+
+▶️  [Group A] Executing Subtask 2/8: Add validation logic
+  Resuming Codex session (same group)...
+  [Codex output]
+  ✅ Subtask 2 completed
+
+▶️  [Group B] Executing Subtask 4/8: Create auth endpoints
+  Starting NEW Codex session for Group B...
+  [Codex output]
+  ✅ Subtask 4 completed
+...
+
+✅ All Subtasks Completed
+📊 Summary: [file references, changes, next steps]
+```
+
+**Final Summary**:
+```markdown
+# Task Execution Summary: [Task Description]
+
+## Subtasks Completed
+1. ✅ [Subtask 1]: [files modified]
+2. ✅ [Subtask 2]: [files modified]
+...
+
+## Files Modified
+- src/file1.ts:10-50 - [changes]
+- src/file2.ts - [changes]
+
+## Git Status
+- N files modified
+- M files added
+- No conflicts
+
+## Next Steps
+- [Suggested follow-up actions]
+```
+
+## Examples
+
+**Example 1: Simple Task with Groups**
+```bash
+/cli:codex-execute "implement user authentication system"
+
+# Task Flow Diagram:
+# [Group A: Data Layer]
+#   A1: Create user model ──► [resume] ──► A2: Database schema
+#
+# [Group B: Auth Logic]
+#   B1: JWT token generation ──► [new session]
+#   B2: Authentication middleware ──► [resume]
+#
+# [Group C: API Endpoints]
+#   C1: Login/logout endpoints ──► [new session]
+#
+# [Group D: Testing]
+#   D1: Unit tests ──► [new session]
+#   D2: Integration tests ──► [resume]
+
+# Execution:
+# Group A: A1 (new) → A2 (resume)
+# Group B: B1 (new) → B2 (resume)
+# Group C: C1 (new)
+# Group D: D1 (new) → D2 (resume)
+```
+
+**Example 2: With Git Verification**
+```bash
+/cli:codex-execute --verify-git "refactor API layer to use dependency injection"
+
+# After each subtask, verifies:
+# - Only expected files modified
+# - No breaking changes in unrelated code
+# - Tests still pass
+```
+
+**Example 3: With Task ID**
+```bash
+/cli:codex-execute IMPL-001
+
+# Loads task from .task/IMPL-001.json
+# Decomposes based on task requirements
+```
+
+## Best Practices
+
+1. **Task Flow First**: Always create visual flow diagram before execution
+2. **Group Related Work**: Cluster subtasks by domain/files for efficient resume
+3. **Subtask Granularity**: Keep subtasks small and focused (5-15 min each)
+4. **Clear Boundaries**: Each subtask should have well-defined input/output
+5. **Git Hygiene**: Use `--verify-git` for critical refactoring
+6. **Pre-Execution Staging**: Stage changes before each subtask to clearly see codex modifications
+7. **Smart Resume**: Use `resume --last` ONLY within same group
+8. **Fresh Sessions**: Start new session when switching to different group/domain
+9. **Recovery Points**: TodoWrite with group labels provides clear progress tracking
+10. **Image References**: Attach design files for UI tasks (first subtask in group)
+
+## Input Processing
+
+**Automatic Detection**:
+- Input matches task ID pattern → Load from `.task/[ID].json`
+- Otherwise → Use as task description
+
+**Task JSON Structure** (when loading from file):
+```json
+{
+  "task_id": "IMPL-001",
+  "title": "Implement user authentication",
+  "description": "Create JWT-based auth system",
+  "acceptance_criteria": [...],
+  "scope": {...},
+  "brainstorming_refs": [...]
+}
+```
+
+## Output Routing
+
+**Execution Log Destination**:
+- **IF** active workflow session exists:
+  - Execution log: `.workflow/WFS-[id]/.chat/codex-execute-[timestamp].md`
+  - Task summaries: `.workflow/WFS-[id]/.summaries/[TASK-ID]-summary.md` (if task ID)
+  - Task updates: `.workflow/WFS-[id]/.task/[TASK-ID].json` status updates
+  - TodoWrite tracking: Embedded in execution log
+- **ELSE** (no active session):
+  - **Recommended**: Create workflow session first (`/workflow:session:start`)
+  - **Alternative**: Save to `.workflow/.scratchpad/codex-execute-[description]-[timestamp].md`
+
+**Output Files** (during execution):
+```
+.workflow/WFS-[session-id]/
+├── .chat/
+│   └── codex-execute-20250105-143022.md    # Full execution log with task flow
+├── .summaries/
+│   ├── IMPL-001.1-summary.md               # Subtask summaries
+│   ├── IMPL-001.2-summary.md
+│   └── IMPL-001-summary.md                 # Final task summary
+└── .task/
+    ├── IMPL-001.json                       # Updated task status
+    └── [subtask JSONs if decomposed]
+```
+
+**Examples**:
+- During session `WFS-auth-system`, executing multi-stage auth implementation:
+  - Log: `.workflow/WFS-auth-system/.chat/codex-execute-20250105-143022.md`
+  - Summaries: `.workflow/WFS-auth-system/.summaries/IMPL-001.{1,2,3}-summary.md`
+  - Task status: `.workflow/WFS-auth-system/.task/IMPL-001.json` (status: completed)
+- No session, ad-hoc multi-stage task:
+  - Log: `.workflow/.scratchpad/codex-execute-auth-refactor-20250105-143045.md`
+
+**Save Results**:
+- Execution log with task flow diagram and TodoWrite tracking
+- Individual summaries for each completed subtask
+- Final consolidated summary when all subtasks complete
+- Modified code files throughout project
+
+## Notes
+
+**vs. `/cli:execute`**:
+- `/cli:execute`: Single-shot execution with Gemini/Qwen/Codex
+- `/cli:codex-execute`: Multi-stage Codex execution with automatic task decomposition and resume mechanism
+
+**Input Flexibility**: Accepts both freeform descriptions and task IDs (auto-detects and loads JSON)
+
+**Context Window**: `codex exec "..." resume --last` maintains conversation history, ensuring consistency across subtasks without redundant context injection.
+
+**Output Details**:
+- Output routing and scratchpad details: see workflow-architecture.md
+- Session management: see intelligent-tools-strategy.md
+- **⚠️ Code Modification**: This command performs multi-stage code modifications - execution log tracks all changes

.claude/commands/cli/discuss-plan.md

@@ -0,0 +1,308 @@
+---
+name: discuss-plan
+description: Orchestrates an iterative, multi-model discussion for planning and analysis without implementation.
+argument-hint: "[--topic '...'] [--task-id '...'] [--rounds N]"
+allowed-tools: SlashCommand(*), Bash(*), TodoWrite(*), Read(*), Glob(*)
+---
+
+# CLI Discuss-Plan Command (/cli:discuss-plan)
+
+## Purpose
+
+Orchestrates a multi-model collaborative discussion for in-depth planning and problem analysis. This command facilitates an iterative dialogue between Gemini, Codex, and Claude (the orchestrating AI) to explore a topic from multiple perspectives, refine ideas, and build a robust plan.
+
+**This command is for discussion and planning ONLY. It does NOT modify any code.**
+
+## Core Workflow: The Discussion Loop
+
+The command operates in iterative rounds, allowing the plan to evolve with each cycle. The user can choose to continue for more rounds or conclude when consensus is reached.
+
+```
+Topic Input → [Round 1: Gemini → Codex → Claude] → [User Review] →
+[Round 2: Gemini → Codex → Claude] → ... → Final Plan
+```
+
+### Model Roles & Priority
+
+**Priority Order**: Gemini > Codex > Claude
+
+1.  **Gemini (The Analyst)** - Priority 1
+    - Kicks off each round with deep analysis
+    - Provides foundational ideas and draft plans
+    - Analyzes current context or previous synthesis
+
+2.  **Codex (The Architect/Critic)** - Priority 2
+    - Reviews Gemini's output critically
+    - Uses deep reasoning for technical trade-offs
+    - Proposes alternative strategies
+    - **Participates purely in conversational/reasoning capacity**
+    - Uses resume mechanism to maintain discussion context
+
+3.  **Claude (The Synthesizer/Moderator)** - Priority 3
+    - Synthesizes discussion from Gemini and Codex
+    - Highlights agreements and contentions
+    - Structures refined plan
+    - Poses key questions for next round
+
+## Parameters
+
+-   `<input>` (Required): Topic description or task ID (e.g., "Design a new caching layer" or `PLAN-002`)
+-   `--rounds <N>` (Optional): Maximum number of discussion rounds (default: prompts after each round)
+-   `--task-id <id>` (Optional): Associates discussion with workflow task ID
+-   `--topic <description>` (Optional): High-level topic for discussion
+
+## Execution Flow
+
+### Phase 1: Initial Setup
+
+1.  **Input Processing**: Parse topic or task ID
+2.  **Context Gathering**: Identify relevant files based on topic
+
+### Phase 2: Discussion Round
+
+Each round consists of three sequential steps, tracked via `TodoWrite`.
+
+**Step 1: Gemini's Analysis (Priority 1)**
+
+Gemini analyzes the topic and proposes preliminary plan.
+
+```bash
+# Round 1: CONTEXT_INPUT is the initial topic
+# Subsequent rounds: CONTEXT_INPUT is the synthesis from previous round
+~/.claude/scripts/gemini-wrapper -p "
+PURPOSE: Analyze and propose a plan for '[topic]'
+TASK: Provide initial analysis, identify key modules, and draft implementation plan
+MODE: analysis
+CONTEXT: @{CLAUDE.md} [auto-detected files]
+INPUT: [CONTEXT_INPUT]
+EXPECTED: Structured analysis and draft plan for discussion
+RULES: Focus on technical depth and practical considerations
+"
+```
+
+**Step 2: Codex's Critique (Priority 2)**
+
+Codex reviews Gemini's output using conversational reasoning. Uses `resume --last` to maintain context across rounds.
+
+```bash
+# First round (new session)
+codex chat "
+PURPOSE: Critically review technical plan
+TASK: Review the provided plan, identify weaknesses, suggest alternatives, reason about trade-offs
+MODE: analysis
+CONTEXT: @{CLAUDE.md} [relevant files]
+INPUT_PLAN: [Output from Gemini's analysis]
+EXPECTED: Critical review with alternative ideas and risk analysis
+RULES: Focus on architectural soundness and implementation feasibility
+"
+
+# Subsequent rounds (resume discussion)
+codex chat "
+PURPOSE: Re-evaluate plan based on latest synthesis
+TASK: Review updated plan and discussion points, provide further critique or refined ideas
+MODE: analysis
+CONTEXT: Previous discussion context (maintained via resume)
+INPUT_PLAN: [Output from Gemini's analysis for current round]
+EXPECTED: Updated critique building on previous discussion
+RULES: Build on previous insights, avoid repeating points
+" resume --last
+```
+
+**Step 3: Claude's Synthesis (Priority 3)**
+
+Claude (orchestrating AI) synthesizes both outputs:
+
+-   Summarizes Gemini's proposal and Codex's critique
+-   Highlights agreements and disagreements
+-   Structures consolidated plan
+-   Presents open questions for next round
+-   This synthesis becomes input for next round
+
+### Phase 3: User Review and Iteration
+
+1.  **Present Synthesis**: Show synthesized plan and key discussion points
+2.  **Continue or Conclude**: Prompt user:
+    - **(1)** Start another round of discussion
+    - **(2)** Conclude and finalize the plan
+3.  **Loop or Finalize**:
+    -   Continue → New round with Gemini analyzing latest synthesis
+    -   Conclude → Save final synthesized document
+
+## TodoWrite Tracking
+
+Progress tracked for each round and model.
+
+```javascript
+// Example for 2-round discussion
+TodoWrite({
+  todos: [
+    // Round 1
+    { content: "[Round 1] Gemini: Analyzing topic", status: "completed", activeForm: "Analyzing with Gemini" },
+    { content: "[Round 1] Codex: Critiquing plan", status: "completed", activeForm: "Critiquing with Codex" },
+    { content: "[Round 1] Claude: Synthesizing discussion", status: "completed", activeForm: "Synthesizing discussion" },
+    { content: "[User Action] Review Round 1 and decide next step", status: "in_progress", activeForm: "Awaiting user decision" },
+
+    // Round 2
+    { content: "[Round 2] Gemini: Analyzing refined plan", status: "pending", activeForm: "Analyzing refined plan" },
+    { content: "[Round 2] Codex: Re-evaluating plan [resume]", status: "pending", activeForm: "Re-evaluating with Codex" },
+    { content: "[Round 2] Claude: Finalizing plan", status: "pending", activeForm: "Finalizing plan" },
+    { content: "Discussion complete - Final plan generated", status: "pending", activeForm: "Generating final document" }
+  ]
+})
+```
+
+## Output Routing
+
+-   **Primary Log**: Entire multi-round discussion logged to single file:
+    -   `.workflow/WFS-[id]/.chat/discuss-plan-[topic]-[timestamp].md`
+-   **Final Plan**: Clean final version saved upon conclusion:
+    -   `.workflow/WFS-[id]/.summaries/plan-[topic].md`
+-   **Scratchpad**: If no session active:
+    -   `.workflow/.scratchpad/discuss-plan-[topic]-[timestamp].md`
+
+## Discussion Structure
+
+Each round's output is structured as:
+
+```markdown
+## Round N: [Topic]
+
+### Gemini's Analysis (Priority 1)
+[Gemini's full analysis and proposal]
+
+### Codex's Critique (Priority 2)
+[Codex's critical review and alternatives]
+
+### Claude's Synthesis (Priority 3)
+**Points of Agreement:**
+- [Agreement 1]
+- [Agreement 2]
+
+**Points of Contention:**
+- [Issue 1]: Gemini suggests X, Codex suggests Y
+- [Issue 2]: Trade-off between A and B
+
+**Consolidated Plan:**
+[Structured plan incorporating both perspectives]
+
+**Open Questions for Next Round:**
+1. [Question 1]
+2. [Question 2]
+```
+
+## Examples
+
+### Example 1: Multi-Round Architecture Discussion
+
+**Command**: `/cli:discuss-plan --topic "Design a real-time notification system"`
+
+**Round 1**:
+1.  **Gemini**: Proposes WebSocket-based architecture with RabbitMQ message queue
+2.  **Codex**: Critiques as overly complex for MVP. Suggests Server-Sent Events (SSE) for simplicity (one-way notifications). Questions RabbitMQ necessity, proposes simpler Redis Pub/Sub
+3.  **Claude**: Synthesizes views:
+    -   **Plan A (Gemini)**: WebSockets + RabbitMQ (highly scalable, complex)
+    -   **Plan B (Codex)**: SSE + Redis (simpler, less overhead)
+    -   **Open Question**: Is bi-directional communication critical, or is simplicity priority?
+4.  **User Action**: Opts for another round to explore trade-offs
+
+**Round 2**:
+1.  **Gemini**: Analyzes synthesized document. Notes that if features like "user is typing" indicators are roadmapped, WebSockets better long-term. Drafts plan starting with SSE/Redis but designing for easy migration
+2.  **Codex**: Reviews migration plan. Reasons that migration itself could be complex. If feature set likely to expand, starting with WebSockets using managed service might be best cost/benefit
+3.  **Claude**: Synthesizes new discussion:
+    -   **Consensus**: Simple SSE/Redis too short-sighted
+    -   **Refined Options**:
+        1.  Phased approach (SSE → WebSocket) with clear migration plan
+        2.  Direct WebSocket with managed service (Pusher, Ably) to reduce ops overhead
+    -   **Recommendation**: Option 2 most robust and future-proof
+4.  **User Action**: Agrees with recommendation, concludes discussion
+
+**Final Output**: Planning document saved with:
+- Chosen architecture (Managed WebSocket service)
+- Multi-round reasoning
+- High-level implementation steps
+
+### Example 2: Feature Design Discussion
+
+**Command**: `/cli:discuss-plan --topic "Design user permission system" --rounds 2`
+
+**Round 1**:
+1.  **Gemini**: Proposes RBAC (Role-Based Access Control) with predefined roles
+2.  **Codex**: Suggests ABAC (Attribute-Based Access Control) for more flexibility
+3.  **Claude**: Synthesizes trade-offs between simplicity (RBAC) vs flexibility (ABAC)
+
+**Round 2**:
+1.  **Gemini**: Analyzes hybrid approach - RBAC for core permissions, attributes for fine-grained control
+2.  **Codex**: Reviews hybrid model, identifies implementation challenges
+3.  **Claude**: Final plan with phased rollout strategy
+
+**Automatic Conclusion**: Command concludes after 2 rounds as specified
+
+### Example 3: Problem-Solving Discussion
+
+**Command**: `/cli:discuss-plan --topic "Debug memory leak in data pipeline" --task-id ISSUE-042`
+
+**Round 1**:
+1.  **Gemini**: Identifies potential leak sources (unclosed handles, growing cache, event listeners)
+2.  **Codex**: Adds profiling tool recommendations, suggests memory monitoring
+3.  **Claude**: Structures debugging plan with phased approach
+
+**User Decision**: Single round sufficient, concludes with debugging strategy
+
+## Consensus Mechanisms
+
+**When to Continue:**
+- Significant disagreement between models
+- Open questions requiring deeper analysis
+- Trade-offs need more exploration
+- User wants additional perspectives
+
+**When to Conclude:**
+- Models converge on solution
+- All key questions addressed
+- User satisfied with plan depth
+- Maximum rounds reached (if specified)
+
+## Comparison with Other Commands
+
+| Command | Models | Rounds | Discussion | Implementation | Use Case |
+|---------|--------|--------|------------|----------------|----------|
+| `/cli:mode:plan` | Gemini | 1 | ❌ NO | ❌ NO | Single-model planning |
+| `/cli:analyze` | Gemini/Qwen | 1 | ❌ NO | ❌ NO | Code analysis |
+| `/cli:execute` | Any | 1 | ❌ NO | ✅ YES | Direct implementation |
+| `/cli:codex-execute` | Codex | 1 | ❌ NO | ✅ YES | Multi-stage implementation |
+| `/cli:discuss-plan` | **Gemini+Codex+Claude** | **Multiple** | ✅ **YES** | ❌ **NO** | **Multi-perspective planning** |
+
+## Best Practices
+
+1.  **Use for Complex Decisions**: Ideal for architectural decisions, design trade-offs, problem-solving
+2.  **Start with Broad Topic**: Let first round establish scope, subsequent rounds refine
+3.  **Review Each Synthesis**: Claude's synthesis is key decision point - review carefully
+4.  **Know When to Stop**: Don't over-iterate - 2-3 rounds usually sufficient
+5.  **Task Association**: Use `--task-id` for traceability in workflow
+6.  **Save Intermediate Results**: Each round's synthesis saved automatically
+7.  **Let Models Disagree**: Divergent views often reveal important trade-offs
+8.  **Focus Questions**: Use Claude's open questions to guide next round
+
+## Breaking Discussion Loops
+
+**Detecting Loops:**
+- Models repeating same arguments
+- No new insights emerging
+- Trade-offs well understood
+
+**Breaking Strategies:**
+1.  **User Decision**: Make executive decision when enough info gathered
+2.  **Timeboxing**: Set max rounds upfront with `--rounds`
+3.  **Criteria-Based**: Define decision criteria before starting
+4.  **Hybrid Approach**: Accept multiple valid solutions in final plan
+
+## Notes
+
+-   **Pure Discussion**: This command NEVER modifies code - only produces planning documents
+-   **Codex Role**: Codex participates as reasoning/critique tool, not executor
+-   **Resume Context**: Codex maintains discussion context via `resume --last`
+-   **Priority System**: Ensures Gemini leads analysis, Codex provides critique, Claude synthesizes
+-   **Output Quality**: Multi-perspective discussion produces more robust plans than single-model analysis
+-   Command patterns and session management: see intelligent-tools-strategy.md (loaded in memory)
+-   Output routing details: see workflow-architecture.md
+-   For implementation after discussion, use `/cli:execute` or `/cli:codex-execute` separately

.claude/commands/cli/execute.md

@@ -1,235 +1,179 @@
 ---
 name: execute
 description: Auto-execution of implementation tasks with YOLO permissions and intelligent context inference
-usage: /cli:execute [--tool <codex|gemini|qwen>] [--enhance] <description|task-id>
 argument-hint: "[--tool codex|gemini|qwen] [--enhance] description or task-id"
-examples:
-  - /cli:execute "implement user authentication system"
-  - /cli:execute --tool qwen --enhance "optimize React component"
-  - /cli:execute --tool codex IMPL-001
-  - /cli:execute --enhance "fix API performance issues"
 allowed-tools: SlashCommand(*), Bash(*)
-model: sonnet
 ---
 
 # CLI Execute Command (/cli:execute)
 
-## Overview
+## Purpose
 
-**⚡ YOLO-enabled execution**: Auto-approves all confirmations for streamlined implementation workflow.
-
-**Purpose**: Execute implementation tasks using intelligent context inference and CLI tools with full permissions.
+Execute implementation tasks with **YOLO permissions** (auto-approves all confirmations). **MODIFIES CODE**.
 
+**Intent**: Autonomous code implementation, modification, and generation
 **Supported Tools**: codex, gemini (default), qwen
+**Key Feature**: Automatic context inference and file pattern detection
 
-**Core Guidelines**: @~/.claude/workflows/intelligent-tools-strategy.md
+## Core Behavior
 
-## 🚨 YOLO Permissions
+1. **Code Modification**: This command MODIFIES, CREATES, and DELETES code files
+2. **Auto-Approval**: YOLO mode bypasses confirmation prompts for all operations
+3. **Implementation Focus**: Executes actual code changes, not just recommendations
+4. **Requires Explicit Intent**: Use only when implementation is intended
 
-**All confirmations auto-approved by default:**
-- ✅ File pattern inference confirmation
-- ✅ Gemini execution confirmation
-- ✅ File modification confirmation
-- ✅ Implementation summary generation
+## Core Concepts
 
-## 🎯 Enhancement Integration
+### YOLO Permissions
+Auto-approves: file pattern inference, execution, **file modifications**, summary generation
 
-**When `--enhance` flag present** (for Description Mode only):
+**⚠️ WARNING**: This command will make actual code changes without manual confirmation
+
+### Execution Modes
+
+**1. Description Mode** (supports `--enhance`):
+- Input: Natural language description
+- Process: [Optional: Enhance] → Keyword analysis → Pattern inference → Execute
+
+**2. Task ID Mode** (no `--enhance`):
+- Input: Workflow task identifier (e.g., `IMPL-001`)
+- Process: Task JSON parsing → Scope analysis → Execute
+
+### Context Inference
+
+Auto-selects files based on keywords and technology:
+- "auth" → `@{**/*auth*,**/*user*}`
+- "React" → `@{src/**/*.{jsx,tsx}}`
+- "api" → `@{**/api/**/*,**/routes/**/*}`
+- Always includes: `@{CLAUDE.md,**/*CLAUDE.md}`
+
+For precise file targeting, use `rg` or MCP tools to discover files first.
+
+### Codex Session Continuity
+
+**Resume Pattern** for related tasks:
 ```bash
-# Step 1: Enhance the description
-SlashCommand(command="/enhance-prompt \"[description]\"")
+# First task - establish session
+codex -C [dir] --full-auto exec "[task]" --skip-git-repo-check -s danger-full-access
 
-# Step 2: Use enhanced output for execution
-# Enhanced output provides:
-# - INTENT: Clear technical goal
-# - CONTEXT: Session memory + codebase patterns
-# - ACTION: Specific implementation steps
-# - ATTENTION: Critical constraints
+# Related task - continue session
+codex --full-auto exec "[related-task]" resume --last --skip-git-repo-check -s danger-full-access
 ```
 
-**Example**:
-```bash
-# User: /gemini:execute --enhance "fix login"
+Use `resume --last` when current task extends/relates to previous execution. See intelligent-tools-strategy.md for auto-resume rules.
 
-# Step 1: Enhance
-/enhance-prompt "fix login"
-# Returns:
-# INTENT: Debug authentication failure in login flow
-# CONTEXT: JWT auth in src/auth/, known token expiry issue
-# ACTION: Fix token validation → update refresh logic → test flow
-# ATTENTION: Preserve existing session management
+## Parameters
 
-# Step 2: Execute with enhanced context
-gemini --all-files -p "@{src/auth/**/*} @{CLAUDE.md}
-Implementation: Debug authentication failure in login flow
-Focus: Token validation, refresh logic, test flow
-Constraints: Preserve existing session management"
-```
-
-**Note**: `--enhance` only applies to Description Mode. Task ID Mode uses task JSON directly.
-
-## Execution Modes
-
-### 1. Description Mode (supports --enhance)
-**Input**: Natural language description
-```bash
-/gemini:execute "implement JWT authentication with middleware"
-/gemini:execute --enhance "implement JWT authentication with middleware"
-```
-**Process**: [Optional: Enhance] → Keyword analysis → Pattern inference → Context collection → Execution
-
-### 2. Task ID Mode (no --enhance)
-**Input**: Workflow task identifier
-```bash
-/gemini:execute IMPL-001
-```
-**Process**: Task JSON parsing → Scope analysis → Context integration → Execution
-
-## Context Inference Logic
-
-**Auto-selects relevant files based on:**
-- **Keywords**: "auth" → `@{**/*auth*,**/*user*}`
-- **Technology**: "React" → `@{src/**/*.{jsx,tsx}}`
-- **Task Type**: "api" → `@{**/api/**/*,**/routes/**/*}`
-- **Always includes**: `@{CLAUDE.md,**/*CLAUDE.md}`
-
-## Command Options
-
-| Option | Purpose |
-|--------|---------|
-| `--debug` | Verbose execution logging |
-| `--save-session` | Save complete execution session to workflow |
+- `--tool <codex|gemini|qwen>` - Select CLI tool (default: gemini)
+- `--enhance` - Enhance input with `/enhance-prompt` first (Description Mode only)
+- `<description|task-id>` - Natural language description or task identifier
+- `--debug` - Verbose logging
+- `--save-session` - Save execution to workflow session
 
 ## Workflow Integration
 
-### Session Management
-⚠️ **Auto-detects active session**: Checks `.workflow/.active-*` marker file
+**Session Management**: Auto-detects `.workflow/.active-*` marker
+- Active session: Save to `.workflow/WFS-[id]/.chat/execute-[timestamp].md`
+- No session: Create new session or save to scratchpad
 
-**Session storage:**
-- **Active session exists**: Saves to `.workflow/WFS-[topic]/.chat/execute-[timestamp].md`
-- **No active session**: Creates new session directory
+**Task Integration**: Load from `.task/[TASK-ID].json`, update status, generate summary
+
+## Output Routing
+
+**Execution Log Destination**:
+- **IF** active workflow session exists:
+  - Save to `.workflow/WFS-[id]/.chat/execute-[timestamp].md`
+  - Update task status in `.task/[TASK-ID].json` (if task ID provided)
+  - Generate summary in `.workflow/WFS-[id]/.summaries/[TASK-ID]-summary.md`
+- **ELSE** (no active session):
+  - **Option 1**: Create new workflow session for task
+  - **Option 2**: Save to `.workflow/.scratchpad/execute-[description]-[timestamp].md`
+
+**Output Files** (when active session exists):
+- Execution log: `.workflow/WFS-[id]/.chat/execute-[timestamp].md`
+- Task summary: `.workflow/WFS-[id]/.summaries/[TASK-ID]-summary.md` (if task ID)
+- Modified code: Project files per implementation
+
+**Examples**:
+- During session `WFS-auth-system`, executing `IMPL-001`:
+  - Log: `.workflow/WFS-auth-system/.chat/execute-20250105-143022.md`
+  - Summary: `.workflow/WFS-auth-system/.summaries/IMPL-001-summary.md`
+- No session, ad-hoc implementation:
+  - Log: `.workflow/.scratchpad/execute-jwt-auth-20250105-143045.md`
+
+## Command Template
 
-### Task Integration
-```bash
-# Execute specific workflow task
-/gemini:execute IMPL-001
-
-# Loads from: .task/IMPL-001.json
-# Uses: task context, brainstorming refs, scope definitions
-# Updates: workflow status, generates summary
-```
-
-## Execution Templates
-
-**Core Guidelines**: @~/.claude/workflows/intelligent-tools-strategy.md
-
-### Permission Requirements
-
-**Gemini Write Access** (when file modifications needed):
-- Add `--approval-mode yolo` flag for auto-approval
-- Required for: file creation, modification, deletion
-
-### User Description Template
-```bash
-cd [target-directory] && ~/.claude/scripts/gemini-wrapper --approval-mode yolo -p "
-PURPOSE: [clear implementation goal from description]
-TASK: [specific implementation task]
-CONTEXT: @{inferred_patterns} @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Implementation code with file:line locations, test cases, integration guidance
-RULES: [template reference if applicable] | [constraints]
-"
-```
-
-**Example**:
 ```bash
+# Gemini/Qwen: MODE=write with --approval-mode yolo
 cd . && ~/.claude/scripts/gemini-wrapper --approval-mode yolo -p "
-PURPOSE: Implement JWT authentication with middleware
-TASK: Create authentication system with token validation
-CONTEXT: @{**/*auth*,**/*middleware*} @{CLAUDE.md}
-EXPECTED: Auth service, middleware, tests with file modifications
-RULES: Follow existing auth patterns | Security best practices
+PURPOSE: [implementation goal]
+TASK: [specific implementation]
+MODE: write
+CONTEXT: @{CLAUDE.md} [auto-detected files]
+EXPECTED: Working implementation with code changes
+RULES: [constraints] | Auto-approve all changes
 "
+
+# Codex: MODE=auto with danger-full-access
+codex -C . --full-auto exec "
+PURPOSE: [implementation goal]
+TASK: [specific implementation]
+MODE: auto
+CONTEXT: [auto-detected files]
+EXPECTED: Complete implementation with tests
+" --skip-git-repo-check -s danger-full-access
 ```
 
-### Task ID Template
+## Examples
+
+**Basic Implementation** (⚠️ modifies code):
 ```bash
-cd [task-directory] && ~/.claude/scripts/gemini-wrapper --approval-mode yolo -p "
-PURPOSE: [task_title]
-TASK: Execute [task-id] implementation
-CONTEXT: @{task_files} @{brainstorming_refs} @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Complete implementation following acceptance criteria
-RULES: $(cat [task_template]) | Task type: [task_type], Scope: [task_scope]
-"
+/cli:execute "implement JWT authentication with middleware"
+# Executes: Creates auth middleware, updates routes, modifies config
+# Result: NEW/MODIFIED code files with JWT implementation
 ```
 
-**Example**:
+**Enhanced Implementation** (⚠️ modifies code):
 ```bash
-cd .workflow/WFS-123 && ~/.claude/scripts/gemini-wrapper --approval-mode yolo -p "
-PURPOSE: Implement user profile editing
-TASK: Execute IMPL-001 implementation
-CONTEXT: @{src/user/**/*} @{.brainstorming/product-owner/analysis.md} @{CLAUDE.md}
-EXPECTED: Profile edit API, UI components, validation, tests
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/development/feature.txt) | Type: feature, Scope: user module
-"
+/cli:execute --enhance "implement JWT authentication"
+# Step 1: Enhance to expand requirements
+# Step 2: Execute implementation with auto-approval
+# Result: Complete auth system with MODIFIED code files
 ```
 
-## Auto-Generated Outputs
-
-### 1. Implementation Summary
-**Location**: `.summaries/[TASK-ID]-summary.md` or auto-generated ID
-
-```markdown
-# Task Summary: [Task-ID] [Description]
-
-## Implementation
-- **Files Modified**: [file:line references]
-- **Features Added**: [specific functionality]
-- **Context Used**: [inferred patterns]
-
-## Integration
-- [Links to workflow documents]
+**Task Execution** (⚠️ modifies code):
+```bash
+/cli:execute IMPL-001
+# Reads: .task/IMPL-001.json for requirements
+# Executes: Implementation based on task spec
+# Result: Code changes per task definition
 ```
 
-### 2. Execution Session
-**Location**: `.chat/execute-[timestamp].md`
-
-```markdown
-# Execution Session: [Timestamp]
-
-## Input
-[User description or Task ID]
-
-## Context Inference
-[File patterns used with rationale]
-
-## Implementation Results
-[Generated code and modifications]
-
-## Status Updates
-[Workflow integration updates]
+**Codex Implementation** (⚠️ modifies code):
+```bash
+/cli:execute --tool codex "optimize database queries"
+# Executes: Codex with full file access
+# Result: MODIFIED query code, new indexes, updated tests
 ```
 
-## Error Handling
+**Qwen Code Generation** (⚠️ modifies code):
+```bash
+/cli:execute --tool qwen --enhance "refactor auth module"
+# Step 1: Enhanced refactoring plan
+# Step 2: Execute with MODE=write
+# Result: REFACTORED auth code with structural changes
+```
 
-- **Task ID not found**: Lists available tasks
-- **Pattern inference failure**: Uses generic `src/**/*` pattern
-- **Execution failure**: Attempts fallback with simplified context
-- **File modification errors**: Reports specific file/permission issues
+## Comparison with Analysis Commands
 
-## Performance Features
+| Command | Intent | Code Changes | Auto-Approve |
+|---------|--------|--------------|--------------|
+| `/cli:analyze` | Understand code | ❌ NO | N/A |
+| `/cli:chat` | Ask questions | ❌ NO | N/A |
+| `/cli:execute` | **Implement** | ✅ **YES** | ✅ **YES** |
 
-- **Smart caching**: Frequently used pattern mappings
-- **Progressive inference**: Precise → broad pattern fallback
-- **Parallel execution**: When multiple contexts needed
-- **Directory optimization**: Switches to optimal execution path
-
-## Integration Workflow
-
-**Typical sequence:**
-1. `workflow:plan` → Creates tasks
-2. `/gemini:execute IMPL-001` → Executes with YOLO permissions
-3. Auto-updates workflow status and generates summaries
-4. `workflow:review` → Final validation
-
-**vs. `/gemini:analyze`**: Execute performs analysis **and implementation**, analyze is read-only.
+## Notes
 
+- Command templates, YOLO mode details, and session management: see intelligent-tools-strategy.md (loaded in memory)
+- Output routing and scratchpad details: see workflow-architecture.md
+- **⚠️ Code Modification**: This command modifies code - execution logs document changes made

.claude/commands/cli/mode/bug-index.md

@@ -1,23 +1,25 @@
 ---
 name: bug-index
 description: Bug analysis and fix suggestions using CLI tools
-usage: /cli:mode:bug-index [--tool <codex|gemini|qwen>] [--enhance] [--cd "path"] "bug description"
 argument-hint: "[--tool codex|gemini|qwen] [--enhance] [--cd path] bug description"
-examples:
-  - /cli:mode:bug-index "authentication null pointer error"
-  - /cli:mode:bug-index --tool qwen --enhance "login not working"
-  - /cli:mode:bug-index --tool codex --cd "src/auth" "token validation fails"
 allowed-tools: SlashCommand(*), Bash(*)
-model: sonnet
 ---
 
 # CLI Mode: Bug Index (/cli:mode:bug-index)
 
 ## Purpose
 
-Execute systematic bug analysis and fix suggestions using CLI tools with diagnostic template.
+Systematic bug analysis with diagnostic template (`~/.claude/prompt-templates/bug-fix.md`).
 
 **Supported Tools**: codex, gemini (default), qwen
+**Key Feature**: `--cd` flag for directory-scoped analysis
+
+## Parameters
+
+- `--tool <codex|gemini|qwen>` - Tool selection (default: gemini)
+- `--enhance` - Enhance bug description with `/enhance-prompt` first
+- `--cd "path"` - Target directory for focused analysis
+- `<bug-description>` (Required) - Bug description or error message
 
 ## Execution Flow
 
@@ -26,26 +28,33 @@ Execute systematic bug analysis and fix suggestions using CLI tools with diagnos
 3. Parse bug description (original or enhanced)
 4. Detect target directory (from `--cd` or auto-infer)
 5. Build command for selected tool with bug-fix template
-6. Execute analysis
-7. Save to session (if active)
+6. Execute analysis (read-only, provides fix recommendations)
+7. Save to `.workflow/WFS-[id]/.chat/bug-index-[timestamp].md`
 
 ## Core Rules
 
-1. **Enhance First (if flagged)**: Execute `/enhance-prompt` before analysis
-2. **Directory Context**: Use `cd` when `--cd` provided or auto-detected
-3. **Template Required**: Always use bug-fix template
-4. **Session Output**: Save to `.workflow/WFS-[id]/.chat/bug-index-[timestamp].md`
+1. **Analysis Only**: This command analyzes bugs and suggests fixes - it does NOT modify code
+2. **Enhance First (if flagged)**: Execute `/enhance-prompt` before analysis
+3. **Directory Context**: Use `cd` when `--cd` provided or auto-detected
+4. **Template Required**: Always use bug-fix template
+5. **Session Output**: Save analysis results and fix recommendations to session chat
+
+## Analysis Focus (via Template)
+
+- Root cause investigation and diagnosis
+- Code path tracing to locate issues
+- Targeted minimal fix recommendations
+- Impact assessment of proposed changes
 
 ## Command Template
 
-**Core Guidelines**: @~/.claude/workflows/intelligent-tools-strategy.md
-
 ```bash
 cd [directory] && ~/.claude/scripts/gemini-wrapper --all-files -p "
 PURPOSE: [bug analysis goal]
 TASK: Systematic bug analysis and fix recommendations
+MODE: analysis
 CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} [entire codebase in directory]
-EXPECTED: Root cause analysis, code path tracing, targeted fixes
+EXPECTED: Root cause analysis, code path tracing, targeted fix suggestions
 RULES: $(cat ~/.claude/prompt-templates/bug-fix.md) | Bug: [description]
 "
 ```
@@ -56,9 +65,10 @@ RULES: $(cat ~/.claude/prompt-templates/bug-fix.md) | Bug: [description]
 ```bash
 cd . && ~/.claude/scripts/gemini-wrapper --all-files -p "
 PURPOSE: Debug authentication null pointer error
-TASK: Identify root cause and provide fix
+TASK: Identify root cause and provide fix recommendations
+MODE: analysis
 CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Root cause, code path, minimal fix, impact assessment
+EXPECTED: Root cause, code path, minimal fix suggestion, impact assessment
 RULES: $(cat ~/.claude/prompt-templates/bug-fix.md) | Bug: null pointer in login flow
 "
 ```
@@ -68,47 +78,39 @@ RULES: $(cat ~/.claude/prompt-templates/bug-fix.md) | Bug: null pointer in login
 cd src/auth && ~/.claude/scripts/gemini-wrapper --all-files -p "
 PURPOSE: Fix token validation failure
 TASK: Analyze token validation bug in auth module
+MODE: analysis
 CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Validation logic analysis, fix recommendation
+EXPECTED: Validation logic analysis, fix recommendation with minimal changes
 RULES: $(cat ~/.claude/prompt-templates/bug-fix.md) | Bug: token validation fails intermittently
 "
 ```
 
-**With Enhancement**:
+## Bug Investigation Workflow
+
 ```bash
-# User: /gemini:mode:bug-index --enhance "login broken"
+# 1. Find bug-related files
+rg "error_keyword" --files-with-matches
+mcp__code-index__search_code_advanced(pattern="error|exception", file_pattern="*.ts")
 
-# Step 1: Enhance
-/enhance-prompt "login broken"
-# Returns:
-# INTENT: Debug login authentication failure
-# CONTEXT: Known session state issue
-# ACTION: Check session management → verify token → test flow
-
-# Step 2: Analyze with enhanced context
-cd . && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: Debug login authentication failure
-TASK: Analyze session management, token handling, auth flow
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} Known: session state issue
-EXPECTED: Root cause in session/token, targeted fix
-RULES: $(cat ~/.claude/prompt-templates/bug-fix.md) | Focus on session management
-"
+# 2. Execute bug analysis with focused context (analysis only, no code changes)
+/cli:mode:bug-index --cd "src/module" "specific error description"
 ```
 
-## Analysis Focus
+## Output Routing
 
-**Template provides**:
-- **Root Cause Analysis**: Systematic investigation
-- **Code Path Tracing**: Execution flow analysis
-- **Targeted Solutions**: Minimal, specific fixes
-- **Impact Assessment**: Side effect evaluation
+**Output Destination Logic**:
+- **Active session exists AND bug is session-relevant**:
+  - Save to `.workflow/WFS-[id]/.chat/bug-index-[timestamp].md`
+- **No active session OR quick debugging**:
+  - Save to `.workflow/.scratchpad/bug-index-[description]-[timestamp].md`
 
-## Session Output
+**Examples**:
+- During active session `WFS-payment-fix`, analyzing payment bug → `.chat/bug-index-20250105-143022.md`
+- No session, quick null pointer investigation → `.scratchpad/bug-index-null-pointer-20250105-143045.md`
 
-**Location**: `.workflow/WFS-[topic]/.chat/bug-index-[timestamp].md`
+## Notes
 
-**Includes**:
-- Bug description
-- Template used
-- Analysis results
-- Recommended actions
+- Command templates and file patterns: see intelligent-tools-strategy.md (loaded in memory)
+- Scratchpad directory details: see workflow-architecture.md
+- Template path: `~/.claude/prompt-templates/bug-fix.md`
+- Always uses `--all-files` for comprehensive codebase context

.claude/commands/cli/mode/code-analysis.md

@@ -1,23 +1,25 @@
 ---
 name: code-analysis
 description: Deep code analysis and debugging using CLI tools with specialized template
-usage: /cli:mode:code-analysis [--tool <codex|gemini|qwen>] [--enhance] [--cd "path"] "analysis target"
 argument-hint: "[--tool codex|gemini|qwen] [--enhance] [--cd path] analysis target"
-examples:
-  - /cli:mode:code-analysis "analyze authentication flow logic"
-  - /cli:mode:code-analysis --tool qwen --enhance "explain data transformation pipeline"
-  - /cli:mode:code-analysis --tool codex --cd "src/core" "trace execution path for user registration"
 allowed-tools: SlashCommand(*), Bash(*)
-model: sonnet
 ---
 
 # CLI Mode: Code Analysis (/cli:mode:code-analysis)
 
 ## Purpose
 
-Execute systematic code analysis and debugging using CLI tools with specialized code analysis template.
+Systematic code analysis with execution path tracing template (`~/.claude/prompt-templates/code-analysis.md`).
 
 **Supported Tools**: codex, gemini (default), qwen
+**Key Feature**: `--cd` flag for directory-scoped analysis
+
+## Parameters
+
+- `--tool <codex|gemini|qwen>` - Tool selection (default: gemini)
+- `--enhance` - Enhance analysis target with `/enhance-prompt` first
+- `--cd "path"` - Target directory for focused analysis
+- `<analysis-target>` (Required) - Code analysis target or question
 
 ## Execution Flow
 
@@ -26,20 +28,20 @@ Execute systematic code analysis and debugging using CLI tools with specialized
 3. Parse analysis target (original or enhanced)
 4. Detect target directory (from `--cd` or auto-infer)
 5. Build command for selected tool with code-analysis template
-6. Execute deep analysis
-7. Save to session (if active)
+6. Execute deep analysis (read-only, no code modification)
+7. Save to `.workflow/WFS-[id]/.chat/code-analysis-[timestamp].md`
 
 ## Core Rules
 
-1. **Tool Selection**: Use `--tool` value or default to gemini
-2. **Enhance First (if flagged)**: Execute `/enhance-prompt` before analysis
-3. **Directory Context**: Use `cd` when `--cd` provided or auto-detected
-4. **Template Required**: Always use code-analysis template
-5. **Session Output**: Save to `.workflow/WFS-[id]/.chat/code-analysis-[timestamp].md`
+1. **Analysis Only**: This command analyzes code and provides insights - it does NOT modify code
+2. **Tool Selection**: Use `--tool` value or default to gemini
+3. **Enhance First (if flagged)**: Execute `/enhance-prompt` before analysis
+4. **Directory Context**: Use `cd` when `--cd` provided or auto-detected
+5. **Template Required**: Always use code-analysis template
+6. **Session Output**: Save analysis results to session chat
 
-## Analysis Capabilities
+## Analysis Capabilities (via Template)
 
-The code-analysis template provides:
 - **Systematic Code Analysis**: Break down complex code into manageable parts
 - **Execution Path Tracing**: Track variable states and call stacks
 - **Control & Data Flow**: Understand code logic and data transformations
@@ -47,158 +49,74 @@ The code-analysis template provides:
 - **Logical Reasoning**: Explain "why" behind code behavior
 - **Debugging Insights**: Identify potential bugs or inefficiencies
 
-## Command Templates
+## Command Template
 
-**Core Guidelines**: @~/.claude/workflows/intelligent-tools-strategy.md
-
-### Gemini (Default)
 ```bash
 cd [directory] && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: [analysis goal from target]
-TASK: Deep code analysis with execution path tracing
+PURPOSE: [analysis goal]
+TASK: Systematic code analysis and execution path tracing
+MODE: analysis
 CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} [entire codebase in directory]
-EXPECTED: Systematic analysis, call flow diagram, data transformations, logical explanation
-RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on [specific aspect]
+EXPECTED: Execution trace, call flow diagram, debugging insights
+RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on [aspect]
 "
 ```
 
-### Qwen
-```bash
-cd [directory] && ~/.claude/scripts/qwen-wrapper --all-files -p "
-PURPOSE: [analysis goal from target]
-TASK: Architecture-level code analysis and pattern recognition
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} [entire codebase in directory]
-EXPECTED: Architectural insights, design patterns, code structure analysis
-RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on [specific aspect]
-"
-```
-
-### Codex
-```bash
-codex -C [directory] --full-auto exec "
-PURPOSE: [analysis goal from target]
-TASK: Deep code inspection with debugging insights
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} [entire codebase in directory]
-EXPECTED: Execution trace, bug identification, optimization opportunities
-RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on [specific aspect]
-" --skip-git-repo-check -s danger-full-access
-```
-
 ## Examples
 
-**Basic Code Analysis (Gemini)**:
+**Basic Code Analysis**:
 ```bash
 cd . && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: Analyze authentication flow logic
-TASK: Trace authentication execution path and identify key functions
+PURPOSE: Trace authentication execution flow
+TASK: Analyze complete auth flow from request to response
+MODE: analysis
 CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Step-by-step flow, call diagram, data passing between functions
-RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on control flow and security
+EXPECTED: Step-by-step execution trace with call diagram, variable states
+RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on control flow
 "
 ```
 
-**Architecture Analysis (Qwen)**:
+**Directory-Specific Analysis**:
 ```bash
-# User: /cli:mode:code-analysis --tool qwen "explain data transformation pipeline"
-
-cd . && ~/.claude/scripts/qwen-wrapper --all-files -p "
-PURPOSE: Explain data transformation pipeline architecture
-TASK: Analyze data flow and transformation patterns
+cd src/auth && ~/.claude/scripts/gemini-wrapper --all-files -p "
+PURPOSE: Understand JWT token validation logic
+TASK: Trace JWT validation from middleware to service layer
+MODE: analysis
 CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Pipeline structure, transformation stages, data format changes
-RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on data flow and patterns
+EXPECTED: Validation flow diagram, token lifecycle analysis
+RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on security
 "
 ```
 
-**Deep Debugging (Codex)**:
-```bash
-# User: /cli:mode:code-analysis --tool codex --cd "src/core" "trace execution path for user registration"
+## Code Tracing Workflow
 
-codex -C src/core --full-auto exec "
-PURPOSE: Trace execution path for user registration
-TASK: Deep analysis of registration flow with debugging insights
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Complete execution trace, variable states, potential issues
-RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on edge cases and error handling
-" --skip-git-repo-check -s danger-full-access
+```bash
+# 1. Find entry points and related files
+rg "function.*authenticate|class.*AuthService" --files-with-matches
+mcp__code-index__search_code_advanced(pattern="authenticate|login", file_pattern="*.ts")
+
+# 2. Build call graph understanding
+# entry → middleware → service → repository
+
+# 3. Execute deep analysis (analysis only, no code changes)
+/cli:mode:code-analysis --cd "src" "trace execution from entry point"
 ```
 
-**With Enhancement**:
-```bash
-# User: /cli:mode:code-analysis --enhance "why is login slow"
+## Output Routing
 
-# Step 1: Enhance
-/enhance-prompt "why is login slow"
-# Returns:
-# INTENT: Identify performance bottlenecks in login flow
-# CONTEXT: Authentication module, database queries
-# ACTION: Trace execution path → identify slow operations → suggest optimizations
+**Output Destination Logic**:
+- **Active session exists AND analysis is session-relevant**:
+  - Save to `.workflow/WFS-[id]/.chat/code-analysis-[timestamp].md`
+- **No active session OR standalone analysis**:
+  - Save to `.workflow/.scratchpad/code-analysis-[description]-[timestamp].md`
 
-# Step 2: Analyze with enhanced context
-cd . && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: Identify performance bottlenecks in login flow
-TASK: Trace login execution path and measure operation costs
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} @{**/*auth*,**/*login*}
-EXPECTED: Performance analysis, bottleneck identification, optimization recommendations
-RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on performance and database queries
-"
-```
+**Examples**:
+- During active session `WFS-auth-refactor`, analyzing auth flow → `.chat/code-analysis-20250105-143022.md`
+- No session, tracing request lifecycle → `.scratchpad/code-analysis-request-flow-20250105-143045.md`
 
-## Analysis Output Structure
+## Notes
 
-Based on code-analysis.md template, output includes:
-
-### 1. 思考过程 (Thinking Process)
-- Analysis strategy and approach
-- Key assumptions about code behavior
-
-### 2. 对问题的理解 (Understanding)
-- Restate analysis target
-- Confirm understanding of requirements
-
-### 3. 核心解答 (Core Answer)
-- Direct, concise answer to analysis question
-
-### 4. 详细分析与调用逻辑 (Detailed Analysis)
-- **代码段识别**: Relevant code sections
-- **执行流程**: Step-by-step execution flow
-- **调用图**: Visual call flow diagram with symbols:
-  - `───►` Function call
-  - `◄───` Return
-  - `│` Continuation
-  - `├─` Intermediate step
-  - `└─` Last step in block
-- **数据传递**: Data passing and state changes
-- **逻辑解释**: Why code behaves this way
-
-### 5. 总结 (Summary)
-- Key findings and recommendations
-
-## Session Output
-
-**Location**: `.workflow/WFS-[topic]/.chat/code-analysis-[timestamp].md`
-
-**Includes**:
-- Analysis target
-- Template used
-- Complete structured analysis
-- Call flow diagrams
-- Debugging insights
-- Recommendations
-
-## Use Cases
-
-| Use Case | Best Tool | Focus |
-|----------|-----------|-------|
-| **Understand execution flow** | gemini | Call sequences, data flow |
-| **Architectural patterns** | qwen | Design patterns, structure |
-| **Performance debugging** | codex | Bottlenecks, optimizations |
-| **Bug investigation** | codex | Error paths, edge cases |
-| **Code review** | gemini | Logic correctness, clarity |
-| **Refactoring planning** | qwen | Structure improvements |
-
-## Tool Selection Guide
-
-- **Gemini**: Best for general code understanding and tracing
-- **Qwen**: Best for architectural analysis and pattern recognition
-- **Codex**: Best for deep debugging and performance analysis
+- Command templates and file patterns: see intelligent-tools-strategy.md (loaded in memory)
+- Scratchpad directory details: see workflow-architecture.md
+- Template path: `~/.claude/prompt-templates/code-analysis.md`
+- Always uses `--all-files` for comprehensive code context

.claude/commands/cli/mode/plan.md

@@ -1,23 +1,25 @@
 ---
 name: plan
 description: Project planning and architecture analysis using CLI tools
-usage: /cli:mode:plan [--tool <codex|gemini|qwen>] [--enhance] [--cd "path"] "topic"
 argument-hint: "[--tool codex|gemini|qwen] [--enhance] [--cd path] topic"
-examples:
-  - /cli:mode:plan "design user dashboard"
-  - /cli:mode:plan --tool qwen --enhance "plan microservices migration"
-  - /cli:mode:plan --tool codex --cd "src/auth" "authentication system"
 allowed-tools: SlashCommand(*), Bash(*)
-model: sonnet
 ---
 
 # CLI Mode: Plan (/cli:mode:plan)
 
 ## Purpose
 
-Execute planning and architecture analysis using CLI tools with specialized template.
+Comprehensive planning and architecture analysis with strategic planning template (`~/.claude/prompt-templates/plan.md`).
 
 **Supported Tools**: codex, gemini (default), qwen
+**Key Feature**: `--cd` flag for directory-scoped planning
+
+## Parameters
+
+- `--tool <codex|gemini|qwen>` - Tool selection (default: gemini)
+- `--enhance` - Enhance topic with `/enhance-prompt` first
+- `--cd "path"` - Target directory for focused planning
+- `<topic>` (Required) - Planning topic or architectural question
 
 ## Execution Flow
 
@@ -26,79 +28,93 @@ Execute planning and architecture analysis using CLI tools with specialized temp
 3. Parse topic (original or enhanced)
 4. Detect target directory (from `--cd` or auto-infer)
 5. Build command for selected tool with planning template
-6. Execute analysis
-7. Save to session (if active)
+6. Execute analysis (read-only, no code modification)
+7. Save to `.workflow/WFS-[id]/.chat/plan-[timestamp].md`
 
 ## Core Rules
 
-1. **Enhance First (if flagged)**: Execute `/enhance-prompt` before planning
-2. **Directory Context**: Use `cd` when `--cd` provided or auto-detected
-3. **Template Required**: Always use planning template
-4. **Session Output**: Save to `.workflow/WFS-[id]/.chat/plan-[timestamp].md`
+1. **Analysis Only**: This command provides planning recommendations and insights - it does NOT modify code
+2. **Enhance First (if flagged)**: Execute `/enhance-prompt` before planning
+3. **Directory Context**: Use `cd` when `--cd` provided or auto-detected
+4. **Template Required**: Always use planning template
+5. **Session Output**: Save analysis results to session chat
+
+## Planning Capabilities (via Template)
+
+- Strategic architecture insights and recommendations
+- Implementation roadmaps and suggestions
+- Key technical decisions analysis
+- Risk assessment
+- Resource planning
 
 ## Command Template
 
-**Core Guidelines**: @~/.claude/workflows/intelligent-tools-strategy.md
-
 ```bash
 cd [directory] && ~/.claude/scripts/gemini-wrapper --all-files -p "
 PURPOSE: [planning goal from topic]
 TASK: Comprehensive planning and architecture analysis
+MODE: analysis
 CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} [entire codebase in directory]
-EXPECTED: Strategic insights, implementation roadmap, key decisions
+EXPECTED: Strategic insights, implementation recommendations, key decisions
 RULES: $(cat ~/.claude/prompt-templates/plan.md) | Focus on [topic area]
 "
 ```
 
 ## Examples
 
-**Basic Planning**:
+**Basic Planning Analysis**:
 ```bash
 cd . && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: Design user dashboard feature architecture
-TASK: Comprehensive architecture planning for dashboard
+PURPOSE: Design user dashboard architecture
+TASK: Plan dashboard component structure and data flow
+MODE: analysis
 CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Architecture design, component structure, implementation roadmap
-RULES: $(cat ~/.claude/prompt-templates/plan.md) | Focus on scalability and UX
+EXPECTED: Architecture recommendations, component design, data flow diagram
+RULES: $(cat ~/.claude/prompt-templates/plan.md) | Focus on scalability
 "
 ```
 
-**Directory-Specific**:
+**Directory-Specific Planning**:
 ```bash
-cd src/auth && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: Plan authentication system redesign
-TASK: Analyze current auth and plan improvements
+cd src/api && ~/.claude/scripts/gemini-wrapper --all-files -p "
+PURPOSE: Plan API refactoring strategy
+TASK: Analyze current API structure and recommend improvements
+MODE: analysis
 CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Migration strategy, security improvements, timeline
-RULES: $(cat ~/.claude/prompt-templates/plan.md) | Focus on security and backward compatibility
+EXPECTED: Refactoring roadmap, breaking change analysis, migration plan
+RULES: $(cat ~/.claude/prompt-templates/plan.md) | Maintain backward compatibility
 "
 ```
 
-**With Enhancement**:
+## Planning Workflow
+
 ```bash
-# User: /gemini:mode:plan --enhance "fix auth issues"
+# 1. Discover project structure
+~/.claude/scripts/get_modules_by_depth.sh
+mcp__code-index__find_files(pattern="*.ts")
 
-# Step 1: Enhance
-/enhance-prompt "fix auth issues"
-# Returns structured planning context
+# 2. Gather existing architecture info
+rg "architecture|design" --files-with-matches
 
-# Step 2: Plan with enhanced input
-cd . && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: [enhanced goal]
-TASK: [enhanced task description]
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} [enhanced context]
-EXPECTED: Strategic plan with enhanced requirements
-RULES: $(cat ~/.claude/prompt-templates/plan.md) | [enhanced constraints]
-"
+# 3. Execute planning analysis (analysis only, no code changes)
+/cli:mode:plan "topic for strategic planning"
 ```
 
-## Session Output
+## Output Routing
 
-**Location**: `.workflow/WFS-[topic]/.chat/plan-[timestamp].md`
+**Output Destination Logic**:
+- **Active session exists AND planning is session-relevant**:
+  - Save to `.workflow/WFS-[id]/.chat/plan-[timestamp].md`
+- **No active session OR exploratory planning**:
+  - Save to `.workflow/.scratchpad/plan-[description]-[timestamp].md`
 
-**Includes**:
-- Planning topic
-- Template used
-- Analysis results
-- Implementation roadmap
-- Key decisions
+**Examples**:
+- During active session `WFS-dashboard`, planning dashboard architecture → `.chat/plan-20250105-143022.md`
+- No session, exploring new feature idea → `.scratchpad/plan-feature-idea-20250105-143045.md`
+
+## Notes
+
+- Command templates and file patterns: see intelligent-tools-strategy.md (loaded in memory)
+- Scratchpad directory details: see workflow-architecture.md
+- Template path: `~/.claude/prompt-templates/plan.md`
+- Always uses `--all-files` for comprehensive project context

.claude/commands/enhance-prompt.md

@@ -1,12 +1,7 @@
 ---
 name: enhance-prompt
 description: Context-aware prompt enhancement using session memory and codebase analysis
-usage: /enhance-prompt <user_input>
 argument-hint: "user input to enhance"
-examples:
-  - /enhance-prompt "add user profile editing"
-  - /enhance-prompt "fix login button"
-  - /enhance-prompt "clean up the payment code"
 ---
 
 ## Overview

.claude/commands/task/breakdown.md

@@ -1,12 +1,7 @@
 ---
 name: breakdown
 description: Intelligent task decomposition with context-aware subtask generation
-usage: /task:breakdown <task-id>
-argument-hint: task-id
-examples:
-  - /task:breakdown IMPL-1
-  - /task:breakdown IMPL-1.1
-  - /task:breakdown impl-3
+argument-hint: "task-id"
 ---
 
 # Task Breakdown Command (/task:breakdown)

.claude/commands/task/create.md

@@ -1,12 +1,7 @@
 ---
 name: create
 description: Create implementation tasks with automatic context awareness
-usage: /task:create "title"
-argument-hint: "task title"
-examples:
-  - /task:create "Implement user authentication"
-  - /task:create "Build REST API endpoints"
-  - /task:create "Fix login validation bug"
+argument-hint: "\"task title\""
 ---
 
 # Task Create Command (/task:create)

.claude/commands/task/execute.md

@@ -1,12 +1,7 @@
 ---
 name: execute
 description: Execute tasks with appropriate agents and context-aware orchestration
-usage: /task:execute <task-id>
-argument-hint: task-id
-examples:
-  - /task:execute IMPL-1
-  - /task:execute IMPL-1.2
-  - /task:execute IMPL-3
+argument-hint: "task-id"
 ---
 
 ### 🚀 **Command Overview: `/task:execute`**

.claude/commands/task/replan.md

@@ -1,12 +1,7 @@
 ---
 name: replan
 description: Replan individual tasks with detailed user input and change tracking
-usage: /task:replan <task-id> [input]
-argument-hint: task-id ["text"|file.md|ISS-001]
-examples:
-  - /task:replan IMPL-1 "Add OAuth2 authentication support"
-  - /task:replan IMPL-1 updated-specs.md
-  - /task:replan IMPL-1 ISS-001
+argument-hint: "task-id [\"text\"|file.md]"
 ---
 
 # Task Replan Command (/task:replan)
@@ -38,12 +33,6 @@ Replans individual tasks with multiple input options, change tracking, and versi
 ```
 Supports: .md, .txt, .json, .yaml
 
-### Issue Reference
-```bash
-/task:replan IMPL-1 ISS-001
-```
-Loads issue description and requirements
-
 ### Interactive Mode
 ```bash
 /task:replan IMPL-1 --interactive

.claude/commands/update-memory-full.md

@@ -1,40 +1,50 @@
 ---
 name: update-memory-full
 description: Complete project-wide CLAUDE.md documentation update
-usage: /update-memory-full
-examples:
-  - /update-memory-full                      # Full project documentation update
+argument-hint: "[--tool gemini|qwen|codex]"
 ---
 
 ### 🚀 Command Overview: `/update-memory-full`
 
 Complete project-wide documentation update using depth-parallel execution.
 
+**Tool Selection**:
+- **Gemini (default)**: Documentation generation, pattern recognition, architecture review
+- **Qwen**: Architecture analysis, system design documentation
+- **Codex**: Implementation validation, code quality analysis
+
 ### 📝 Execution Template
 
 ```bash
 #!/bin/bash
 # Complete project-wide CLAUDE.md documentation update
 
-# Step 1: Code Index architecture analysis
+# Step 1: Parse tool selection (default: gemini)
+tool="gemini"
+[[ "$*" == *"--tool qwen"* ]] && tool="qwen"
+[[ "$*" == *"--tool codex"* ]] && tool="codex"
+
+# Step 2: Code Index architecture analysis
 mcp__code-index__search_code_advanced(pattern="class|function|interface", file_pattern="**/*.{ts,js,py}")
 mcp__code-index__find_files(pattern="**/*.{md,json,yaml,yml}")
 
-# Step 2: Cache git changes
+# Step 3: Cache git changes
 Bash(git add -A 2>/dev/null || true)
 
-# Step 3: Get and display project structure
+# Step 4: Get and display project structure
 modules=$(Bash(~/.claude/scripts/get_modules_by_depth.sh list))
 count=$(echo "$modules" | wc -l)
 
-# Step 3: Analysis handover → Model takes control
+# Step 5: Analysis handover → Model takes control
 # BASH_EXECUTION_STOPS → MODEL_ANALYSIS_BEGINS
 
 # Pseudocode flow:
 # IF (module_count > 20 OR complex_project_detected):
-#     → Task "Complex project full update" subagent_type: "memory-gemini-bridge"
+#     → Task "Complex project full update" subagent_type: "memory-bridge"
 # ELSE:
 #     → Present plan and WAIT FOR USER APPROVAL before execution
+#
+# Pass tool parameter to update_module_claude.sh: "$tool"
 ```
 
 ### 🧠 Model Analysis Phase
@@ -43,9 +53,9 @@ After the bash script completes the initial analysis, the model takes control to
 
 1. **Analyze Complexity**: Review module count and project context
 2. **Parse CLAUDE.md Status**: Extract which modules have/need CLAUDE.md files
-3. **Choose Strategy**: 
+3. **Choose Strategy**:
    - Simple projects: Present execution plan with CLAUDE.md paths to user
-   - Complex projects: Delegate to memory-gemini-bridge agent
+   - Complex projects: Delegate to memory-bridge agent
 4. **Present Detailed Plan**: Show user exactly which CLAUDE.md files will be created/updated
 5. **⚠️ CRITICAL: WAIT FOR USER APPROVAL**: No execution without explicit user consent
 
@@ -56,17 +66,19 @@ After the bash script completes the initial analysis, the model takes control to
 Model will present detailed plan:
 ```
 📋 Update Plan:
+  Tool: [gemini|qwen|codex] (from --tool parameter)
+
   NEW CLAUDE.md files (X):
     - ./src/components/CLAUDE.md
     - ./src/services/CLAUDE.md
-  
+
   UPDATE existing CLAUDE.md files (Y):
     - ./CLAUDE.md
     - ./src/CLAUDE.md
     - ./tests/CLAUDE.md
 
   Total: N CLAUDE.md files will be processed
-  
+
   ⚠️ Confirm execution? (y/n)
 ```
 
@@ -84,7 +96,7 @@ depth_modules = organize_by_depth(modules)
 FOR depth FROM max_depth DOWN TO 0:
     FOR each module IN depth_modules[depth]:
         WHILE active_jobs >= 4: wait(0.1)
-        Bash(~/.claude/scripts/update_module_claude.sh "$module" "full" &)
+        Bash(~/.claude/scripts/update_module_claude.sh "$module" "full" "$tool" &)
     wait_all_jobs()
 
 # Step 6: Safety check and restore staging state
@@ -102,13 +114,43 @@ Bash(git status --short)
 ```
 
 **For Complex Projects (>20 modules):**
-The model will delegate to the memory-gemini-bridge agent using the Task tool:
-```
+
+The model will delegate to the memory-bridge agent with structured context:
+
+```javascript
 Task "Complex project full update"
-prompt: "Execute full documentation update for [count] modules using depth-parallel execution"
-subagent_type: "memory-gemini-bridge"
+subagent_type: "memory-bridge"
+prompt: `
+CONTEXT:
+- Total modules: ${module_count}
+- Tool: ${tool}  // from --tool parameter, default: gemini
+- Mode: full
+- Existing CLAUDE.md: ${existing_count}
+- New CLAUDE.md needed: ${new_count}
+
+MODULE LIST:
+${modules_output}  // Full output from get_modules_by_depth.sh list
+
+REQUIREMENTS:
+1. Use TodoWrite to track each depth level before execution
+2. Process depths 5→0 sequentially, max 4 parallel jobs per depth
+3. Command format: update_module_claude.sh "<path>" "full" "${tool}" &
+4. Extract exact path from "depth:N|path:<PATH>|..." format
+5. Verify all ${module_count} modules are processed
+6. Run safety check after completion
+7. Display git status
+
+Execute depth-parallel updates for all modules.
+`
 ```
 
+**Agent receives complete context:**
+- Module count and tool selection
+- Full structured module list
+- Clear execution requirements
+- Path extraction format
+- Success criteria
+
 
 ### 📚 Usage Examples
 

.claude/commands/update-memory-related.md

@@ -1,15 +1,18 @@
 ---
 name: update-memory-related
 description: Context-aware CLAUDE.md documentation updates based on recent changes
-usage: /update-memory-related
-examples:
-  - /update-memory-related                    # Update documentation based on recent changes
+argument-hint: "[--tool gemini|qwen|codex]"
 ---
 
 ### 🚀 Command Overview: `/update-memory-related`
 
 Context-aware documentation update for modules affected by recent changes.
 
+**Tool Selection**:
+- **Gemini (default)**: Documentation generation, pattern recognition, architecture review
+- **Qwen**: Architecture analysis, system design documentation
+- **Codex**: Implementation validation, code quality analysis
+
 
 ### 📝 Execution Template
 
@@ -17,30 +20,37 @@ Context-aware documentation update for modules affected by recent changes.
 #!/bin/bash
 # Context-aware CLAUDE.md documentation update
 
-# Step 1: Code Index refresh and architecture analysis
+# Step 1: Parse tool selection (default: gemini)
+tool="gemini"
+[[ "$*" == *"--tool qwen"* ]] && tool="qwen"
+[[ "$*" == *"--tool codex"* ]] && tool="codex"
+
+# Step 2: Code Index refresh and architecture analysis
 mcp__code-index__refresh_index()
 mcp__code-index__search_code_advanced(pattern="class|function|interface", file_pattern="**/*.{ts,js,py}")
 
-# Step 2: Detect changed modules (before staging)
+# Step 3: Detect changed modules (before staging)
 changed=$(Bash(~/.claude/scripts/detect_changed_modules.sh list))
 
-# Step 3: Cache git changes (protect current state)
+# Step 4: Cache git changes (protect current state)
 Bash(git add -A 2>/dev/null || true)
 
-# Step 3: Use detected changes or fallback
+# Step 5: Use detected changes or fallback
 if [ -z "$changed" ]; then
     changed=$(Bash(~/.claude/scripts/get_modules_by_depth.sh list | head -10))
 fi
 count=$(echo "$changed" | wc -l)
 
-# Step 4: Analysis handover → Model takes control  
+# Step 6: Analysis handover → Model takes control
 # BASH_EXECUTION_STOPS → MODEL_ANALYSIS_BEGINS
 
 # Pseudocode flow:
 # IF (change_count > 15 OR complex_changes_detected):
-#     → Task "Complex project related update" subagent_type: "memory-gemini-bridge"
+#     → Task "Complex project related update" subagent_type: "memory-bridge"
 # ELSE:
 #     → Present plan and WAIT FOR USER APPROVAL before execution
+#
+# Pass tool parameter to update_module_claude.sh: "$tool"
 ```
 
 ### 🧠 Model Analysis Phase
@@ -51,7 +61,7 @@ After the bash script completes change detection, the model takes control to:
 2. **Parse CLAUDE.md Status**: Extract which changed modules have/need CLAUDE.md files
 3. **Choose Strategy**: 
    - Simple changes: Present execution plan with CLAUDE.md paths to user
-   - Complex changes: Delegate to memory-gemini-bridge agent
+   - Complex changes: Delegate to memory-bridge agent
 4. **Present Detailed Plan**: Show user exactly which CLAUDE.md files will be created/updated for changed modules
 5. **⚠️ CRITICAL: WAIT FOR USER APPROVAL**: No execution without explicit user consent
 
@@ -62,18 +72,20 @@ After the bash script completes change detection, the model takes control to:
 Model will present detailed plan for affected modules:
 ```
 📋 Related Update Plan:
+  Tool: [gemini|qwen|codex] (from --tool parameter)
+
   CHANGED modules affecting CLAUDE.md:
-  
+
   NEW CLAUDE.md files (X):
     - ./src/api/auth/CLAUDE.md  [new module]
     - ./src/utils/helpers/CLAUDE.md  [new module]
-  
+
   UPDATE existing CLAUDE.md files (Y):
     - ./src/api/CLAUDE.md  [parent of changed auth/]
     - ./src/CLAUDE.md  [root level]
 
   Total: N CLAUDE.md files will be processed for recent changes
-  
+
   ⚠️ Confirm execution? (y/n)
 ```
 
@@ -91,7 +103,7 @@ depth_modules = organize_by_depth(changed_modules)
 FOR depth FROM max_depth DOWN TO 0:
     FOR each module IN depth_modules[depth]:
         WHILE active_jobs >= 4: wait(0.1)
-        Bash(~/.claude/scripts/update_module_claude.sh "$module" "related" &)
+        Bash(~/.claude/scripts/update_module_claude.sh "$module" "related" "$tool" &)
     wait_all_jobs()
 
 # Step 6: Safety check and restore staging state
@@ -109,13 +121,44 @@ Bash(git diff --stat)
 ```
 
 **For Complex Changes (>15 modules):**
-The model will delegate to the memory-gemini-bridge agent using the Task tool:
-```
+
+The model will delegate to the memory-bridge agent with structured context:
+
+```javascript
 Task "Complex project related update"
-prompt: "Execute context-aware update for [count] changed modules using depth-parallel execution"
-subagent_type: "memory-gemini-bridge"
+subagent_type: "memory-bridge"
+prompt: `
+CONTEXT:
+- Total modules: ${change_count}
+- Tool: ${tool}  // from --tool parameter, default: gemini
+- Mode: related
+- Changed modules detected via: detect_changed_modules.sh
+- Existing CLAUDE.md: ${existing_count}
+- New CLAUDE.md needed: ${new_count}
+
+MODULE LIST:
+${changed_modules_output}  // Full output from detect_changed_modules.sh list
+
+REQUIREMENTS:
+1. Use TodoWrite to track each depth level before execution
+2. Process depths sequentially (deepest→shallowest), max 4 parallel jobs per depth
+3. Command format: update_module_claude.sh "<path>" "related" "${tool}" &
+4. Extract exact path from "depth:N|path:<PATH>|..." format
+5. Verify all ${change_count} modules are processed
+6. Run safety check after completion
+7. Display git diff --stat
+
+Execute depth-parallel updates for changed modules only.
+`
 ```
 
+**Agent receives complete context:**
+- Changed module count and tool selection
+- Full structured module list (changed only)
+- Clear execution requirements with "related" mode
+- Path extraction format
+- Success criteria
+
 
 ### 📚 Usage Examples
 

.claude/commands/version.md

@@ -1,9 +1,6 @@
 ---
 name: version
 description: Display version information and check for updates
-usage: /version
-examples:
-  - /version
 allowed-tools: Bash(*)
 ---
 
@@ -170,8 +167,8 @@ Bash: bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-W
 
 **Scenario 3: Development version**
 ```
-✨ You are running a development version (3.3.0-dev)
-This is newer than the latest stable release (v3.2.2)
+✨ You are running a development version (3.4.0-dev)
+This is newer than the latest stable release (v3.3.0)
 ```
 
 ## Simple Bash Commands

.claude/commands/workflow/action-plan-verify.md

@@ -0,0 +1,417 @@
+---
+name: action-plan-verify
+description: Perform non-destructive cross-artifact consistency and quality analysis of IMPL_PLAN.md and task.json before execution
+argument-hint: "[optional: --session session-id]"
+allowed-tools: Read(*), TodoWrite(*), Glob(*), Bash(*)
+---
+
+## User Input
+
+```text
+$ARGUMENTS
+```
+
+You **MUST** consider the user input before proceeding (if not empty).
+
+## Goal
+
+Identify inconsistencies, duplications, ambiguities, and underspecified items between action planning artifacts (`IMPL_PLAN.md`, `task.json`) and brainstorming artifacts (`synthesis-specification.md`) before implementation. This command MUST run only after `/workflow:plan` has successfully produced complete `IMPL_PLAN.md` and task JSON files.
+
+## Operating Constraints
+
+**STRICTLY READ-ONLY**: Do **not** modify any files. Output a structured analysis report. Offer an optional remediation plan (user must explicitly approve before any follow-up editing commands).
+
+**Synthesis Authority**: The `synthesis-specification.md` is **authoritative** for requirements and design decisions. Any conflicts between IMPL_PLAN/tasks and synthesis are automatically CRITICAL and require adjustment of the plan/tasks—not reinterpretation of requirements.
+
+## Execution Steps
+
+### 1. Initialize Analysis Context
+
+```bash
+# Detect active workflow session
+IF --session parameter provided:
+    session_id = provided session
+ELSE:
+    CHECK: .workflow/.active-* marker files
+    IF active_session EXISTS:
+        session_id = get_active_session()
+    ELSE:
+        ERROR: "No active workflow session found. Use --session <session-id>"
+        EXIT
+
+# Derive absolute paths
+session_dir = .workflow/WFS-{session}
+brainstorm_dir = session_dir/.brainstorming
+task_dir = session_dir/.task
+
+# Validate required artifacts
+SYNTHESIS = brainstorm_dir/synthesis-specification.md
+IMPL_PLAN = session_dir/IMPL_PLAN.md
+TASK_FILES = Glob(task_dir/*.json)
+
+# Abort if missing
+IF NOT EXISTS(SYNTHESIS):
+    ERROR: "synthesis-specification.md not found. Run /workflow:brainstorm:synthesis first"
+    EXIT
+
+IF NOT EXISTS(IMPL_PLAN):
+    ERROR: "IMPL_PLAN.md not found. Run /workflow:plan first"
+    EXIT
+
+IF TASK_FILES.count == 0:
+    ERROR: "No task JSON files found. Run /workflow:plan first"
+    EXIT
+```
+
+### 2. Load Artifacts (Progressive Disclosure)
+
+Load only minimal necessary context from each artifact:
+
+**From synthesis-specification.md**:
+- Functional Requirements (IDs, descriptions, acceptance criteria)
+- Non-Functional Requirements (IDs, targets)
+- Business Requirements (IDs, success metrics)
+- Key Architecture Decisions
+- Risk factors and mitigation strategies
+- Implementation Roadmap (high-level phases)
+
+**From IMPL_PLAN.md**:
+- Summary and objectives
+- Context Analysis
+- Implementation Strategy
+- Task Breakdown Summary
+- Success Criteria
+- Brainstorming Artifacts References (if present)
+
+**From task.json files**:
+- Task IDs
+- Titles and descriptions
+- Status
+- Dependencies (depends_on, blocks)
+- Context (requirements, focus_paths, acceptance, artifacts)
+- Flow control (pre_analysis, implementation_approach)
+- Meta (complexity, priority, use_codex)
+
+### 3. Build Semantic Models
+
+Create internal representations (do not include raw artifacts in output):
+
+**Requirements inventory**:
+- Each functional/non-functional/business requirement with stable ID
+- Requirement text, acceptance criteria, priority
+
+**Architecture decisions inventory**:
+- ADRs from synthesis
+- Technology choices
+- Data model references
+
+**Task coverage mapping**:
+- Map each task to one or more requirements (by ID reference or keyword inference)
+- Map each requirement to covering tasks
+
+**Dependency graph**:
+- Task-to-task dependencies (depends_on, blocks)
+- Requirement-level dependencies (from synthesis)
+
+### 4. Detection Passes (Token-Efficient Analysis)
+
+Focus on high-signal findings. Limit to 50 findings total; aggregate remainder in overflow summary.
+
+#### A. Requirements Coverage Analysis
+
+- **Orphaned Requirements**: Requirements in synthesis with zero associated tasks
+- **Unmapped Tasks**: Tasks with no clear requirement linkage
+- **NFR Coverage Gaps**: Non-functional requirements (performance, security, scalability) not reflected in tasks
+
+#### B. Consistency Validation
+
+- **Requirement Conflicts**: Tasks contradicting synthesis requirements
+- **Architecture Drift**: IMPL_PLAN architecture not matching synthesis ADRs
+- **Terminology Drift**: Same concept named differently across IMPL_PLAN and tasks
+- **Data Model Inconsistency**: Tasks referencing entities/fields not in synthesis data model
+
+#### C. Dependency Integrity
+
+- **Circular Dependencies**: Task A depends on B, B depends on C, C depends on A
+- **Missing Dependencies**: Task requires outputs from another task but no explicit dependency
+- **Broken Dependencies**: Task depends on non-existent task ID
+- **Logical Ordering Issues**: Implementation tasks before foundational setup without dependency note
+
+#### D. Synthesis Alignment
+
+- **Priority Conflicts**: High-priority synthesis requirements mapped to low-priority tasks
+- **Success Criteria Mismatch**: IMPL_PLAN success criteria not covering synthesis acceptance criteria
+- **Risk Mitigation Gaps**: Critical risks in synthesis without corresponding mitigation tasks
+
+#### E. Task Specification Quality
+
+- **Ambiguous Focus Paths**: Tasks with vague or missing focus_paths
+- **Underspecified Acceptance**: Tasks without clear acceptance criteria
+- **Missing Artifacts References**: Tasks not referencing relevant brainstorming artifacts in context.artifacts
+- **Weak Flow Control**: Tasks without clear implementation_approach or pre_analysis steps
+- **Missing Target Files**: Tasks without flow_control.target_files specification
+
+#### F. Duplication Detection
+
+- **Overlapping Task Scope**: Multiple tasks with nearly identical descriptions
+- **Redundant Requirements Coverage**: Same requirement covered by multiple tasks without clear partitioning
+
+#### G. Feasibility Assessment
+
+- **Complexity Misalignment**: Task marked "simple" but requires multiple file modifications
+- **Resource Conflicts**: Parallel tasks requiring same resources/files
+- **Skill Gap Risks**: Tasks requiring skills not in team capability assessment (from synthesis)
+
+### 5. Severity Assignment
+
+Use this heuristic to prioritize findings:
+
+- **CRITICAL**:
+  - Violates synthesis authority (requirement conflict)
+  - Core requirement with zero coverage
+  - Circular dependencies
+  - Broken dependencies
+
+- **HIGH**:
+  - NFR coverage gaps
+  - Priority conflicts
+  - Missing risk mitigation tasks
+  - Ambiguous acceptance criteria
+
+- **MEDIUM**:
+  - Terminology drift
+  - Missing artifacts references
+  - Weak flow control
+  - Logical ordering issues
+
+- **LOW**:
+  - Style/wording improvements
+  - Minor redundancy not affecting execution
+
+### 6. Produce Compact Analysis Report
+
+Output a Markdown report (no file writes) with the following structure:
+
+```markdown
+## Action Plan Verification Report
+
+**Session**: WFS-{session-id}
+**Generated**: {timestamp}
+**Artifacts Analyzed**: synthesis-specification.md, IMPL_PLAN.md, {N} task files
+
+---
+
+### Executive Summary
+
+- **Overall Risk Level**: CRITICAL | HIGH | MEDIUM | LOW
+- **Recommendation**: BLOCK_EXECUTION | PROCEED_WITH_FIXES | PROCEED_WITH_CAUTION | PROCEED
+- **Critical Issues**: {count}
+- **High Issues**: {count}
+- **Medium Issues**: {count}
+- **Low Issues**: {count}
+
+---
+
+### Findings Summary
+
+| ID | Category | Severity | Location(s) | Summary | Recommendation |
+|----|----------|----------|-------------|---------|----------------|
+| C1 | Coverage | CRITICAL | synthesis:FR-03 | Requirement "User auth" has zero task coverage | Add authentication implementation task |
+| H1 | Consistency | HIGH | IMPL-1.2 vs synthesis:ADR-02 | Task uses REST while synthesis specifies GraphQL | Align task with ADR-02 decision |
+| M1 | Specification | MEDIUM | IMPL-2.1 | Missing context.artifacts reference | Add @synthesis reference |
+| L1 | Duplication | LOW | IMPL-3.1, IMPL-3.2 | Similar scope | Consider merging |
+
+(Add one row per finding; generate stable IDs prefixed by severity initial.)
+
+---
+
+### Requirements Coverage Analysis
+
+| Requirement ID | Requirement Summary | Has Task? | Task IDs | Priority Match | Notes |
+|----------------|---------------------|-----------|----------|----------------|-------|
+| FR-01 | User authentication | ✅ Yes | IMPL-1.1, IMPL-1.2 | ✅ Match | Complete |
+| FR-02 | Data export | ✅ Yes | IMPL-2.3 | ⚠️ Mismatch | High req → Med priority task |
+| FR-03 | Profile management | ❌ No | - | - | **CRITICAL: Zero coverage** |
+| NFR-01 | Response time <200ms | ❌ No | - | - | **HIGH: No performance tasks** |
+
+**Coverage Metrics**:
+- Functional Requirements: 85% (17/20 covered)
+- Non-Functional Requirements: 40% (2/5 covered)
+- Business Requirements: 100% (5/5 covered)
+
+---
+
+### Unmapped Tasks
+
+| Task ID | Title | Issue | Recommendation |
+|---------|-------|-------|----------------|
+| IMPL-4.5 | Refactor utils | No requirement linkage | Link to technical debt or remove |
+
+---
+
+### Dependency Graph Issues
+
+**Circular Dependencies**: None detected ✅
+
+**Broken Dependencies**:
+- IMPL-2.3 depends on "IMPL-2.4" (non-existent)
+
+**Logical Ordering Issues**:
+- IMPL-5.1 (integration test) has no dependency on IMPL-1.* (implementation tasks)
+
+---
+
+### Synthesis Alignment Issues
+
+| Issue Type | Synthesis Reference | IMPL_PLAN/Task | Impact | Recommendation |
+|------------|---------------------|----------------|--------|----------------|
+| Architecture Conflict | synthesis:ADR-01 (JWT auth) | IMPL_PLAN uses session cookies | HIGH | Update IMPL_PLAN to use JWT |
+| Priority Mismatch | synthesis:FR-02 (High) | IMPL-2.3 (Medium) | MEDIUM | Elevate task priority |
+| Missing Risk Mitigation | synthesis:Risk-03 (API rate limits) | No mitigation tasks | HIGH | Add rate limiting implementation task |
+
+---
+
+### Task Specification Quality Issues
+
+**Missing Artifacts References**: 12 tasks lack context.artifacts
+**Weak Flow Control**: 5 tasks lack implementation_approach
+**Missing Target Files**: 8 tasks lack flow_control.target_files
+
+**Sample Issues**:
+- IMPL-1.2: No context.artifacts reference to synthesis
+- IMPL-3.1: Missing flow_control.target_files specification
+- IMPL-4.2: Vague focus_paths ["src/"] - needs refinement
+
+---
+
+### Feasibility Concerns
+
+| Concern | Tasks Affected | Issue | Recommendation |
+|---------|----------------|-------|----------------|
+| Skill Gap | IMPL-6.1, IMPL-6.2 | Requires Kubernetes expertise not in team | Add training task or external consultant |
+| Resource Conflict | IMPL-3.1, IMPL-3.2 | Both modify src/auth/service.ts in parallel | Add dependency or serialize |
+
+---
+
+### Metrics
+
+- **Total Requirements**: 30 (20 functional, 5 non-functional, 5 business)
+- **Total Tasks**: 25
+- **Overall Coverage**: 77% (23/30 requirements with ≥1 task)
+- **Critical Issues**: 2
+- **High Issues**: 5
+- **Medium Issues**: 8
+- **Low Issues**: 3
+
+---
+
+### Next Actions
+
+#### If CRITICAL Issues Exist (Current Status: 2 CRITICAL)
+**Recommendation**: ❌ **BLOCK EXECUTION** - Resolve CRITICAL issues before proceeding
+
+**Required Actions**:
+1. **CRITICAL**: Add authentication implementation tasks to cover FR-03
+2. **CRITICAL**: Add performance optimization tasks to cover NFR-01
+
+#### If Only HIGH/MEDIUM/LOW Issues
+**Recommendation**: ⚠️ **PROCEED WITH CAUTION** - Issues are non-blocking but should be addressed
+
+**Suggested Improvements**:
+1. Add context.artifacts references to all tasks (use /task:replan)
+2. Fix broken dependency IMPL-2.3 → IMPL-2.4
+3. Add flow_control.target_files to underspecified tasks
+
+#### Command Suggestions
+```bash
+# Fix critical coverage gaps
+/task:create "Implement user authentication (FR-03)"
+/task:create "Add performance optimization (NFR-01)"
+
+# Refine existing tasks
+/task:replan IMPL-1.2 "Add context.artifacts and target_files"
+
+# Update IMPL_PLAN if architecture drift detected
+# (Manual edit required)
+```
+```
+
+### 7. Provide Remediation Options
+
+At end of report, ask the user:
+
+```markdown
+### 🔧 Remediation Options
+
+Would you like me to:
+1. **Generate task suggestions** for unmapped requirements (no auto-creation)
+2. **Provide specific edit commands** for top N issues (you execute manually)
+3. **Create remediation checklist** for systematic fixing
+
+(Do NOT apply fixes automatically - this is read-only analysis)
+```
+
+### 8. Update Session Metadata
+
+```json
+{
+  "phases": {
+    "PLAN": {
+      "status": "completed",
+      "action_plan_verification": {
+        "completed": true,
+        "completed_at": "timestamp",
+        "overall_risk_level": "HIGH",
+        "recommendation": "PROCEED_WITH_FIXES",
+        "issues": {
+          "critical": 2,
+          "high": 5,
+          "medium": 8,
+          "low": 3
+        },
+        "coverage": {
+          "functional_requirements": 0.85,
+          "non_functional_requirements": 0.40,
+          "business_requirements": 1.00
+        },
+        "report_path": ".workflow/WFS-{session}/.process/ACTION_PLAN_VERIFICATION.md"
+      }
+    }
+  }
+}
+```
+
+## Operating Principles
+
+### Context Efficiency
+- **Minimal high-signal tokens**: Focus on actionable findings
+- **Progressive disclosure**: Load artifacts incrementally
+- **Token-efficient output**: Limit findings table to 50 rows; summarize overflow
+- **Deterministic results**: Rerunning without changes produces consistent IDs and counts
+
+### Analysis Guidelines
+- **NEVER modify files** (this is read-only analysis)
+- **NEVER hallucinate missing sections** (if absent, report them accurately)
+- **Prioritize synthesis violations** (these are always CRITICAL)
+- **Use examples over exhaustive rules** (cite specific instances)
+- **Report zero issues gracefully** (emit success report with coverage statistics)
+
+### Verification Taxonomy
+- **Coverage**: Requirements → Tasks mapping
+- **Consistency**: Cross-artifact alignment
+- **Dependencies**: Task ordering and relationships
+- **Synthesis Alignment**: Adherence to authoritative requirements
+- **Task Quality**: Specification completeness
+- **Feasibility**: Implementation risks
+
+## Behavior Rules
+
+- **If no issues found**: Report "✅ Action plan verification passed. No issues detected." and suggest proceeding to `/workflow:execute`.
+- **If CRITICAL issues exist**: Recommend blocking execution until resolved.
+- **If only HIGH/MEDIUM issues**: User may proceed with caution, but provide improvement suggestions.
+- **If IMPL_PLAN.md or task files missing**: Instruct user to run `/workflow:plan` first.
+- **Always provide actionable remediation suggestions**: Don't just identify problems—suggest solutions.
+
+## Context
+
+{ARGS}

.claude/commands/workflow/brainstorm/artifacts.md

@@ -1,12 +1,7 @@
 ---
 name: artifacts
 description: Generate role-specific topic-framework.md dynamically based on selected roles
-usage: /workflow:brainstorm:artifacts "<topic>" [--roles "role1,role2,role3"]
 argument-hint: "topic or challenge description for framework generation"
-examples:
-  - /workflow:brainstorm:artifacts "Build real-time collaboration feature"
-  - /workflow:brainstorm:artifacts "Optimize database performance" --roles "system-architect,data-architect,subject-matter-expert"
-  - /workflow:brainstorm:artifacts "Implement secure authentication system" --roles "ui-designer,ux-expert,subject-matter-expert"
 allowed-tools: TodoWrite(*), Read(*), Write(*), Bash(*), Glob(*)
 ---
 
@@ -368,4 +363,4 @@ ELSE:
 ### Integration Points
 - **Compatible with**: Other brainstorming commands in the same session
 - **Builds foundation for**: More detailed planning and implementation phases
-- **Outputs used by**: `/workflow:brainstorm:synthesis` command for cross-analysis integration
+- **Outputs used by**: `/workflow:brainstorm:synthesis` command for cross-analysis integration

.claude/commands/workflow/brainstorm/auto-parallel.md

@@ -1,12 +1,7 @@
 ---
 name: auto-parallel
 description: Parallel brainstorming automation with dynamic role selection and concurrent execution
-usage: /workflow:brainstorm:auto-parallel "<topic>"
 argument-hint: "topic or challenge description"
-examples:
-  - /workflow:brainstorm:auto-parallel "Build real-time collaboration feature"
-  - /workflow:brainstorm:auto-parallel "Optimize database performance for millions of users"
-  - /workflow:brainstorm:auto-parallel "Implement secure authentication system"
 allowed-tools: SlashCommand(*), Task(*), TodoWrite(*), Read(*), Write(*), Bash(*), Glob(*)
 ---
 
@@ -327,4 +322,4 @@ Command coordination model: artifacts command → parallel role analysis → syn
 - **Agent self-management**: Agents handle their own workflow and validation
 - **Concurrent operation**: No inter-agent dependencies enabling parallel execution
 - **Reference-based synthesis**: Post-processing integration without content duplication
-- **TodoWrite orchestration**: Progress tracking and workflow control throughout entire process
+- **TodoWrite orchestration**: Progress tracking and workflow control throughout entire process

.claude/commands/workflow/brainstorm/auto-squeeze.md

@@ -1,12 +1,7 @@
 ---
 name: auto-squeeze
 description: Orchestrate 3-phase brainstorming workflow by executing commands sequentially
-usage: /workflow:brainstorm:auto-squeeze "<topic>"
 argument-hint: "topic or challenge description for coordinated brainstorming"
-examples:
-  - /workflow:brainstorm:auto-squeeze "Build real-time collaboration feature"
-  - /workflow:brainstorm:auto-squeeze "Optimize database performance for millions of users"
-  - /workflow:brainstorm:auto-squeeze "Implement secure authentication system"
 allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*), Glob(*)
 ---
 
@@ -255,4 +250,4 @@ Return summary to user
 ✅ Update TodoWrite after each role completion
 ✅ Execute Phase 3 (synthesis) after all roles complete
 ✅ Validate synthesis-report.md exists
-✅ Return summary with all generated files
+✅ Return summary with all generated files

.claude/commands/workflow/brainstorm/data-architect.md

@@ -1,12 +1,7 @@
 ---
 name: data-architect
 description: Generate or update data-architect/analysis.md addressing topic-framework discussion points
-usage: /workflow:brainstorm:data-architect [topic]
 argument-hint: "optional topic - uses existing framework if available"
-examples:
-  - /workflow:brainstorm:data-architect
-  - /workflow:brainstorm:data-architect "user analytics data pipeline"
-  - /workflow:brainstorm:data-architect "real-time data processing system"
 allowed-tools: Task(conceptual-planning-agent), TodoWrite(*), Read(*), Write(*)
 ---
 
@@ -202,4 +197,4 @@ TodoWrite({
 ### Integration Points
 - **Framework Reference**: @../topic-framework.md for structured discussion points
 - **Cross-Role Synthesis**: Data architecture insights available for synthesis-report.md integration
-- **Agent Autonomy**: Independent execution with framework guidance
+- **Agent Autonomy**: Independent execution with framework guidance

.claude/commands/workflow/brainstorm/product-manager.md

@@ -1,12 +1,7 @@
 ---
 name: product-manager
 description: Generate or update product-manager/analysis.md addressing topic-framework discussion points
-usage: /workflow:brainstorm:product-manager [topic]
 argument-hint: "optional topic - uses existing framework if available"
-examples:
-  - /workflow:brainstorm:product-manager
-  - /workflow:brainstorm:product-manager "user authentication redesign"
-  - /workflow:brainstorm:product-manager "mobile app performance optimization"
 allowed-tools: Task(conceptual-planning-agent), TodoWrite(*), Read(*), Write(*)
 ---
 

.claude/commands/workflow/brainstorm/product-owner.md

@@ -1,12 +1,7 @@
 ---
 name: product-owner
 description: Generate or update product-owner/analysis.md addressing topic-framework discussion points
-usage: /workflow:brainstorm:product-owner [topic]
 argument-hint: "optional topic - uses existing framework if available"
-examples:
-  - /workflow:brainstorm:product-owner
-  - /workflow:brainstorm:product-owner "user authentication redesign"
-  - /workflow:brainstorm:product-owner "mobile app performance optimization"
 allowed-tools: Task(conceptual-planning-agent), TodoWrite(*), Read(*), Write(*)
 ---
 

.claude/commands/workflow/brainstorm/scrum-master.md

@@ -1,12 +1,7 @@
 ---
 name: scrum-master
 description: Generate or update scrum-master/analysis.md addressing topic-framework discussion points
-usage: /workflow:brainstorm:scrum-master [topic]
 argument-hint: "optional topic - uses existing framework if available"
-examples:
-  - /workflow:brainstorm:scrum-master
-  - /workflow:brainstorm:scrum-master "user authentication redesign"
-  - /workflow:brainstorm:scrum-master "mobile app performance optimization"
 allowed-tools: Task(conceptual-planning-agent), TodoWrite(*), Read(*), Write(*)
 ---
 

.claude/commands/workflow/brainstorm/subject-matter-expert.md

@@ -1,12 +1,7 @@
 ---
 name: subject-matter-expert
 description: Generate or update subject-matter-expert/analysis.md addressing topic-framework discussion points
-usage: /workflow:brainstorm:subject-matter-expert [topic]
 argument-hint: "optional topic - uses existing framework if available"
-examples:
-  - /workflow:brainstorm:subject-matter-expert
-  - /workflow:brainstorm:subject-matter-expert "user authentication redesign"
-  - /workflow:brainstorm:subject-matter-expert "mobile app performance optimization"
 allowed-tools: Task(conceptual-planning-agent), TodoWrite(*), Read(*), Write(*)
 ---
 

.claude/commands/workflow/brainstorm/synthesis.md

@@ -1,35 +1,43 @@
 ---
 name: synthesis
-description: Generate synthesis-report.md from topic-framework and role analyses with @ references
-usage: /workflow:brainstorm:synthesis
+description: Generate synthesis-specification.md from topic-framework and role analyses with @ references
 argument-hint: "no arguments required - synthesizes existing framework and role analyses"
-examples:
-  - /workflow:brainstorm:synthesis
 allowed-tools: Read(*), Write(*), TodoWrite(*), Glob(*)
 ---
 
 ## 🧩 **Synthesis Document Generator**
 
 ### Core Function
-**Specialized command for generating synthesis-report.md** that integrates topic-framework.md and all role analysis.md files using @ reference system. Creates comprehensive strategic analysis with cross-role insights.
+**Specialized command for generating synthesis-specification.md** that integrates topic-framework.md and all role analysis.md files using @ reference system. Creates comprehensive implementation specification with cross-role insights.
+
+**Dynamic Role Discovery**: Automatically detects which roles participated in brainstorming by scanning for `*/analysis.md` files. Synthesizes only actual participating roles, not predefined lists.
 
 ### Primary Capabilities
-- **Framework Integration**: Reference topic-framework.md discussion points across all roles
-- **Role Analysis Integration**: Consolidate all role/analysis.md files using @ references
-- **Cross-Framework Comparison**: Compare how each role addressed framework discussion points
+- **Dynamic Role Discovery**: Automatically identifies participating roles at runtime
+- **Framework Integration**: Reference topic-framework.md discussion points across all discovered roles
+- **Role Analysis Integration**: Consolidate all discovered role/analysis.md files using @ references
+- **Cross-Framework Comparison**: Compare how each participating role addressed framework discussion points
 - **@ Reference System**: Create structured references to source documents
 - **Update Detection**: Smart updates when new role analyses are added
+- **Flexible Participation**: Supports any subset of available roles (1 to 9+)
 
 ### Document Integration Model
 **Three-Document Reference System**:
 1. **topic-framework.md** → Structured discussion framework (input)
 2. **[role]/analysis.md** → Role-specific analyses addressing framework (input)
-3. **synthesis-report.md** → Integrated synthesis with @ references (output)
+3. **synthesis-specification.md** → Complete integrated specification (output)
 
 ## ⚙️ **Execution Protocol**
 
-### ⚠️ Direct Execution Only
-**DO NOT use Task tool or delegate to any agent** - This is a document synthesis task using only Read/Write/Glob tools for aggregating existing analyses.
+### ⚠️ Direct Execution by Main Claude
+**Execution Model**: Main Claude directly executes this command without delegating to sub-agents.
+
+**Rationale**:
+- **Full Context Access**: Avoids context transmission loss that occurs with Task tool delegation
+- **Complex Cognitive Analysis**: Leverages main Claude's complete reasoning capabilities for cross-role synthesis
+- **Tool Usage**: Combines Read/Write/Glob tools with main Claude's analytical intelligence
+
+**DO NOT use Task tool** - Main Claude performs intelligent analysis directly while reading/writing files, ensuring no information loss from context passing.
 
 ### Phase 1: Document Discovery & Validation
 ```bash
@@ -51,22 +59,39 @@ IF NOT EXISTS:
 
 ### Phase 2: Role Analysis Discovery
 ```bash
-# Discover available role analyses
+# Dynamically discover available role analyses
 SCAN_DIRECTORY: .workflow/WFS-{session}/.brainstorming/
 FIND_ANALYSES: [
-    */analysis.md files in role directories
+    Scan all subdirectories for */analysis.md files
+    Extract role names from directory names
 ]
+
+# Available roles (for reference, actual participation is dynamic):
+# - product-manager
+# - product-owner
+# - scrum-master
+# - system-architect
+# - ui-designer
+# - ux-expert
+# - data-architect
+# - subject-matter-expert
+# - test-strategist
+
 LOAD_DOCUMENTS: {
     "topic_framework": topic-framework.md,
-    "role_analyses": [discovered analysis.md files],
-    "existing_synthesis": synthesis-report.md (if exists)
+    "role_analyses": [dynamically discovered analysis.md files],
+    "participating_roles": [extract role names from discovered directories],
+    "existing_synthesis": synthesis-specification.md (if exists)
 }
+
+# Note: Not all roles participate in every brainstorming session
+# Only synthesize roles that actually produced analysis.md files
 ```
 
 ### Phase 3: Update Mechanism Check
 ```bash
 # Check for existing synthesis
-IF synthesis-report.md EXISTS:
+IF synthesis-specification.md EXISTS:
     SHOW current synthesis summary to user
     ASK: "Synthesis exists. Do you want to:"
     OPTIONS:
@@ -84,42 +109,60 @@ Initialize synthesis task tracking:
   {"content": "Validate topic-framework.md and role analyses availability", "status": "in_progress", "activeForm": "Validating source documents"},
   {"content": "Load topic framework discussion points structure", "status": "pending", "activeForm": "Loading framework structure"},
   {"content": "Cross-analyze role responses to each framework point", "status": "pending", "activeForm": "Cross-analyzing framework responses"},
-  {"content": "Generate synthesis-report.md with @ references", "status": "pending", "activeForm": "Generating synthesis with references"},
+  {"content": "Generate synthesis-specification.md with @ references", "status": "pending", "activeForm": "Generating synthesis with references"},
   {"content": "Update session metadata with synthesis completion", "status": "pending", "activeForm": "Updating session metadata"}
 ]
 ```
 
-### Phase 4: Cross-Role Analysis Execution
+### Phase 5: Cross-Role Analysis Execution
 
-#### 4.1 Data Collection and Preprocessing
+**Dynamic Role Processing**: The number and types of roles are determined at runtime based on actual analysis.md files discovered in Phase 2.
+
+#### 5.1 Data Collection and Preprocessing
 ```pseudo
-FOR each role_directory in brainstorming_roles:
-    IF role_directory exists:
-        role_analysis = Read(role_directory + "/analysis.md")
-        role_recommendations = Read(role_directory + "/recommendations.md") IF EXISTS
-        role_insights[role] = extract_key_insights(role_analysis)
-        role_recommendations[role] = extract_recommendations(role_analysis)
-        role_concerns[role] = extract_concerns_risks(role_analysis)
+# Iterate over dynamically discovered role analyses
+FOR each discovered_role IN participating_roles:
+    role_directory = brainstorm_dir + "/" + discovered_role
+
+    # Load role analysis (required)
+    role_analysis = Read(role_directory + "/analysis.md")
+
+    # Load optional artifacts if present
+    IF EXISTS(role_directory + "/recommendations.md"):
+        role_recommendations[discovered_role] = Read(role_directory + "/recommendations.md")
     END IF
+
+    # Extract insights from analysis
+    role_insights[discovered_role] = extract_key_insights(role_analysis)
+    role_recommendations[discovered_role] = extract_recommendations(role_analysis)
+    role_concerns[discovered_role] = extract_concerns_risks(role_analysis)
+    role_diagrams[discovered_role] = identify_diagrams_and_visuals(role_analysis)
 END FOR
+
+# Log participating roles for metadata
+participating_role_count = COUNT(participating_roles)
+participating_role_names = participating_roles
 ```
 
-#### 4.2 Cross-Role Insight Analysis
+#### 5.2 Cross-Role Insight Analysis
 ```pseudo
-# Consensus identification
+# Consensus identification (across all participating roles)
 consensus_areas = identify_common_themes(role_insights)
 agreement_matrix = create_agreement_matrix(role_recommendations)
 
-# Disagreement analysis
+# Disagreement analysis (track which specific roles disagree)
 disagreement_areas = identify_conflicting_views(role_insights)
 tension_points = analyze_role_conflicts(role_recommendations)
+FOR each conflict IN disagreement_areas:
+    conflict.dissenting_roles = identify_dissenting_roles(conflict)
+END FOR
 
 # Innovation opportunity extraction
 innovation_opportunities = extract_breakthrough_ideas(role_insights)
 synergy_opportunities = identify_cross_role_synergies(role_insights)
 ```
 
-#### 4.3 Priority and Decision Matrix Generation
+#### 5.3 Priority and Decision Matrix Generation
 ```pseudo
 # Create comprehensive evaluation matrix
 FOR each recommendation:
@@ -137,16 +180,6 @@ SORT recommendations BY priority_score DESC
 ## 📊 **Output Specification**
 
 ### Output Location
-```
-.workflow/WFS-{topic-slug}/.brainstorming/
-├── topic-framework.md          # Input: Framework structure
-├── [role]/analysis.md          # Input: Role analyses (multiple)
-└── synthesis-report.md         # ★ OUTPUT: Integrated synthesis with @ references
-```
-
-### Streamlined Single-Document Output ⚠️ SIMPLIFIED STRUCTURE
-
-#### Output Document - Single Comprehensive Synthesis
 The synthesis process creates **one consolidated document** that integrates all role perspectives:
 
 ```
@@ -157,30 +190,74 @@ The synthesis process creates **one consolidated document** that integrates all
 ```
 
 #### synthesis-specification.md Structure (Complete Specification)
+
+**Document Purpose**: Defines **"WHAT"** to build - comprehensive requirements and design blueprint.
+**Scope**: High-level features, requirements, and design specifications. Does NOT include executable task breakdown (that's IMPL_PLAN.md's responsibility).
+
 ```markdown
 # [Topic] - Integrated Implementation Specification
 
 **Framework Reference**: @topic-framework.md | **Generated**: [timestamp] | **Session**: WFS-[topic-slug]
 **Source Integration**: All brainstorming role perspectives consolidated
+**Document Type**: Requirements & Design Specification (WHAT to build)
 
 ## Executive Summary
 Strategic overview with key insights, breakthrough opportunities, and implementation priorities.
 
+## Key Designs & Decisions
+### Core Architecture Diagram
+```mermaid
+graph TD
+    A[Component A] --> B[Component B]
+    B --> C[Component C]
+```
+*Reference: @system-architect/analysis.md#architecture-diagram*
+
+### User Journey Map
+![User Journey](./assets/user-journey.png)
+*Reference: @ux-expert/analysis.md#user-journey*
+
+### Data Model Overview
+```mermaid
+erDiagram
+    USER ||--o{ ORDER : places
+    ORDER ||--|{ LINE-ITEM : contains
+```
+*Reference: @data-architect/analysis.md#data-model*
+
+### Architecture Decision Records (ADRs)
+**ADR-01: [Decision Title]**
+- **Context**: Background and problem statement
+- **Decision**: Chosen approach
+- **Rationale**: Why this approach was selected
+- **Reference**: @system-architect/analysis.md#adr-01
+
+## Controversial Points & Alternatives
+| Point | Adopted Solution | Alternative Solution(s) | Decision Rationale | Dissenting Roles |
+|-------|------------------|-------------------------|--------------------| -----------------|
+| Authentication | JWT Token (@security-expert) | Session-Cookie (@system-architect) | Stateless API support for multi-platform | System Architect noted session performance benefits |
+| UI Framework | React (@ui-designer) | Vue.js (@subject-matter-expert) | Team expertise and ecosystem maturity | Subject Matter Expert preferred Vue for learning curve |
+
+*This section preserves decision context and rejected alternatives for future reference.*
+
 ## Requirements & Acceptance Criteria
 ### Functional Requirements
-| ID | Description | Source | Priority | Acceptance | Dependencies |
-|----|-------------|--------|----------|------------|--------------|
-| FR-01 | Core feature | @role/analysis.md | High | Criteria | None |
+| ID | Description | Rationale Summary | Source | Priority | Acceptance | Dependencies |
+|----|-------------|-------------------|--------|----------|------------|--------------|
+| FR-01 | User authentication | Enable secure multi-platform access | @product-manager/analysis.md | High | User can login via email/password | None |
+| FR-02 | Data export | User-requested analytics feature | @product-owner/analysis.md | Medium | Export to CSV/JSON | FR-01 |
 
 ### Non-Functional Requirements
-| ID | Description | Target | Validation |
-|----|-------------|--------|------------|
-| NFR-01 | Performance | <200ms | Testing |
+| ID | Description | Rationale Summary | Target | Validation | Source |
+|----|-------------|-------------------|--------|------------|--------|
+| NFR-01 | Response time | UX research shows <200ms critical | <200ms | Load testing | @ux-expert/analysis.md |
+| NFR-02 | Data encryption | Compliance requirement | AES-256 | Security audit | @security-expert/analysis.md |
 
 ### Business Requirements
-| ID | Description | Value | Success Metric |
-|----|-------------|-------|----------------|
-| BR-01 | User engagement | High | 80% retention |
+| ID | Description | Rationale Summary | Value | Success Metric | Source |
+|----|-------------|-------------------|-------|----------------|--------|
+| BR-01 | User retention | Market analysis shows engagement gap | High | 80% 30-day retention | @product-manager/analysis.md |
+| BR-02 | Revenue growth | Business case justification | High | 25% MRR increase | @product-owner/analysis.md |
 
 ## Design Specifications
 ### UI/UX Guidelines
@@ -201,7 +278,34 @@ Strategic overview with key insights, breakthrough opportunities, and implementa
 - Compliance requirements and regulations
 - Technical quality and domain-specific patterns
 
-## Implementation Roadmap
+## Process & Collaboration Concerns
+**Consolidated from**: @scrum-master/analysis.md, @product-owner/analysis.md
+
+### Team Capability Assessment
+| Required Skill | Current Level | Gap Analysis | Mitigation Strategy | Reference |
+|----------------|---------------|--------------|---------------------|-----------|
+| Kubernetes | Intermediate | Need advanced knowledge | Training + external consultant | @scrum-master/analysis.md |
+| React Hooks | Advanced | Team ready | None | @scrum-master/analysis.md |
+
+### Process Risks
+| Risk | Impact | Probability | Mitigation | Owner |
+|------|--------|-------------|------------|-------|
+| Cross-team API dependency | High | Medium | Early API contract definition | @scrum-master/analysis.md |
+| UX-Dev alignment gap | Medium | High | Weekly design sync meetings | @ux-expert/analysis.md |
+
+### Collaboration Patterns
+- **Design-Dev Pairing**: UI Designer and Frontend Dev pair programming for complex interactions
+- **Architecture Reviews**: Weekly arch review for system-level decisions
+- **User Testing Cadence**: Bi-weekly UX testing sessions with real users
+- **Reference**: @scrum-master/analysis.md#collaboration
+
+### Timeline Constraints
+- **Blocking Dependencies**: Project-X API must complete before Phase 2
+- **Resource Constraints**: Only 2 backend developers available in Q1
+- **External Dependencies**: Third-party OAuth provider integration timeline
+- **Reference**: @scrum-master/analysis.md#constraints
+
+## Implementation Roadmap (High-Level)
 ### Development Phases
 **Phase 1** (0-3 months): Foundation and core features
 **Phase 2** (3-6 months): Advanced features and integrations
@@ -212,10 +316,12 @@ Strategic overview with key insights, breakthrough opportunities, and implementa
 - Testing strategy and quality assurance
 - Deployment and monitoring approach
 
-### Task Breakdown
-- Epic and feature mapping aligned with requirements
-- Sprint planning guidance with dependency management
-- Resource allocation and timeline recommendations
+### Feature Grouping (Epic-Level)
+- High-level feature grouping and prioritization
+- Epic-level dependencies and sequencing
+- Strategic milestones and release planning
+
+**Note**: Detailed task breakdown into executable work items is handled by `/workflow:plan` → `IMPL_PLAN.md`
 
 ## Risk Assessment & Mitigation
 ### Critical Risks Identified
@@ -235,6 +341,9 @@ Strategic overview with key insights, breakthrough opportunities, and implementa
 
 ### Streamlined Status Synchronization
 Upon completion, update `workflow-session.json`:
+
+**Dynamic Role Participation**: The `participating_roles` and `roles_synthesized` values are determined at runtime based on actual analysis.md files discovered.
+
 ```json
 {
   "phases": {
@@ -242,22 +351,47 @@ Upon completion, update `workflow-session.json`:
       "status": "completed",
       "synthesis_completed": true,
       "completed_at": "timestamp",
-      "participating_roles": ["product-manager", "product-owner", "scrum-master", "system-architect", "ui-designer", "ux-expert", "data-architect", "subject-matter-expert", "test-strategist"],
+      "participating_roles": ["<dynamically-discovered-role-1>", "<dynamically-discovered-role-2>", "..."],
+      "available_roles": ["product-manager", "product-owner", "scrum-master", "system-architect", "ui-designer", "ux-expert", "data-architect", "subject-matter-expert", "test-strategist"],
       "consolidated_output": {
         "synthesis_specification": ".workflow/WFS-{topic}/.brainstorming/synthesis-specification.md"
       },
       "synthesis_quality": {
         "role_integration": "complete",
         "requirement_coverage": "comprehensive",
+        "decision_transparency": "alternatives_documented",
+        "process_risks_identified": true,
         "implementation_readiness": "ready"
       },
       "content_metrics": {
-        "roles_synthesized": 9,
-        "functional_requirements": 25,
-        "non_functional_requirements": 12,
-        "business_requirements": 8,
-        "implementation_phases": 3,
-        "risk_factors_identified": 8
+        "roles_synthesized": "<COUNT(participating_roles)>",
+        "functional_requirements": "<dynamic-count>",
+        "non_functional_requirements": "<dynamic-count>",
+        "business_requirements": "<dynamic-count>",
+        "architecture_decisions": "<dynamic-count>",
+        "controversial_points": "<dynamic-count>",
+        "diagrams_included": "<dynamic-count>",
+        "process_risks": "<dynamic-count>",
+        "team_skill_gaps": "<dynamic-count>",
+        "implementation_phases": "<dynamic-count>",
+        "risk_factors_identified": "<dynamic-count>"
+      }
+    }
+  }
+}
+```
+
+**Example with actual values**:
+```json
+{
+  "phases": {
+    "BRAINSTORM": {
+      "status": "completed",
+      "participating_roles": ["product-manager", "system-architect", "ui-designer", "ux-expert", "scrum-master"],
+      "content_metrics": {
+        "roles_synthesized": 5,
+        "functional_requirements": 18,
+        "controversial_points": 2
       }
     }
   }
@@ -268,28 +402,96 @@ Upon completion, update `workflow-session.json`:
 
 ### Required Synthesis Elements
 - [ ] Integration of all available role analyses with comprehensive coverage
-- [ ] Clear identification of consensus areas and disagreement points
+- [ ] **Key Designs & Decisions**: Architecture diagrams, user journey maps, ADRs documented
+- [ ] **Controversial Points**: Disagreement points, alternatives, and decision rationale captured
+- [ ] **Process Concerns**: Team capability gaps, process risks, collaboration patterns identified
 - [ ] Quantified priority recommendation matrix with evaluation criteria
 - [ ] Actionable implementation plan with phased approach
 - [ ] Comprehensive risk assessment with mitigation strategies
 
 ### Synthesis Analysis Quality Standards
 - [ ] **Completeness**: Integrates all available role analyses without gaps
+- [ ] **Visual Clarity**: Key diagrams (architecture, data model, user journey) included via Mermaid or images
+- [ ] **Decision Transparency**: Documents not just decisions, but alternatives and why they were rejected
 - [ ] **Insight Generation**: Identifies cross-role patterns and deep insights
-- [ ] **Actionability**: Provides specific, executable recommendations and next steps
-- [ ] **Balance**: Considers all role perspectives and addresses concerns
+- [ ] **Actionability**: Provides specific, executable recommendations with rationale
+- [ ] **Balance**: Considers all role perspectives, including process-oriented roles (Scrum Master)
 - [ ] **Forward-Looking**: Includes long-term strategic and innovation considerations
 
 ### Output Validation Criteria
 - [ ] **Priority-Based**: Recommendations prioritized using multi-dimensional evaluation
-- [ ] **Resource-Aware**: Implementation plans consider resource and time constraints
-- [ ] **Risk-Managed**: Comprehensive risk assessment with mitigation strategies
+- [ ] **Context-Rich**: Each requirement includes rationale summary for immediate understanding
+- [ ] **Resource-Aware**: Team skill gaps and constraints explicitly documented
+- [ ] **Risk-Managed**: Both technical and process risks captured with mitigation strategies
 - [ ] **Measurable Success**: Clear success metrics and monitoring frameworks
 - [ ] **Clear Actions**: Specific next steps with assigned responsibilities and timelines
 
 ### Integration Excellence Standards
-- [ ] **Cross-Role Synthesis**: Successfully identifies and resolves role perspective conflicts
+- [ ] **Cross-Role Synthesis**: Successfully identifies and documents role perspective conflicts
+- [ ] **No Role Marginalization**: Process, UX, and compliance concerns equally visible as functional requirements
 - [ ] **Strategic Coherence**: Recommendations form coherent strategic direction
-- [ ] **Implementation Readiness**: Plans are detailed enough for immediate execution
+- [ ] **Implementation Readiness**: Plans detailed enough for immediate execution, with clear handoff to IMPL_PLAN.md
 - [ ] **Stakeholder Alignment**: Addresses needs and concerns of all key stakeholders
-- [ ] **Continuous Improvement**: Establishes framework for ongoing optimization and learning
+- [ ] **Decision Traceability**: Every major decision traceable to source role analysis via @ references
+- [ ] **Continuous Improvement**: Establishes framework for ongoing optimization and learning
+
+## 🚀 **Recommended Next Steps**
+
+After synthesis completion, follow this recommended workflow:
+
+### Option 1: Standard Planning Workflow (Recommended)
+```bash
+# Step 1: Verify conceptual clarity (Quality Gate)
+/workflow:concept-verify --session WFS-{session-id}
+# → Interactive Q&A (up to 5 questions) to clarify ambiguities in synthesis
+
+# Step 2: Proceed to action planning (after concept verification)
+/workflow:plan --session WFS-{session-id}
+# → Generates IMPL_PLAN.md and task.json files
+
+# Step 3: Verify action plan quality (Quality Gate)
+/workflow:action-plan-verify --session WFS-{session-id}
+# → Read-only analysis to catch issues before execution
+
+# Step 4: Start implementation
+/workflow:execute --session WFS-{session-id}
+```
+
+### Option 2: TDD Workflow
+```bash
+# Step 1: Verify conceptual clarity
+/workflow:concept-verify --session WFS-{session-id}
+
+# Step 2: Generate TDD task chains (RED-GREEN-REFACTOR)
+/workflow:tdd-plan --session WFS-{session-id} "Feature description"
+
+# Step 3: Verify TDD plan quality
+/workflow:action-plan-verify --session WFS-{session-id}
+
+# Step 4: Execute TDD workflow
+/workflow:execute --session WFS-{session-id}
+```
+
+### Quality Gates Explained
+
+**`/workflow:concept-verify`** (Phase 2 - After Brainstorming):
+- **Purpose**: Detect and resolve conceptual ambiguities before detailed planning
+- **Time**: 10-20 minutes (interactive)
+- **Value**: Reduces downstream rework by 40-60%
+- **Output**: Updated synthesis-specification.md with clarifications
+
+**`/workflow:action-plan-verify`** (Phase 4 - After Planning):
+- **Purpose**: Validate IMPL_PLAN.md and task.json consistency and completeness
+- **Time**: 5-10 minutes (read-only analysis)
+- **Value**: Prevents execution of flawed plans, saves 2-5 days
+- **Output**: Verification report with actionable recommendations
+
+### Skip Verification? (Not Recommended)
+
+If you want to skip verification and proceed directly:
+```bash
+/workflow:plan --session WFS-{session-id}
+/workflow:execute --session WFS-{session-id}
+```
+
+⚠️ **Warning**: Skipping verification increases risk of late-stage issues and rework.

.claude/commands/workflow/brainstorm/system-architect.md

@@ -1,11 +1,7 @@
 ---
 name: system-architect
 description: Generate or update system-architect/analysis.md addressing topic-framework discussion points
-usage: /workflow:brainstorm:system-architect [topic]
 argument-hint: "optional topic - uses existing framework if available"
-examples:
-  - /workflow:brainstorm:system-architect
-  - /workflow:brainstorm:system-architect "user authentication redesign"
 allowed-tools: Task(conceptual-planning-agent), TodoWrite(*), Read(*), Write(*)
 ---
 
@@ -369,4 +365,4 @@ System architect perspective provides:
 - [ ] **Resource Planning**: Resource requirements clearly defined and realistic
 - [ ] **Risk Management**: Technical risks identified with mitigation plans
 - [ ] **Performance Validation**: Architecture can meet performance requirements
-- [ ] **Evolution Strategy**: Design allows for future growth and changes
+- [ ] **Evolution Strategy**: Design allows for future growth and changes

.claude/commands/workflow/brainstorm/ui-designer.md

@@ -1,12 +1,7 @@
 ---
 name: ui-designer
 description: Generate or update ui-designer/analysis.md addressing topic-framework discussion points
-usage: /workflow:brainstorm:ui-designer [topic]
 argument-hint: "optional topic - uses existing framework if available"
-examples:
-  - /workflow:brainstorm:ui-designer
-  - /workflow:brainstorm:ui-designer "user authentication redesign"
-  - /workflow:brainstorm:ui-designer "mobile app navigation improvement"
 allowed-tools: Task(conceptual-planning-agent), TodoWrite(*), Read(*), Write(*)
 ---
 
@@ -202,4 +197,4 @@ TodoWrite({
 ### Integration Points
 - **Framework Reference**: @../topic-framework.md for structured discussion points
 - **Cross-Role Synthesis**: UI/UX insights available for synthesis-report.md integration
-- **Agent Autonomy**: Independent execution with framework guidance
+- **Agent Autonomy**: Independent execution with framework guidance

.claude/commands/workflow/brainstorm/ux-expert.md

@@ -1,12 +1,7 @@
 ---
 name: ux-expert
 description: Generate or update ux-expert/analysis.md addressing topic-framework discussion points
-usage: /workflow:brainstorm:ux-expert [topic]
 argument-hint: "optional topic - uses existing framework if available"
-examples:
-  - /workflow:brainstorm:ux-expert
-  - /workflow:brainstorm:ux-expert "user authentication redesign"
-  - /workflow:brainstorm:ux-expert "mobile app performance optimization"
 allowed-tools: Task(conceptual-planning-agent), TodoWrite(*), Read(*), Write(*)
 ---
 

.claude/commands/workflow/concept-clarify.md

@@ -0,0 +1,307 @@
+---
+name: concept-clarify
+description: Identify underspecified areas in brainstorming artifacts through targeted clarification questions before action planning
+argument-hint: "[optional: --session session-id]"
+allowed-tools: Read(*), Write(*), Edit(*), TodoWrite(*), Glob(*), Bash(*)
+---
+
+## User Input
+
+```text
+$ARGUMENTS
+```
+
+You **MUST** consider the user input before proceeding (if not empty).
+
+## Outline
+
+**Goal**: Detect and reduce ambiguity or missing decision points in brainstorming artifacts (synthesis-specification.md, topic-framework.md, role analyses) before moving to action planning phase.
+
+**Timing**: This command runs AFTER `/workflow:brainstorm:synthesis` and BEFORE `/workflow:plan`. It serves as a quality gate to ensure conceptual clarity before detailed task planning.
+
+**Execution steps**:
+
+1. **Session Detection & Validation**
+   ```bash
+   # Detect active workflow session
+   IF --session parameter provided:
+       session_id = provided session
+   ELSE:
+       CHECK: .workflow/.active-* marker files
+       IF active_session EXISTS:
+           session_id = get_active_session()
+       ELSE:
+           ERROR: "No active workflow session found. Use --session <session-id> or start a session."
+           EXIT
+
+   # Validate brainstorming completion
+   brainstorm_dir = .workflow/WFS-{session}/.brainstorming/
+
+   CHECK: brainstorm_dir/synthesis-specification.md
+   IF NOT EXISTS:
+       ERROR: "synthesis-specification.md not found. Run /workflow:brainstorm:synthesis first"
+       EXIT
+
+   CHECK: brainstorm_dir/topic-framework.md
+   IF NOT EXISTS:
+       WARN: "topic-framework.md not found. Verification will be limited."
+   ```
+
+2. **Load Brainstorming Artifacts**
+   ```bash
+   # Load primary artifacts
+   synthesis_spec = Read(brainstorm_dir + "/synthesis-specification.md")
+   topic_framework = Read(brainstorm_dir + "/topic-framework.md") # if exists
+
+   # Discover role analyses
+   role_analyses = Glob(brainstorm_dir + "/*/analysis.md")
+   participating_roles = extract_role_names(role_analyses)
+   ```
+
+3. **Ambiguity & Coverage Scan**
+
+   Perform structured scan using this taxonomy. For each category, mark status: **Clear** / **Partial** / **Missing**.
+
+   **Requirements Clarity**:
+   - Functional requirements specificity and measurability
+   - Non-functional requirements with quantified targets
+   - Business requirements with success metrics
+   - Acceptance criteria completeness
+
+   **Architecture & Design Clarity**:
+   - Architecture decisions with rationale
+   - Data model completeness (entities, relationships, constraints)
+   - Technology stack justification
+   - Integration points and API contracts
+
+   **User Experience & Interface**:
+   - User journey completeness
+   - Critical interaction flows
+   - Error/edge case handling
+   - Accessibility and localization considerations
+
+   **Implementation Feasibility**:
+   - Team capability vs. required skills
+   - External dependencies and failure modes
+   - Resource constraints (timeline, personnel)
+   - Technical constraints and tradeoffs
+
+   **Risk & Mitigation**:
+   - Critical risks identified
+   - Mitigation strategies defined
+   - Success factors clarity
+   - Monitoring and quality gates
+
+   **Process & Collaboration**:
+   - Role responsibilities and handoffs
+   - Collaboration patterns defined
+   - Timeline and milestone clarity
+   - Dependency management strategy
+
+   **Decision Traceability**:
+   - Controversial points documented
+   - Alternatives considered and rejected
+   - Decision rationale clarity
+   - Consensus vs. dissent tracking
+
+   **Terminology & Consistency**:
+   - Canonical terms defined
+   - Consistent naming across artifacts
+   - No unresolved placeholders (TODO, TBD, ???)
+
+   For each category with **Partial** or **Missing** status, add to candidate question queue unless:
+   - Clarification would not materially change implementation strategy
+   - Information is better deferred to planning phase
+
+4. **Generate Prioritized Question Queue**
+
+   Internally generate prioritized queue of candidate questions (maximum 5):
+
+   **Constraints**:
+   - Maximum 5 questions per session
+   - Each question must be answerable with:
+     * Multiple-choice (2-5 mutually exclusive options), OR
+     * Short answer (≤5 words)
+   - Only include questions whose answers materially impact:
+     * Architecture decisions
+     * Data modeling
+     * Task decomposition
+     * Risk mitigation
+     * Success criteria
+   - Ensure category coverage balance
+   - Favor clarifications that reduce downstream rework risk
+
+   **Prioritization Heuristic**:
+   ```
+   priority_score = (impact_on_planning * 0.4) +
+                    (uncertainty_level * 0.3) +
+                    (risk_if_unresolved * 0.3)
+   ```
+
+   If zero high-impact ambiguities found, proceed to **Step 8** (report success).
+
+5. **Sequential Question Loop** (Interactive)
+
+   Present **EXACTLY ONE** question at a time:
+
+   **Multiple-choice format**:
+   ```markdown
+   **Question {N}/5**: {Question text}
+
+   | Option | Description |
+   |--------|-------------|
+   | A | {Option A description} |
+   | B | {Option B description} |
+   | C | {Option C description} |
+   | D | {Option D description} |
+   | Short | Provide different answer (≤5 words) |
+   ```
+
+   **Short-answer format**:
+   ```markdown
+   **Question {N}/5**: {Question text}
+
+   Format: Short answer (≤5 words)
+   ```
+
+   **Answer Validation**:
+   - Validate answer maps to option or fits ≤5 word constraint
+   - If ambiguous, ask quick disambiguation (doesn't count as new question)
+   - Once satisfactory, record in working memory and proceed to next question
+
+   **Stop Conditions**:
+   - All critical ambiguities resolved
+   - User signals completion ("done", "no more", "proceed")
+   - Reached 5 questions
+
+   **Never reveal future queued questions in advance**.
+
+6. **Integration After Each Answer** (Incremental Update)
+
+   After each accepted answer:
+
+   ```bash
+   # Ensure Clarifications section exists
+   IF synthesis_spec NOT contains "## Clarifications":
+       Insert "## Clarifications" section after "# [Topic]" heading
+
+   # Create session subsection
+   IF NOT contains "### Session YYYY-MM-DD":
+       Create "### Session {today's date}" under "## Clarifications"
+
+   # Append clarification entry
+   APPEND: "- Q: {question} → A: {answer}"
+
+   # Apply clarification to appropriate section
+   CASE category:
+       Functional Requirements → Update "## Requirements & Acceptance Criteria"
+       Architecture → Update "## Key Designs & Decisions" or "## Design Specifications"
+       User Experience → Update "## Design Specifications > UI/UX Guidelines"
+       Risk → Update "## Risk Assessment & Mitigation"
+       Process → Update "## Process & Collaboration Concerns"
+       Data Model → Update "## Key Designs & Decisions > Data Model Overview"
+       Non-Functional → Update "## Requirements & Acceptance Criteria > Non-Functional Requirements"
+
+   # Remove obsolete/contradictory statements
+   IF clarification invalidates existing statement:
+       Replace statement instead of duplicating
+
+   # Save immediately
+   Write(synthesis_specification.md)
+   ```
+
+7. **Validation After Each Write**
+
+   - [ ] Clarifications section contains exactly one bullet per accepted answer
+   - [ ] Total asked questions ≤ 5
+   - [ ] Updated sections contain no lingering placeholders
+   - [ ] No contradictory earlier statements remain
+   - [ ] Markdown structure valid
+   - [ ] Terminology consistent across all updated sections
+
+8. **Completion Report**
+
+   After questioning loop ends or early termination:
+
+   ```markdown
+   ## ✅ Concept Verification Complete
+
+   **Session**: WFS-{session-id}
+   **Questions Asked**: {count}/5
+   **Artifacts Updated**: synthesis-specification.md
+   **Sections Touched**: {list section names}
+
+   ### Coverage Summary
+
+   | Category | Status | Notes |
+   |----------|--------|-------|
+   | Requirements Clarity | ✅ Resolved | Acceptance criteria quantified |
+   | Architecture & Design | ✅ Clear | No ambiguities found |
+   | Implementation Feasibility | ⚠️ Deferred | Team training plan to be defined in IMPL_PLAN |
+   | Risk & Mitigation | ✅ Resolved | Critical risks now have mitigation strategies |
+   | ... | ... | ... |
+
+   **Legend**:
+   - ✅ Resolved: Was Partial/Missing, now addressed
+   - ✅ Clear: Already sufficient
+   - ⚠️ Deferred: Low impact, better suited for planning phase
+   - ❌ Outstanding: Still Partial/Missing but question quota reached
+
+   ### Recommendations
+
+   - ✅ **PROCEED to /workflow:plan**: Conceptual foundation is clear
+   - OR ⚠️ **Address Outstanding Items First**: {list critical outstanding items}
+   - OR 🔄 **Run /workflow:concept-clarify Again**: If new information available
+
+   ### Next Steps
+   ```bash
+   /workflow:plan  # Generate IMPL_PLAN.md and task.json
+   ```
+   ```
+
+9. **Update Session Metadata**
+
+   ```json
+   {
+     "phases": {
+       "BRAINSTORM": {
+         "status": "completed",
+         "concept_verification": {
+           "completed": true,
+           "completed_at": "timestamp",
+           "questions_asked": 3,
+           "categories_clarified": ["Requirements", "Risk", "Architecture"],
+           "outstanding_items": [],
+           "recommendation": "PROCEED_TO_PLANNING"
+         }
+       }
+     }
+   }
+   ```
+
+## Behavior Rules
+
+- **If no meaningful ambiguities found**: Report "No critical ambiguities detected. Conceptual foundation is clear." and suggest proceeding to `/workflow:plan`.
+- **If synthesis-specification.md missing**: Instruct user to run `/workflow:brainstorm:synthesis` first.
+- **Never exceed 5 questions** (disambiguation retries don't count as new questions).
+- **Respect user early termination**: Signals like "stop", "done", "proceed" should stop questioning.
+- **If quota reached with high-impact items unresolved**: Explicitly flag them under "Outstanding" with recommendation to address before planning.
+- **Avoid speculative tech stack questions** unless absence blocks conceptual clarity.
+
+## Operating Principles
+
+### Context Efficiency
+- **Minimal high-signal tokens**: Focus on actionable clarifications
+- **Progressive disclosure**: Load artifacts incrementally
+- **Deterministic results**: Rerunning without changes produces consistent analysis
+
+### Verification Guidelines
+- **NEVER hallucinate missing sections**: Report them accurately
+- **Prioritize high-impact ambiguities**: Focus on what affects planning
+- **Use examples over exhaustive rules**: Cite specific instances
+- **Report zero issues gracefully**: Emit success report with coverage statistics
+- **Update incrementally**: Save after each answer to minimize context loss
+
+## Context
+
+{ARGS}

.claude/commands/workflow/execute.md

@@ -1,11 +1,7 @@
 ---
 name: execute
 description: Coordinate agents for existing workflow tasks with automatic discovery
-usage: /workflow:execute [--resume-session="session-id"]
-argument-hint: [--resume-session="session-id"]
-examples:
-  - /workflow:execute
-  - /workflow:execute --resume-session="WFS-user-auth"
+argument-hint: "[--resume-session=\"session-id\"]"
 ---
 
 # Workflow Execute Command
@@ -429,10 +425,28 @@ Task(subagent_type="{meta.agent}",
         "on_error": "skip_optional|fail|retry_once"
       }
     ],
-    "implementation_approach": {
-      "task_description": "Implement following consolidated synthesis specification...",
-      "modification_points": ["Apply synthesis specification requirements..."]
-    },
+    "implementation_approach": [
+      {
+        "step": 1,
+        "title": "Implement task following synthesis specification",
+        "description": "Implement '[title]' following synthesis specification. PRIORITY: Use synthesis-specification.md as primary requirement source. When implementation needs technical details (e.g., API schemas, caching configs, design tokens), refer to artifacts[] for detailed specifications from original role analyses.",
+        "modification_points": [
+          "Apply consolidated requirements from synthesis-specification.md",
+          "Follow technical guidelines from synthesis",
+          "Consult artifacts for implementation details when needed",
+          "Integrate with existing patterns"
+        ],
+        "logic_flow": [
+          "Load synthesis specification",
+          "Parse architecture and requirements",
+          "Implement following specification",
+          "Consult artifacts for technical details when needed",
+          "Validate against acceptance criteria"
+        ],
+        "depends_on": [],
+        "output": "implementation"
+      }
+    ],
     "target_files": ["file:function:lines", "path/to/NewFile.ts"]
   }
 }

.claude/commands/workflow/issue/close.md

@@ -1,142 +0,0 @@
----
-name: close
-description: Close a completed or obsolete workflow issue
-usage: /workflow:issue:close <issue-id> [reason]
-
-examples:
-  - /workflow:issue:close ISS-001
-  - /workflow:issue:close ISS-001 "Feature implemented in PR #42"
-  - /workflow:issue:close ISS-002 "Duplicate of ISS-001"
----
-
-# Close Workflow Issue (/workflow:issue:close)
-
-## Purpose
-Mark an issue as closed/resolved with optional reason documentation.
-
-## Usage
-```bash
-/workflow:issue:close <issue-id> ["reason"]
-```
-
-## Closing Process
-
-### Quick Close
-Simple closure without reason:
-```bash
-/workflow:issue:close ISS-001
-```
-
-### Close with Reason
-Include closure reason:
-```bash
-/workflow:issue:close ISS-001 "Feature implemented in PR #42"
-/workflow/issue/close ISS-002 "Duplicate of ISS-001"  
-/workflow/issue/close ISS-003 "No longer relevant"
-```
-
-### Interactive Close (Default)
-Without reason, prompts for details:
-```
-Closing Issue ISS-001: Add OAuth2 social login support
-Current Status: Open | Priority: High | Type: Feature
-
-Why is this issue being closed?
-1. ✅ Completed - Issue resolved successfully
-2. 🔄 Duplicate - Duplicate of another issue
-3. ❌ Invalid - Issue is invalid or not applicable  
-4. 🚫 Won't Fix - Decided not to implement
-5. 📝 Custom reason
-
-Choice: _
-```
-
-## Closure Categories
-
-### Completed (Default)
-- Issue was successfully resolved
-- Implementation finished
-- Requirements met
-- Ready for review/testing
-
-### Duplicate
-- Same as existing issue
-- Consolidated into another issue
-- Reference to primary issue provided
-
-### Invalid
-- Issue description unclear
-- Not a valid problem/request
-- Outside project scope
-- Misunderstanding resolved
-
-### Won't Fix
-- Decided not to implement
-- Business decision to decline
-- Technical constraints prevent
-- Priority too low
-
-### Custom Reason
-- Specific project context
-- Detailed explanation needed
-- Complex closure scenario
-
-## Closure Effects
-
-### Status Update
-- Changes status from "open" to "closed"
-- Records closure details
-- Saves closure reason and category
-
-### Integration Cleanup
-- Unlinks from workflow tasks (if integrated)
-- Removes from active TodoWrite items
-- Updates session statistics
-
-### History Preservation
-- Maintains full issue history
-- Records closure details
-- Preserves for future reference
-
-## Session Updates
-
-### Statistics
-Updates session issue counts:
-- Decrements open issues
-- Increments closed issues
-- Updates completion metrics
-
-### Progress Tracking
-- Updates workflow progress
-- Refreshes TodoWrite status
-- Updates session health metrics
-
-## Output
-Displays:
-- Issue closure confirmation
-- Closure reason and category
-- Updated session statistics  
-- Related actions taken
-
-## Reopening
-Closed issues can be reopened:
-```bash
-/workflow/issue/update ISS-001 --status=open
-```
-
-## Error Handling
-- **Issue not found**: Lists available open issues
-- **Already closed**: Shows current status and closure info
-- **Integration conflicts**: Handles task unlinking gracefully
-- **File errors**: Validates and repairs issue files
-
-## Archive Management
-Closed issues:
-- Remain in .issues/ directory
-- Are excluded from default listings
-- Can be viewed with `/workflow/issue/list --closed`
-- Maintain full searchability
-
----
-
-**Result**: Issue properly closed with documented reason and session cleanup

.claude/commands/workflow/issue/create.md

@@ -1,106 +0,0 @@
----
-name: create
-description: Create a new issue or change request
-usage: /workflow:issue:create "issue description"
-
-examples:
-  - /workflow:issue:create "Add OAuth2 social login support"
-  - /workflow:issue:create "Fix user avatar security vulnerability"
----
-
-# Create Workflow Issue (/workflow:issue:create)
-
-## Purpose
-Create a new issue or change request within the current workflow session.
-
-## Usage
-```bash
-/workflow:issue:create "issue description"
-```
-
-## Automatic Behavior
-
-### Issue ID Generation
-- Generates unique ID: ISS-001, ISS-002, etc.
-- Sequential numbering within session
-- Stored in session's .issues/ directory
-
-### Type Detection
-Automatically detects issue type from description:
-- **Bug**: Contains words like "fix", "error", "bug", "broken"
-- **Feature**: Contains words like "add", "implement", "create", "new"
-- **Optimization**: Contains words like "improve", "optimize", "performance"
-- **Documentation**: Contains words like "document", "readme", "docs"
-- **Refactor**: Contains words like "refactor", "cleanup", "restructure"
-
-### Priority Assessment
-Auto-assigns priority based on keywords:
-- **Critical**: "critical", "urgent", "blocker", "security"
-- **High**: "important", "major", "significant"
-- **Medium**: Default for most issues
-- **Low**: "minor", "enhancement", "nice-to-have"
-
-## Issue Storage
-
-### File Structure
-```
-.workflow/WFS-[session]/.issues/
-├── ISS-001.json          # Issue metadata
-├── ISS-002.json          # Another issue
-└── issue-registry.json   # Issue index
-```
-
-### Issue Metadata
-Each issue stores:
-```json
-{
-  "id": "ISS-001",
-  "title": "Add OAuth2 social login support",
-  "type": "feature",
-  "priority": "high",
-  "status": "open",
-  "created_at": "2025-09-08T10:00:00Z",
-  "category": "authentication",
-  "estimated_impact": "medium",
-  "blocking": false,
-  "session_id": "WFS-oauth-integration"
-}
-```
-
-## Session Integration
-
-### Active Session Check
-- Uses current active session (marker file)
-- Creates .issues/ directory if needed
-- Updates session's issue tracking
-
-### TodoWrite Integration
-Optionally adds to task list:
-- Creates todo for issue investigation
-- Links issue to implementation tasks
-- Updates progress tracking
-
-## Output
-Displays:
-- Generated issue ID
-- Detected type and priority
-- Storage location
-- Integration status
-- Quick actions available
-
-## Quick Actions
-After creation:
-- **View**: `/workflow:issue:list`
-- **Update**: `/workflow:issue:update ISS-001`
-- **Integrate**: Link to workflow tasks
-- **Close**: `/workflow:issue:close ISS-001`
-
-## Error Handling
-- **No active session**: Prompts to start session first
-- **Directory creation**: Handles permission issues
-- **Duplicate description**: Warns about similar issues
-- **Invalid description**: Prompts for meaningful description
-
----
-
-**Result**: New issue created and ready for management within workflow

.claude/commands/workflow/issue/list.md

@@ -1,104 +0,0 @@
----
-name: list
-description: List and filter workflow issues
-usage: /workflow:issue:list
-examples:
-  - /workflow:issue:list
-  - /workflow:issue:list --open
-  - /workflow:issue:list --priority=high
----
-
-# List Workflow Issues (/workflow:issue:list)
-
-## Purpose
-Display all issues and change requests within the current workflow session.
-
-## Usage
-```bash
-/workflow:issue:list [filter]
-```
-
-## Optional Filters
-Simple keyword-based filtering:
-```bash
-/workflow:issue:list --open           # Only open issues
-/workflow:issue:list --closed         # Only closed issues
-/workflow:issue:list --critical       # Critical priority
-/workflow:issue:list --high           # High priority
-/workflow:issue:list --bug            # Bug type issues
-/workflow:issue:list --feature        # Feature type issues
-/workflow:issue:list --blocking       # Blocking issues only
-```
-
-## Display Format
-
-### Open Issues
-```
-🔴 ISS-001: Add OAuth2 social login support
-   Type: Feature | Priority: High | Created: 2025-09-07
-   Status: Open | Impact: Medium
-   
-🔴 ISS-002: Fix user avatar security vulnerability  
-   Type: Bug | Priority: Critical | Created: 2025-09-08
-   Status: Open | Impact: High | 🚫 BLOCKING
-```
-
-### Closed Issues
-```
-✅ ISS-003: Update authentication documentation
-   Type: Documentation | Priority: Low
-   Status: Closed | Completed: 2025-09-05
-   Reason: Documentation updated in PR #45
-```
-
-### Integrated Issues
-```
-🔗 ISS-004: Implement rate limiting
-   Type: Feature | Priority: Medium
-   Status: Integrated → IMPL-003
-   Integrated: 2025-09-06 | Task: IMPL-3.json
-```
-
-## Summary Stats
-```
-📊 Issue Summary for WFS-oauth-integration:
-   Total: 4 issues
-   🔴 Open: 2 | ✅ Closed: 1 | 🔗 Integrated: 1
-   🚫 Blocking: 1 | ⚡ Critical: 1 | 📈 High: 1
-```
-
-## Empty State
-If no issues exist:
-```
-No issues found for current session.
-
-Create your first issue:
-/workflow:issue:create "describe the issue or request"
-```
-
-## Quick Actions
-For each issue, shows available actions:
-- **Update**: `/workflow:issue:update ISS-001`
-- **Integrate**: Link to workflow tasks  
-- **Close**: `/workflow:issue:close ISS-001`
-- **View Details**: Full issue information
-
-## Session Context
-- Lists issues from current active session
-- Shows session name and directory
-- Indicates if .issues/ directory exists
-
-## Sorting
-Issues are sorted by:
-1. Blocking status (blocking first)
-2. Priority (critical → high → medium → low)
-3. Creation date (newest first)
-
-## Performance
-- Fast loading from JSON files
-- Cached issue registry
-- Efficient filtering
-
----
-
-**Result**: Complete overview of all workflow issues with their current status

.claude/commands/workflow/issue/update.md

@@ -1,135 +0,0 @@
----
-name: update
-description: Update an existing workflow issue
-usage: /workflow:issue:update <issue-id> [changes]
-
-examples:
-  - /workflow:issue:update ISS-001
-  - /workflow:issue:update ISS-001 --priority=critical
-  - /workflow:issue:update ISS-001 --status=closed
----
-
-# Update Workflow Issue (/workflow:issue:update)
-
-## Purpose
-Modify attributes and status of an existing workflow issue.
-
-## Usage
-```bash
-/workflow:issue:update <issue-id> [options]
-```
-
-## Quick Updates
-Simple attribute changes:
-```bash
-/workflow:issue:update ISS-001 --priority=critical
-/workflow:issue:update ISS-001 --status=closed
-/workflow:issue:update ISS-001 --blocking
-/workflow:issue:update ISS-001 --type=bug
-```
-
-## Interactive Mode (Default)
-Without options, opens interactive editor:
-```
-Issue ISS-001: Add OAuth2 social login support
-Current Status: Open | Priority: High | Type: Feature
-
-What would you like to update?
-1. Status (open → closed/integrated)
-2. Priority (high → critical/medium/low)  
-3. Type (feature → bug/optimization/etc)
-4. Description
-5. Add comment
-6. Toggle blocking status
-7. Cancel
-
-Choice: _
-```
-
-## Available Updates
-
-### Status Changes
-- **open** → **closed**: Issue resolved
-- **open** → **integrated**: Linked to workflow task
-- **closed** → **open**: Reopen issue
-- **integrated** → **open**: Unlink from tasks
-
-### Priority Levels
-- **critical**: Urgent, blocking progress
-- **high**: Important, should address soon
-- **medium**: Standard priority
-- **low**: Nice-to-have, can defer
-
-### Issue Types  
-- **bug**: Something broken that needs fixing
-- **feature**: New functionality to implement
-- **optimization**: Performance or efficiency improvement
-- **refactor**: Code structure improvement
-- **documentation**: Documentation updates
-
-### Additional Options
-- **blocking/non-blocking**: Whether issue blocks progress
-- **description**: Update issue description
-- **comments**: Add notes and updates
-
-## Update Process
-
-### Validation
-- Verifies issue exists in current session
-- Checks valid status transitions
-- Validates priority and type values
-
-### Change Tracking
-- Records update details
-- Tracks who made changes
-- Maintains change history
-
-### File Updates
-- Updates ISS-XXX.json file
-- Refreshes issue-registry.json
-- Updates session statistics
-
-## Change History
-Maintains audit trail:
-```json
-{
-  "changes": [
-    {
-      "field": "priority",
-      "old_value": "high",
-      "new_value": "critical",
-      "reason": "Security implications discovered"
-    }
-  ]
-}
-```
-
-## Integration Effects
-
-### Task Integration
-When status changes to "integrated":
-- Links to workflow task (optional)
-- Updates task context with issue reference
-- Creates bidirectional linking
-
-### Session Updates
-- Updates session issue statistics
-- Refreshes TodoWrite if applicable
-- Updates workflow progress tracking
-
-## Output
-Shows:
-- What was changed
-- Before and after values
-- Integration status
-- Available next actions
-
-## Error Handling
-- **Issue not found**: Lists available issues
-- **Invalid status**: Shows valid transitions
-- **Permission errors**: Clear error messages
-- **File corruption**: Validates and repairs
-
----
-
-**Result**: Issue successfully updated with change tracking and integration

.claude/commands/workflow/plan.md

@@ -1,13 +1,7 @@
 ---
 name: plan
 description: Orchestrate 4-phase planning workflow by executing commands and passing context between phases
-usage: /workflow:plan [--agent] <input>
-argument-hint: "[--agent] \"text description\"|file.md|ISS-001"
-examples:
-  - /workflow:plan "Build authentication system"
-  - /workflow:plan --agent "Build authentication system"
-  - /workflow:plan requirements.md
-  - /workflow:plan ISS-001
+argument-hint: "[--agent] [--cli-execute] \"text description\"|file.md"
 allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)
 ---
 
@@ -15,26 +9,36 @@ allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)
 
 ## Coordinator Role
 
-**This command is a pure orchestrator**: Execute 4 slash commands in sequence, parse their outputs, pass context between them, and ensure complete execution.
+**This command is a pure orchestrator**: Execute 4 slash commands in sequence, parse their outputs, pass context between them, and ensure complete execution through **automatic continuation**.
 
-**Execution Flow**:
-1. Initialize TodoWrite → Execute Phase 1 → Parse output → Update TodoWrite
-2. Execute Phase 2 with Phase 1 data → Parse output → Update TodoWrite
-3. Execute Phase 3 with Phase 2 data → Parse output → Update TodoWrite
-4. Execute Phase 4 with Phase 3 validation → Update TodoWrite → Return summary
+**Execution Model - Auto-Continue Workflow**:
+
+This workflow runs **fully autonomously** once triggered. Each phase completes, reports its output to you, then **immediately and automatically** proceeds to the next phase without requiring any user intervention.
+
+1. **User triggers**: `/workflow:plan "task"`
+2. **Phase 1 executes** → Reports output to user → Auto-continues
+3. **Phase 2 executes** → Reports output to user → Auto-continues
+4. **Phase 3 executes** → Reports output to user → Auto-continues
+5. **Phase 4 executes** → Reports final summary
+
+**Auto-Continue Mechanism**:
+- TodoList tracks current phase status
+- After each phase completion, automatically executes next pending phase
+- **No user action required** - workflow runs end-to-end autonomously
+- Progress updates shown at each phase for visibility
 
 **Execution Modes**:
 - **Manual Mode** (default): Use `/workflow:tools:task-generate`
 - **Agent Mode** (`--agent`): Use `/workflow:tools:task-generate-agent`
+- **CLI Execute Mode** (`--cli-execute`): Generate tasks with Codex execution commands
 
 ## Core Rules
 
 1. **Start Immediately**: First action is TodoWrite initialization, second action is Phase 1 command execution
 2. **No Preliminary Analysis**: Do not read files, analyze structure, or gather context before Phase 1
 3. **Parse Every Output**: Extract required data from each command's output for next phase
-4. **Sequential Execution**: Each phase depends on previous phase's output
-5. **Complete All Phases**: Do not return to user until Phase 4 completes
-6. **Track Progress**: Update TodoWrite after every phase completion
+4. **Auto-Continue via TodoList**: Check TodoList status to execute next pending phase automatically
+5. **Track Progress**: Update TodoWrite after every phase completion
 
 ## 4-Phase Execution
 
@@ -64,6 +68,8 @@ CONTEXT: Existing user database schema, REST API endpoints
 
 **TodoWrite**: Mark phase 1 completed, phase 2 in_progress
 
+**After Phase 1**: Return to user showing Phase 1 results, then auto-continue to Phase 2
+
 ---
 
 ### Phase 2: Context Gathering
@@ -83,6 +89,8 @@ CONTEXT: Existing user database schema, REST API endpoints
 
 **TodoWrite**: Mark phase 2 completed, phase 3 in_progress
 
+**After Phase 2**: Return to user showing Phase 2 results, then auto-continue to Phase 3
+
 ---
 
 ### Phase 3: Intelligent Analysis
@@ -99,12 +107,35 @@ CONTEXT: Existing user database schema, REST API endpoints
 
 **TodoWrite**: Mark phase 3 completed, phase 4 in_progress
 
+**After Phase 3**: Return to user showing Phase 3 results, then auto-continue to Phase 4
+
 ---
 
 ### Phase 4: Task Generation
-**Command**:
+
+**Relationship with Brainstorm Phase**:
+- If brainstorm synthesis exists (synthesis-specification.md), Phase 3 analysis incorporates it as input
+- **synthesis-specification.md defines "WHAT"**: Requirements, design specs, high-level features
+- **IMPL_PLAN.md defines "HOW"**: Executable task breakdown, dependencies, implementation sequence
+- Task generation translates high-level specifications into concrete, actionable work items
+
+**Command Selection**:
 - Manual: `SlashCommand(command="/workflow:tools:task-generate --session [sessionId]")`
 - Agent: `SlashCommand(command="/workflow:tools:task-generate-agent --session [sessionId]")`
+- CLI Execute: Add `--cli-execute` flag to either command
+
+**Flag Combination**:
+- `--cli-execute` alone: Manual task generation with CLI execution
+- `--agent --cli-execute`: Agent task generation with CLI execution
+
+**Command Examples**:
+```bash
+# Manual with CLI execution
+/workflow:tools:task-generate --session WFS-auth --cli-execute
+
+# Agent with CLI execution
+/workflow:tools:task-generate-agent --session WFS-auth --cli-execute
+```
 
 **Input**: `sessionId` from Phase 1
 
@@ -121,7 +152,12 @@ Planning complete for session: [sessionId]
 Tasks generated: [count]
 Plan: .workflow/[sessionId]/IMPL_PLAN.md
 
-Next: /workflow:execute or /workflow:status
+✅ Recommended Next Steps:
+1. /workflow:action-plan-verify --session [sessionId]  # Verify plan quality before execution
+2. /workflow:status  # Review task breakdown
+3. /workflow:execute  # Start implementation (after verification)
+
+⚠️ Quality Gate: Consider running /workflow:action-plan-verify to catch issues early
 ```
 
 ## TodoWrite Pattern
@@ -175,12 +211,6 @@ TodoWrite({todos: [
    - Extract goal, scope, requirements
    - Format into structured description
 
-4. **Issue Reference** (e.g., `ISS-001`) → Read and structure:
-   - Read issue file
-   - Extract title as goal
-   - Extract description as scope/context
-   - Format into structured description
-
 ## Data Flow
 
 ```
@@ -227,23 +257,26 @@ Return summary to user
 
 - **Parsing Failure**: If output parsing fails, retry command once, then report error
 - **Validation Failure**: If validation fails, report which file/data is missing
-- **Command Failure**: Keep phase `in_progress`, report error to user, do not proceed
+- **Command Failure**: Keep phase `in_progress`, report error to user, do not proceed to next phase
 
 ## Coordinator Checklist
 
 ✅ **Pre-Phase**: Convert user input to structured format (GOAL/SCOPE/CONTEXT)
 ✅ Initialize TodoWrite before any command
 ✅ Execute Phase 1 immediately with structured description
-✅ Parse session ID from Phase 1 output
+✅ Parse session ID from Phase 1 output, store in memory
 ✅ Pass session ID and structured description to Phase 2 command
-✅ Parse context path from Phase 2 output
+✅ Parse context path from Phase 2 output, store in memory
 ✅ Pass session ID and context path to Phase 3 command
 ✅ Verify ANALYSIS_RESULTS.md after Phase 3
-✅ Select correct Phase 4 command based on --agent flag
+✅ **Build Phase 4 command** based on flags:
+  - Base command: `/workflow:tools:task-generate` (or `-agent` if `--agent` flag)
+  - Add `--session [sessionId]`
+  - Add `--cli-execute` if flag present
 ✅ Pass session ID to Phase 4 command
 ✅ Verify all Phase 4 outputs
 ✅ Update TodoWrite after each phase
-✅ Return summary only after Phase 4 completes
+✅ After each phase, automatically continue to next phase based on TodoList status
 
 ## Structure Template Reference
 
@@ -270,4 +303,4 @@ CONSTRAINTS: [Limitations or boundaries]
 
 # Phase 2
 /workflow:tools:context-gather --session WFS-123 "GOAL: Build authentication\nSCOPE: JWT, login, registration\nCONTEXT: REST API"
-```
+```

.claude/commands/workflow/resume.md

@@ -1,12 +1,7 @@
 ---
 name: resume
 description: Intelligent workflow session resumption with automatic progress analysis
-usage: /workflow:resume "<session-id>"
 argument-hint: "session-id for workflow session to resume"
-examples:
-  - /workflow:resume "WFS-user-auth"
-  - /workflow:resume "WFS-api-integration"
-  - /workflow:resume "WFS-database-migration"
 allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)
 ---
 

.claude/commands/workflow/review.md

@@ -1,13 +1,7 @@
 ---
 name: review
 description: Optional specialized review (security, architecture, docs) for completed implementation
-usage: /workflow:review [--type=<type>] [session-id]
-argument-hint: "[--type=security|architecture|action-items|quality] [session-id]"
-examples:
-  - /workflow:review                           # Quality review of active session
-  - /workflow:review --type=security           # Security audit of active session
-  - /workflow:review --type=architecture WFS-user-auth  # Architecture review of specific session
-  - /workflow:review --type=action-items       # Pre-deployment verification
+argument-hint: "[--type=security|architecture|action-items|quality] [optional: session-id]"
 ---
 
 ### 🚀 Command Overview: `/workflow:review`

.claude/commands/workflow/session/complete.md

@@ -1,7 +1,6 @@
 ---
 name: complete
 description: Mark the active workflow session as complete and remove active flag
-usage: /workflow:session:complete
 examples:
   - /workflow:session:complete
   - /workflow:session:complete --detailed

.claude/commands/workflow/session/list.md

@@ -1,7 +1,6 @@
 ---
 name: list
 description: List all workflow sessions with status
-usage: /workflow:session:list
 examples:
   - /workflow:session:list
 ---

.claude/commands/workflow/session/pause.md

@@ -1,69 +0,0 @@
----
-name: pause
-description: Pause the active workflow session
-usage: /workflow:session:pause
-examples:
-  - /workflow:session:pause
----
-
-# Pause Workflow Session (/workflow:session:pause)
-
-## Overview
-Pause the currently active workflow session, saving all state for later resumption.
-
-## Usage
-```bash
-/workflow:session:pause      # Pause current active session
-```
-
-## Implementation Flow
-
-### Step 1: Find Active Session
-```bash
-ls .workflow/.active-* 2>/dev/null | head -1
-```
-
-### Step 2: Get Session Name
-```bash
-basename .workflow/.active-WFS-session-name | sed 's/^\.active-//'
-```
-
-### Step 3: Update Session Status
-```bash
-jq '.status = "paused"' .workflow/WFS-session/workflow-session.json > temp.json
-mv temp.json .workflow/WFS-session/workflow-session.json
-```
-
-### Step 4: Add Pause Timestamp
-```bash
-jq '.paused_at = "'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"' .workflow/WFS-session/workflow-session.json > temp.json
-mv temp.json .workflow/WFS-session/workflow-session.json
-```
-
-### Step 5: Remove Active Marker
-```bash
-rm .workflow/.active-WFS-session-name
-```
-
-## Simple Bash Commands
-
-### Basic Operations
-- **Find active session**: `ls .workflow/.active-*`
-- **Get session name**: `basename marker | sed 's/^\.active-//'`
-- **Update status**: `jq '.status = "paused"' session.json > temp.json`
-- **Add timestamp**: `jq '.paused_at = "'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"'`
-- **Remove marker**: `rm .workflow/.active-session`
-
-### Pause Result
-```
-Session WFS-user-auth paused
-- Status: paused
-- Paused at: 2025-09-15T14:30:00Z
-- Tasks preserved: 8 tasks
-- Can resume with: /workflow:session:resume
-```
-
-## Related Commands
-- `/workflow:session:resume` - Resume paused session
-- `/workflow:session:list` - Show all sessions including paused
-- `/workflow:session:status` - Check session state

.claude/commands/workflow/session/resume.md

@@ -1,9 +1,6 @@
 ---
 name: resume
 description: Resume the most recently paused workflow session
-usage: /workflow:session:resume
-examples:
-  - /workflow:session:resume
 ---
 
 # Resume Workflow Session (/workflow:session:resume)

.claude/commands/workflow/session/start.md

@@ -1,7 +1,6 @@
 ---
 name: start
 description: Discover existing sessions or start a new workflow session with intelligent session management
-usage: /workflow:session:start [--auto|--new] [task_description]
 argument-hint: [--auto|--new] [optional: task description for new session]
 examples:
   - /workflow:session:start

.claude/commands/workflow/session/switch.md

@@ -1,87 +0,0 @@
----
-name: switch
-description: Switch to a different workflow session
-usage: /workflow:session:switch <session-id>
-argument-hint: session-id to switch to
-examples:
-  - /workflow:session:switch WFS-oauth-integration
-  - /workflow:session:switch WFS-user-profile
----
-
-# Switch Workflow Session (/workflow:session:switch)
-
-## Overview
-Switch the active session to a different workflow session.
-
-## Usage
-```bash
-/workflow:session:switch WFS-session-name     # Switch to specific session
-```
-
-## Implementation Flow
-
-### Step 1: Validate Target Session
-```bash
-test -d .workflow/WFS-target-session && echo "Session exists"
-```
-
-### Step 2: Pause Current Session
-```bash
-ls .workflow/.active-* 2>/dev/null | head -1
-jq '.status = "paused"' .workflow/current-session/workflow-session.json > temp.json
-```
-
-### Step 3: Remove Current Active Marker
-```bash
-rm .workflow/.active-* 2>/dev/null
-```
-
-### Step 4: Activate Target Session
-```bash
-jq '.status = "active"' .workflow/WFS-target/workflow-session.json > temp.json
-mv temp.json .workflow/WFS-target/workflow-session.json
-```
-
-### Step 5: Create New Active Marker
-```bash
-touch .workflow/.active-WFS-target-session
-```
-
-### Step 6: Add Switch Timestamp
-```bash
-jq '.switched_at = "'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"' .workflow/WFS-target/workflow-session.json > temp.json
-mv temp.json .workflow/WFS-target/workflow-session.json
-```
-
-## Simple Bash Commands
-
-### Basic Operations
-- **Check session exists**: `test -d .workflow/WFS-session`
-- **Find current active**: `ls .workflow/.active-*`
-- **Pause current**: `jq '.status = "paused"' session.json > temp.json`
-- **Remove marker**: `rm .workflow/.active-*`
-- **Activate target**: `jq '.status = "active"' target.json > temp.json`
-- **Create marker**: `touch .workflow/.active-target`
-
-### Switch Result
-```
-Switched to session: WFS-oauth-integration
-- Previous: WFS-user-auth (paused)
-- Current: WFS-oauth-integration (active)
-- Switched at: 2025-09-15T15:45:00Z
-- Ready for: /workflow:execute
-```
-
-### Error Handling
-```bash
-# Session not found
-test -d .workflow/WFS-nonexistent || echo "Error: Session not found"
-
-# No sessions available
-ls .workflow/WFS-* 2>/dev/null || echo "No sessions available"
-```
-
-## Related Commands
-- `/workflow:session:list` - Show all available sessions
-- `/workflow:session:pause` - Pause current before switching
-- `/workflow:execute` - Continue with new active session

.claude/commands/workflow/status.md

@@ -1,12 +1,7 @@
 ---
 name: workflow:status
 description: Generate on-demand views from JSON task data
-usage: /workflow:status [task-id]
-argument-hint: [optional: task-id]
-examples:
-  - /workflow:status
-  - /workflow:status impl-1
-  - /workflow:status --validate
+argument-hint: "[optional: task-id]"
 ---
 
 # Workflow Status Command (/workflow:status)

.claude/commands/workflow/tdd-plan.md

@@ -1,12 +1,7 @@
 ---
 name: tdd-plan
 description: Orchestrate TDD workflow planning with Red-Green-Refactor task chains
-usage: /workflow:tdd-plan [--agent] <input>
-argument-hint: "[--agent] \"feature description\"|file.md|ISS-001"
-examples:
-  - /workflow:tdd-plan "Implement user authentication"
-  - /workflow:tdd-plan --agent requirements.md
-  - /workflow:tdd-plan ISS-001
+argument-hint: "[--agent] \"feature description\"|file.md"
 allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)
 ---
 
@@ -26,10 +21,11 @@ allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)
 2. **No Preliminary Analysis**: Do not read files before Phase 1
 3. **Parse Every Output**: Extract required data for next phase
 4. **Sequential Execution**: Each phase depends on previous output
-5. **Complete All Phases**: Do not return until Phase 5 completes
+5. **Complete All Phases**: Do not return until Phase 7 completes (with concept verification)
 6. **TDD Context**: All descriptions include "TDD:" prefix
+7. **Quality Gate**: Phase 5 concept verification ensures clarity before task generation
 
-## 5-Phase Execution
+## 7-Phase Execution (with Concept Verification)
 
 ### Phase 1: Session Discovery
 **Command**: `/workflow:session:start --auto "TDD: [structured-description]"`
@@ -50,12 +46,51 @@ TEST_FOCUS: [Test scenarios]
 
 **Parse**: Extract contextPath
 
-### Phase 3: TDD Analysis
+### Phase 3: Test Coverage Analysis
+**Command**: `/workflow:tools:test-context-gather --session [sessionId]`
+
+**Purpose**: Analyze existing codebase for:
+- Existing test patterns and conventions
+- Current test coverage
+- Related components and integration points
+- Test framework detection
+
+**Parse**: Extract testContextPath (`.workflow/[sessionId]/.process/test-context-package.json`)
+
+**Benefits**:
+- Makes TDD aware of existing environment
+- Identifies reusable test patterns
+- Prevents duplicate test creation
+- Enables integration with existing tests
+
+### Phase 4: TDD Analysis
 **Command**: `/workflow:tools:concept-enhanced --session [sessionId] --context [contextPath]`
 
-**Parse**: Verify ANALYSIS_RESULTS.md
+**Note**: Generates ANALYSIS_RESULTS.md with TDD-specific structure:
+- Feature list with testable requirements
+- Test cases for Red phase
+- Implementation requirements for Green phase
+- Refactoring opportunities
+- Task dependencies and execution order
 
-### Phase 4: TDD Task Generation
+**Parse**: Verify ANALYSIS_RESULTS.md contains TDD breakdown sections
+
+### Phase 5: Concept Verification (NEW QUALITY GATE)
+**Command**: `/workflow:concept-verify --session [sessionId]`
+
+**Purpose**: Verify conceptual clarity before TDD task generation
+- Clarify test requirements and acceptance criteria
+- Resolve ambiguities in expected behavior
+- Validate TDD approach is appropriate
+
+**Behavior**:
+- If no ambiguities found → Auto-proceed to Phase 6
+- If ambiguities exist → Interactive clarification (up to 5 questions)
+- After clarifications → Auto-proceed to Phase 6
+
+**Parse**: Verify concept verification completed (check for clarifications section in ANALYSIS_RESULTS.md or synthesis file if exists)
+
+### Phase 6: TDD Task Generation
 **Command**:
 - Manual: `/workflow:tools:task-generate-tdd --session [sessionId]`
 - Agent: `/workflow:tools:task-generate-tdd --session [sessionId] --agent`
@@ -63,19 +98,21 @@ TEST_FOCUS: [Test scenarios]
 **Parse**: Extract feature count, chain count, task count
 
 **Validate**:
-- TDD_PLAN.md exists
-- IMPL_PLAN.md exists
+- IMPL_PLAN.md exists (unified plan with TDD Task Chains section)
 - TEST-*.json, IMPL-*.json, REFACTOR-*.json exist
 - TODO_LIST.md exists
+- IMPL tasks include test-fix-cycle configuration
+- IMPL_PLAN.md contains workflow_type: "tdd" in frontmatter
 
-### Phase 5: TDD Structure Validation
-**Internal validation (no command)**
+### Phase 7: TDD Structure Validation & Action Plan Verification (RECOMMENDED)
+**Internal validation first, then recommend external verification**
 
-**Validate**:
+**Internal Validation**:
 1. Each feature has TEST → IMPL → REFACTOR chain
 2. Dependencies: IMPL depends_on TEST, REFACTOR depends_on IMPL
 3. Meta fields: tdd_phase correct ("red"/"green"/"refactor")
 4. Agents: TEST uses @code-review-test-agent, IMPL/REFACTOR use @code-developer
+5. IMPL tasks contain test-fix-cycle in flow_control for iterative Green phase
 
 **Return Summary**:
 ```
@@ -89,23 +126,30 @@ Structure:
 - Feature 1: TEST-1.1 → IMPL-1.1 → REFACTOR-1.1
 [...]
 
-Plans:
-- TDD Structure: .workflow/[sessionId]/TDD_PLAN.md
-- Implementation: .workflow/[sessionId]/IMPL_PLAN.md
+Plan:
+- Unified Implementation Plan: .workflow/[sessionId]/IMPL_PLAN.md
+  (includes TDD Task Chains section with workflow_type: "tdd")
 
-Next: /workflow:execute or /workflow:tdd-verify
+✅ Recommended Next Steps:
+1. /workflow:action-plan-verify --session [sessionId]  # Verify TDD plan quality
+2. /workflow:execute --session [sessionId]  # Start TDD execution
+3. /workflow:tdd-verify [sessionId]  # Post-execution TDD compliance check
+
+⚠️ Quality Gate: Consider running /workflow:action-plan-verify to validate TDD task dependencies
 ```
 
 ## TodoWrite Pattern
 
 ```javascript
-// Initialize
+// Initialize (7 phases now with concept verification)
 [
-  {content: "Execute session discovery", status: "in_progress", activeForm: "..."},
-  {content: "Execute context gathering", status: "pending", activeForm: "..."},
-  {content: "Execute TDD analysis", status: "pending", activeForm: "..."},
-  {content: "Execute TDD task generation", status: "pending", activeForm: "..."},
-  {content: "Validate TDD structure", status: "pending", activeForm: "..."}
+  {content: "Execute session discovery", status: "in_progress", activeForm: "Executing session discovery"},
+  {content: "Execute context gathering", status: "pending", activeForm": "Executing context gathering"},
+  {content: "Execute test coverage analysis", status: "pending", activeForm": "Executing test coverage analysis"},
+  {content: "Execute TDD analysis", status: "pending", activeForm": "Executing TDD analysis"},
+  {content: "Execute concept verification", status: "pending", activeForm": "Executing concept verification"},
+  {content: "Execute TDD task generation", status: "pending", activeForm: "Executing TDD task generation"},
+  {content: "Validate TDD structure", status: "pending", activeForm: "Validating TDD structure"}
 ]
 
 // Update after each phase: mark current "completed", next "in_progress"
@@ -131,3 +175,96 @@ Convert user input to TDD-structured format:
 - `/workflow:execute` - Execute TDD tasks
 - `/workflow:tdd-verify` - Verify TDD compliance
 - `/workflow:status` - View progress
+## TDD Workflow Enhancements
+
+### Overview
+The TDD workflow has been significantly enhanced by integrating best practices from both traditional `plan --agent` and `test-gen` workflows, creating a hybrid approach that bridges the gap between idealized TDD and real-world development complexity.
+
+### Key Improvements
+
+#### 1. Test Coverage Analysis (Phase 3)
+**Adopted from test-gen workflow**
+
+Before planning TDD tasks, the workflow now analyzes the existing codebase:
+- Detects existing test patterns and conventions
+- Identifies current test coverage
+- Discovers related components and integration points
+- Detects test framework automatically
+
+**Benefits**:
+- Context-aware TDD planning
+- Avoids duplicate test creation
+- Enables integration with existing tests
+- No longer assumes greenfield scenarios
+
+#### 2. Iterative Green Phase with Test-Fix Cycle
+**Adopted from test-gen workflow**
+
+IMPL (Green phase) tasks now include automatic test-fix cycle for resilient implementation:
+
+**Enhanced IMPL Task Flow**:
+```
+1. Write minimal implementation code
+2. Execute test suite
+3. IF tests pass → Complete task ✅
+4. IF tests fail → Enter fix cycle:
+   a. Gemini diagnoses with bug-fix template
+   b. Apply fix (manual or Codex)
+   c. Retest
+   d. Repeat (max 3 iterations)
+5. IF max iterations → Auto-revert changes 🔄
+```
+
+**Benefits**:
+- ✅ Faster feedback within Green phase
+- ✅ Autonomous recovery from implementation errors
+- ✅ Systematic debugging with Gemini
+- ✅ Safe rollback prevents broken state
+
+#### 3. Agent-Driven Planning
+**From plan --agent workflow**
+
+Supports action-planning-agent for more autonomous TDD planning with:
+- MCP tool integration (code-index, exa)
+- Memory-first principles
+- Brainstorming artifact integration
+- Task merging over decomposition
+
+### Workflow Comparison
+
+| Aspect | Previous | Current |
+|--------|----------|---------|
+| **Phases** | 5 | 6 (test coverage analysis) |
+| **Context** | Greenfield assumption | Existing codebase aware |
+| **Green Phase** | Single implementation | Iterative with fix cycle |
+| **Failure Handling** | Manual intervention | Auto-diagnose + fix + revert |
+| **Test Analysis** | None | Deep coverage analysis |
+| **Feedback Loop** | Post-execution | During Green phase |
+
+### Migration Notes
+
+**Backward Compatibility**: ✅ Fully compatible
+- Existing TDD workflows continue to work
+- New features are additive, not breaking
+- Phase 3 can be skipped if test-context-gather not available
+
+**Session Structure**:
+```
+.workflow/WFS-xxx/
+├── IMPL_PLAN.md (unified plan with TDD Task Chains section)
+├── TODO_LIST.md
+├── .process/
+│   ├── context-package.json
+│   ├── test-context-package.json
+│   ├── ANALYSIS_RESULTS.md (enhanced with TDD breakdown)
+│   └── green-fix-iteration-*.md (fix logs)
+└── .task/
+    ├── TEST-*.json (Red phase)
+    ├── IMPL-*.json (Green phase with test-fix-cycle)
+    └── REFACTOR-*.json (Refactor phase)
+```
+
+**Configuration Options** (in IMPL tasks):
+- `meta.max_iterations`: Fix attempts (default: 3)
+- `meta.use_codex`: Auto-fix mode (default: false)
+

.claude/commands/workflow/tdd-verify.md

@@ -1,11 +1,8 @@
 ---
 name: tdd-verify
 description: Verify TDD workflow compliance and generate quality report
-usage: /workflow:tdd-verify [session-id]
-argument-hint: "[WFS-session-id]"
-examples:
-  - /workflow:tdd-verify
-  - /workflow:tdd-verify WFS-auth
+
+argument-hint: "[optional: WFS-session-id]"
 allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(gemini-wrapper:*)
 ---
 

.claude/commands/workflow/test-gen.md

@@ -1,11 +1,7 @@
 ---
 name: test-gen
 description: Create independent test-fix workflow session by analyzing completed implementation
-usage: /workflow:test-gen <source-session-id>
-argument-hint: "<source-session-id>"
-examples:
-  - /workflow:test-gen WFS-user-auth
-  - /workflow:test-gen WFS-api-refactor
+argument-hint: "[--use-codex] [--cli-execute] source-session-id"
 allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)
 ---
 
@@ -20,6 +16,7 @@ allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)
 - **Context-First**: Prioritizes gathering code changes and summaries from source session
 - **Format Reuse**: Creates standard `IMPL-*.json` task, using `meta.type: "test-fix"` for agent assignment
 - **Parameter Simplification**: Tools auto-detect test session type via metadata, no manual cross-session parameters needed
+- **Manual First**: Default to manual fixes, use `--use-codex` flag for automated Codex fix application
 
 **Execution Flow**:
 1. Initialize TodoWrite → Create test session → Parse session ID
@@ -36,8 +33,9 @@ allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)
 5. **Complete All Phases**: Do not return to user until Phase 4 completes (execution triggered separately)
 6. **Track Progress**: Update TodoWrite after every phase completion
 7. **Automatic Detection**: context-gather auto-detects test session and gathers source session context
+8. **Parse --use-codex Flag**: Extract flag from arguments and pass to Phase 4 (test-task-generate)
 
-## 4-Phase Execution
+## 5-Phase Execution
 
 ### Phase 1: Create Test Session
 **Command**: `SlashCommand(command="/workflow:session:start --new \"Test validation for [sourceSessionId]\"")`
@@ -65,107 +63,118 @@ allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)
 
 ---
 
-### Phase 2: Gather Cross-Session Context
-**Command**: `SlashCommand(command="/workflow:tools:context-gather --session [testSessionId]")`
+### Phase 2: Gather Test Context
+**Command**: `SlashCommand(command="/workflow:tools:test-context-gather --session [testSessionId]")`
 
 **Input**: `testSessionId` from Phase 1 (e.g., `WFS-test-user-auth`)
 
-**Automatic Detection**:
-- context-gather reads `.workflow/[testSessionId]/workflow-session.json`
-- Detects `workflow_type: "test_session"`
-- Automatically uses `source_session_id` to gather source session context
-- No need for manual `--source-session` parameter
-
-**Cross-Session Context Collection** (Automatic):
-- Implementation summaries: `.workflow/[sourceSessionId]/.summaries/IMPL-*-summary.md`
-- Code changes: `git log --since=[source_session_created_at]` for changed files
-- Original plan: `.workflow/[sourceSessionId]/IMPL_PLAN.md`
-- Test files: Discovered via MCP code-index tools
+**Expected Behavior**:
+- Load source session implementation context and summaries
+- Analyze test coverage using MCP tools (find existing tests)
+- Identify files requiring tests (coverage gaps)
+- Detect test framework and conventions
+- Generate `test-context-package.json`
 
 **Parse Output**:
-- Extract: context package path (store as `contextPath`)
-- Pattern: `.workflow/[testSessionId]/.process/context-package.json`
+- Extract: test context package path (store as `testContextPath`)
+- Pattern: `.workflow/[testSessionId]/.process/test-context-package.json`
 
 **Validation**:
-- Context package created in test session directory
-- Contains source session artifacts (summaries, changed files)
-- Includes test file inventory
+- Test context package created
+- Contains source session summaries
+- Includes coverage gap analysis
+- Test framework detected
+- Test conventions documented
 
 **TodoWrite**: Mark phase 2 completed, phase 3 in_progress
 
 ---
 
-### Phase 3: Implementation Analysis
-**Command**: `SlashCommand(command="/workflow:tools:concept-enhanced --session [testSessionId] --context [contextPath]")`
+### Phase 3: Test Generation Analysis
+**Command**: `SlashCommand(command="/workflow:tools:test-concept-enhanced --session [testSessionId] --context [testContextPath]")`
 
 **Input**:
-- `testSessionId` from Phase 1 (e.g., `WFS-test-user-auth`)
-- `contextPath` from Phase 2 (e.g., `.workflow/WFS-test-user-auth/.process/context-package.json`)
-
-**Analysis Focus**:
-- Review implementation summaries from source session
-- Identify test files and coverage gaps
-- Assess test execution strategy (unit, integration, e2e)
-- Determine failure diagnosis approach
-- Recommend code quality improvements
+- `testSessionId` from Phase 1
+- `testContextPath` from Phase 2
 
 **Expected Behavior**:
-- Reads context-package.json with cross-session artifacts
-- Executes parallel analysis (Gemini for test strategy, optional Codex for validation)
-- Generates comprehensive test execution strategy
-- Identifies code modification targets for test fixes
-- Provides feasibility assessment for test validation
+- Use Gemini to analyze coverage gaps and implementation context
+- Study existing test patterns and conventions
+- Generate test requirements for each missing test file
+- Design test generation strategy
+- Generate `TEST_ANALYSIS_RESULTS.md`
 
 **Parse Output**:
-- Verify `.workflow/[testSessionId]/.process/ANALYSIS_RESULTS.md` created
-- Contains test strategy and execution plan
-- Lists code modification targets (format: `file:function:lines` or `file`)
-- Includes risk assessment and optimization recommendations
+- Verify `.workflow/[testSessionId]/.process/TEST_ANALYSIS_RESULTS.md` created
+- Contains test requirements and generation strategy
+- Lists test files to create with specifications
 
 **Validation**:
-- File `.workflow/[testSessionId]/.process/ANALYSIS_RESULTS.md` exists
-- Contains complete analysis sections:
-  - Current State Analysis (test coverage, existing tests)
-  - Proposed Solution Design (test execution strategy)
-  - Implementation Strategy (code targets, feasibility)
-  - Solution Optimization (performance, quality)
-  - Critical Success Factors (acceptance criteria)
+- TEST_ANALYSIS_RESULTS.md exists with complete sections:
+  - Coverage Assessment
+  - Test Framework & Conventions
+  - Test Requirements by File
+  - Test Generation Strategy
+  - Implementation Targets (test files to create)
+  - Success Criteria
 
 **TodoWrite**: Mark phase 3 completed, phase 4 in_progress
 
 ---
 
-### Phase 4: Generate Test Task
-**Command**: `SlashCommand(command="/workflow:tools:task-generate --session [testSessionId]")`
+### Phase 4: Generate Test Tasks
+**Command**: `SlashCommand(command="/workflow:tools:test-task-generate [--use-codex] [--cli-execute] --session [testSessionId]")`
 
-**Input**: `testSessionId` from Phase 1
+**Input**:
+- `testSessionId` from Phase 1
+- `--use-codex` flag (if present in original command) - Controls IMPL-002 fix mode
+- `--cli-execute` flag (if present in original command) - Controls IMPL-001 generation mode
 
 **Expected Behavior**:
-- Reads ANALYSIS_RESULTS.md from Phase 3
-- Extracts test strategy and code modification targets
-- Generates `IMPL-001.json` (reusing standard format) with:
-  - `meta.type: "test-fix"` (enables @test-fix-agent assignment)
-  - `meta.agent: "@test-fix-agent"`
-  - `context.requirements`: Test execution requirements from analysis
-  - `context.focus_paths`: Test files and source files from analysis
-  - `context.acceptance`: All tests pass criteria
-  - `flow_control.pre_analysis`: Load source session summaries
-  - `flow_control.implementation_approach`: Test execution strategy from ANALYSIS_RESULTS.md
-  - `flow_control.target_files`: Code modification targets from analysis
+- Parse TEST_ANALYSIS_RESULTS.md from Phase 3
+- Extract test requirements and generation strategy
+- Generate **TWO task JSON files**:
+  - **IMPL-001.json**: Test Generation task (calls @code-developer)
+  - **IMPL-002.json**: Test Execution and Fix Cycle task (calls @test-fix-agent)
+- Generate IMPL_PLAN.md with test generation and execution strategy
+- Generate TODO_LIST.md with both tasks
 
 **Parse Output**:
-- Verify `.workflow/[testSessionId]/.task/IMPL-001.json` exists
+- Verify `.workflow/[testSessionId]/.task/IMPL-001.json` exists (test generation)
+- Verify `.workflow/[testSessionId]/.task/IMPL-002.json` exists (test execution & fix)
 - Verify `.workflow/[testSessionId]/IMPL_PLAN.md` created
 - Verify `.workflow/[testSessionId]/TODO_LIST.md` created
 
-**Validation**:
-- Task JSON has `id: "IMPL-001"` and `meta.type: "test-fix"`
-- IMPL_PLAN.md contains test validation strategy from ANALYSIS_RESULTS.md
-- TODO_LIST.md shows IMPL-001 task
-- flow_control includes code targets and test strategy
-- Task is ready for /workflow:execute
+**Validation - IMPL-001.json (Test Generation)**:
+- Task ID: `IMPL-001`
+- `meta.type: "test-gen"`
+- `meta.agent: "@code-developer"`
+- `context.requirements`: Generate tests based on TEST_ANALYSIS_RESULTS.md
+- `flow_control.pre_analysis`: Load TEST_ANALYSIS_RESULTS.md and test context
+- `flow_control.implementation_approach`: Test generation steps
+- `flow_control.target_files`: Test files to create from analysis section 5
 
-**TodoWrite**: Mark phase 4 completed
+**Validation - IMPL-002.json (Test Execution & Fix)**:
+- Task ID: `IMPL-002`
+- `meta.type: "test-fix"`
+- `meta.agent: "@test-fix-agent"`
+- `meta.use_codex: true|false` (based on --use-codex flag)
+- `context.depends_on: ["IMPL-001"]`
+- `context.requirements`: Execute and fix tests
+- `flow_control.implementation_approach.test_fix_cycle`: Complete cycle specification
+  - **Cycle pattern**: test → gemini_diagnose → manual_fix (or codex if --use-codex) → retest
+  - **Tools configuration**: Gemini for analysis with bug-fix template, manual or Codex for fixes
+  - **Exit conditions**: Success (all pass) or failure (max iterations)
+- `flow_control.implementation_approach.modification_points`: 3-phase execution flow
+  - Phase 1: Initial test execution
+  - Phase 2: Iterative Gemini diagnosis + manual/Codex fixes (based on flag)
+  - Phase 3: Final validation and certification
+
+**TodoWrite**: Mark phase 4 completed, phase 5 in_progress
+
+---
+
+### Phase 5: Return Summary to User
 
 **Return to User**:
 ```
@@ -173,315 +182,120 @@ Independent test-fix workflow created successfully!
 
 Source Session: [sourceSessionId]
 Test Session: [testSessionId]
-Task Created: IMPL-001 (test-fix)
+
+Tasks Created:
+- IMPL-001: Test Generation (@code-developer)
+- IMPL-002: Test Execution & Fix Cycle (@test-fix-agent)
+
+Test Framework: [detected framework]
+Test Files to Generate: [count]
+Max Fix Iterations: 5
+Fix Mode: [Manual|Codex Automated] (based on --use-codex flag)
 
 Next Steps:
 1. Review test plan: .workflow/[testSessionId]/IMPL_PLAN.md
-2. Execute validation: /workflow:execute
+2. Execute workflow: /workflow:execute
 3. Monitor progress: /workflow:status
-
-The @test-fix-agent will:
-- Execute all tests
-- Diagnose any failures
-- Fix code until tests pass
 ```
 
+**TodoWrite**: Mark phase 5 completed
+
 ---
 
 ## TodoWrite Pattern
 
+Track progress through 5 phases:
+
 ```javascript
-// Initialize (before Phase 1)
 TodoWrite({todos: [
-  {"content": "Create independent test session", "status": "in_progress", "activeForm": "Creating test session"},
-  {"content": "Gather cross-session context", "status": "pending", "activeForm": "Gathering cross-session context"},
-  {"content": "Analyze implementation for test strategy", "status": "pending", "activeForm": "Analyzing implementation"},
-  {"content": "Generate test validation task", "status": "pending", "activeForm": "Generating test validation task"}
-]})
-
-// After Phase 1
-TodoWrite({todos: [
-  {"content": "Create independent test session", "status": "completed", "activeForm": "Creating test session"},
-  {"content": "Gather cross-session context", "status": "in_progress", "activeForm": "Gathering cross-session context"},
-  {"content": "Analyze implementation for test strategy", "status": "pending", "activeForm": "Analyzing implementation"},
-  {"content": "Generate test validation task", "status": "pending", "activeForm": "Generating test validation task"}
-]})
-
-// After Phase 2
-TodoWrite({todos: [
-  {"content": "Create independent test session", "status": "completed", "activeForm": "Creating test session"},
-  {"content": "Gather cross-session context", "status": "completed", "activeForm": "Gathering cross-session context"},
-  {"content": "Analyze implementation for test strategy", "status": "in_progress", "activeForm": "Analyzing implementation"},
-  {"content": "Generate test validation task", "status": "pending", "activeForm": "Generating test validation task"}
-]})
-
-// After Phase 3
-TodoWrite({todos: [
-  {"content": "Create independent test session", "status": "completed", "activeForm": "Creating test session"},
-  {"content": "Gather cross-session context", "status": "completed", "activeForm": "Gathering cross-session context"},
-  {"content": "Analyze implementation for test strategy", "status": "completed", "activeForm": "Analyzing implementation"},
-  {"content": "Generate test validation task", "status": "in_progress", "activeForm": "Generating test validation task"}
-]})
-
-// After Phase 4
-TodoWrite({todos: [
-  {"content": "Create independent test session", "status": "completed", "activeForm": "Creating test session"},
-  {"content": "Gather cross-session context", "status": "completed", "activeForm": "Gathering cross-session context"},
-  {"content": "Analyze implementation for test strategy", "status": "completed", "activeForm": "Analyzing implementation"},
-  {"content": "Generate test validation task", "status": "completed", "activeForm": "Generating test validation task"}
+  {"content": "Create independent test session", "status": "in_progress|completed", "activeForm": "Creating test session"},
+  {"content": "Gather test coverage context", "status": "pending|in_progress|completed", "activeForm": "Gathering test coverage context"},
+  {"content": "Analyze test requirements with Gemini", "status": "pending|in_progress|completed", "activeForm": "Analyzing test requirements"},
+  {"content": "Generate test generation and execution tasks", "status": "pending|in_progress|completed", "activeForm": "Generating test tasks"},
+  {"content": "Return workflow summary", "status": "pending|in_progress|completed", "activeForm": "Returning workflow summary"}
 ]})
 ```
 
+Update status to `in_progress` when starting each phase, mark `completed` when done.
+
 ## Data Flow
 
 ```
-User: /workflow:test-gen WFS-user-auth
-    ↓
-Phase 1: session-start --new "Test validation for WFS-user-auth"
-    ↓ Creates: WFS-test-user-auth session
-    ↓ Writes: workflow-session.json with workflow_type="test_session", source_session_id="WFS-user-auth"
-    ↓ Output: testSessionId = "WFS-test-user-auth"
-    ↓
-Phase 2: context-gather --session WFS-test-user-auth
-    ↓ Auto-detects: test session type from workflow-session.json
-    ↓ Auto-reads: source_session_id = "WFS-user-auth"
-    ↓ Gathers: Cross-session context (summaries, code changes, tests)
-    ↓ Output: .workflow/WFS-test-user-auth/.process/context-package.json
-    ↓
-Phase 3: concept-enhanced --session WFS-test-user-auth --context context-package.json
-    ↓ Reads: context-package.json with cross-session artifacts
-    ↓ Executes: Parallel analysis (Gemini test strategy + optional Codex validation)
-    ↓ Analyzes: Test coverage, execution strategy, code targets
-    ↓ Output: .workflow/WFS-test-user-auth/.process/ANALYSIS_RESULTS.md
-    ↓
-Phase 4: task-generate --session WFS-test-user-auth
-    ↓ Reads: ANALYSIS_RESULTS.md with test strategy and code targets
-    ↓ Generates: IMPL-001.json with meta.type="test-fix"
-    ↓ Output: Task, plan, and todo files in test session
-    ↓
-Return: Summary with next steps (user triggers /workflow:execute separately)
+/workflow:test-gen WFS-user-auth
+  ↓
+Phase 1: session-start → WFS-test-user-auth
+  ↓
+Phase 2: test-context-gather → test-context-package.json
+  ↓
+Phase 3: test-concept-enhanced → TEST_ANALYSIS_RESULTS.md
+  ↓
+Phase 4: test-task-generate → IMPL-001.json + IMPL-002.json
+  ↓
+Phase 5: Return summary
+  ↓
+/workflow:execute → IMPL-001 (@code-developer) → IMPL-002 (@test-fix-agent)
 ```
 
-## Session Metadata Design
+## Session Metadata
 
-**Test Session (`WFS-test-user-auth/workflow-session.json`)**:
-```json
-{
-  "session_id": "WFS-test-user-auth",
-  "project": "Test validation for user authentication implementation",
-  "status": "planning",
-  "created_at": "2025-10-03T12:00:00Z",
-  "workflow_type": "test_session",
-  "source_session_id": "WFS-user-auth"
-}
-```
+Test session includes `workflow_type: "test_session"` and `source_session_id` for automatic context gathering.
 
-## Automatic Cross-Session Context Collection
+## Task Output
 
-When `context-gather` detects `workflow_type: "test_session"`:
+Generates two tasks:
+- **IMPL-001** (@code-developer): Test generation from TEST_ANALYSIS_RESULTS.md
+- **IMPL-002** (@test-fix-agent): Test execution with iterative fix cycle (max 5 iterations)
 
-**Collected from Source Session** (`.workflow/WFS-user-auth/`):
-- Implementation summaries: `.summaries/IMPL-*-summary.md`
-- Code changes: `git log --since=[source_created_at] --name-only`
-- Original plan: `IMPL_PLAN.md`
-- Task definitions: `.task/IMPL-*.json`
-
-**Collected from Current Project**:
-- Test files: `mcp__code-index__find_files(pattern="*.test.*")`
-- Test configuration: `package.json`, `jest.config.js`, etc.
-- Source files: Based on changed files from git log
-
-## Task Generation Output
-
-task-generate creates `IMPL-001.json` (reusing standard format) with:
-
-```json
-{
-  "id": "IMPL-001",
-  "title": "Execute and validate tests for [sourceSessionId]",
-  "status": "pending",
-  "meta": {
-    "type": "test-fix",
-    "agent": "@test-fix-agent"
-  },
-  "context": {
-    "requirements": [
-      "Execute complete test suite for all implemented modules",
-      "Diagnose and fix any test failures",
-      "Ensure all tests pass before completion"
-    ],
-    "focus_paths": ["src/**/*.test.ts", "src/**/implementation.ts"],
-    "acceptance": [
-      "All tests pass successfully",
-      "No test failures or errors",
-      "Code is approved and ready for deployment"
-    ],
-    "depends_on": [],
-    "artifacts": []
-  },
-  "flow_control": {
-    "pre_analysis": [
-      {
-        "step": "load_source_session_summaries",
-        "action": "Load implementation summaries from source session",
-        "commands": [
-          "bash(find .workflow/[sourceSessionId]/.summaries/ -name 'IMPL-*-summary.md' 2>/dev/null)",
-          "Read(.workflow/[sourceSessionId]/.summaries/IMPL-001-summary.md)"
-        ],
-        "output_to": "implementation_context",
-        "on_error": "skip_optional"
-      },
-      {
-        "step": "analyze_test_files",
-        "action": "Identify test files and coverage",
-        "commands": [
-          "mcp__code-index__find_files(pattern=\"*.test.*\")",
-          "mcp__code-index__search_code_advanced(pattern=\"test|describe|it\", file_pattern=\"*.test.*\")"
-        ],
-        "output_to": "test_inventory",
-        "on_error": "fail"
-      }
-    ],
-    "implementation_approach": {
-      "task_description": "Execute tests and fix failures until all pass",
-      "modification_points": [
-        "Run test suite using detected framework",
-        "Parse test output to identify failures",
-        "Diagnose root cause of failures",
-        "Modify source code to fix issues",
-        "Re-run tests to verify fixes"
-      ],
-      "logic_flow": [
-        "Load implementation context",
-        "Identify test framework and configuration",
-        "Execute complete test suite",
-        "If failures: analyze error messages",
-        "Fix source code based on diagnosis",
-        "Re-run tests",
-        "Repeat until all tests pass"
-      ]
-    },
-    "target_files": ["src/**/*.test.ts", "src/**/implementation.ts"]
-  }
-}
-```
+See `/workflow:tools:test-task-generate` for complete task JSON schemas.
 
 ## Error Handling
 
-### Phase 1 Failures
-- **Source session not found**: Return error "Source session [sourceSessionId] not found in .workflow/"
-- **Invalid source session**: Return error "Source session [sourceSessionId] has no completed IMPL tasks"
-- **Session creation failed**: Return error "Could not create test session. Check /workflow:session:start"
+| Phase | Error | Action |
+|-------|-------|--------|
+| 1 | Source session not found | Return error with source session ID |
+| 1 | No completed IMPL tasks | Return error, source incomplete |
+| 2 | Context gathering failed | Return error, check source artifacts |
+| 3 | Analysis failed | Return error, check context package |
+| 4 | Task generation failed | Retry once, then error with details |
 
-### Phase 2 Failures
-- **Context gathering failed**: Return error "Could not gather cross-session context. Check source session artifacts"
-- **No source artifacts**: Return error "Source session has no implementation summaries or git history"
+## Output Files
 
-### Phase 3 Failures
-- **Analysis failed**: Return error "Implementation analysis failed. Check context package and ANALYSIS_RESULTS.md"
-- **No test strategy**: Return error "Could not determine test execution strategy from analysis"
-- **Missing code targets**: Warning only, proceed with general test task
-
-### Phase 4 Failures
-- **Task generation failed**: Retry once, then return error with details
-- **Invalid task structure**: Return error with JSON validation details
-
-## Workflow Integration
-
-### Complete Flow Example
-```
-1. Implementation Phase (prior to test-gen)
-   /workflow:plan "Build auth system"
-   → Creates WFS-auth session
-   → @code-developer implements + writes tests
-   → Creates IMPL-001-summary.md in WFS-auth
-
-2. Test Generation Phase (test-gen)
-   /workflow:test-gen WFS-auth
-   Phase 1: session-start → Creates WFS-test-auth session
-   Phase 2: context-gather → Gathers from WFS-auth, creates context-package.json
-   Phase 3: concept-enhanced → Analyzes implementation, creates ANALYSIS_RESULTS.md
-   Phase 4: task-generate → Creates IMPL-001.json with meta.type="test-fix"
-   Returns: Summary with next steps
-
-3. Test Execution Phase (user-triggered)
-   /workflow:execute
-   → Detects active session: WFS-test-auth
-   → @test-fix-agent picks up IMPL-001 (test-fix type)
-   → Runs test suite
-   → Diagnoses failures (if any)
-   → Fixes source code
-   → Re-runs tests
-   → All pass → Code approved ✅
-```
-
-### Output Files Created
-
-**In Test Session** (`.workflow/WFS-test-auth/`):
-- `workflow-session.json` - Contains workflow_type and source_session_id
-- `.process/context-package.json` - Cross-session context from WFS-auth
-- `.process/ANALYSIS_RESULTS.md` - Test strategy and code targets from concept-enhanced
-- `.task/IMPL-001.json` - Test-fix task definition
-- `IMPL_PLAN.md` - Test validation plan (from ANALYSIS_RESULTS.md)
+Created in `.workflow/WFS-test-[session]/`:
+- `workflow-session.json` - Session metadata
+- `.process/test-context-package.json` - Coverage analysis
+- `.process/TEST_ANALYSIS_RESULTS.md` - Test requirements
+- `.task/IMPL-001.json` - Test generation task
+- `.task/IMPL-002.json` - Test execution & fix task
+- `IMPL_PLAN.md` - Test plan
 - `TODO_LIST.md` - Task checklist
-- `.summaries/IMPL-001-summary.md` - Created by @test-fix-agent after completion
+
+## Agent Execution
+
+**IMPL-001** (@code-developer):
+- Generates test files based on TEST_ANALYSIS_RESULTS.md
+- Follows existing test patterns and conventions
+
+**IMPL-002** (@test-fix-agent):
+1. Run test suite
+2. Iterative fix cycle (max 5):
+   - Gemini diagnosis with bug-fix template → surgical fix suggestions
+   - Manual fix application (default) OR Codex applies fixes if --use-codex flag (resume mechanism)
+   - Retest and check regressions
+3. Final validation and certification
+
+See `/workflow:tools:test-task-generate` for detailed specifications.
 
 ## Best Practices
 
-1. **Run after implementation complete**: Ensure source session has completed IMPL tasks and summaries
-2. **Check git commits**: Implementation changes should be committed for accurate git log analysis
-3. **Verify test files exist**: Source implementation should include test files
-4. **Independent sessions**: Test session is separate from implementation session for clean separation
-5. **Monitor execution**: Use `/workflow:status` to track test-fix progress after /workflow:execute
-
-## Coordinator Checklist
-
-✅ Initialize TodoWrite before any command (4 phases)
-✅ Phase 1: Create test session with source session ID
-✅ Parse new test session ID from Phase 1 output
-✅ Phase 2: Run context-gather (auto-detects test session, no extra params)
-✅ Verify context-package.json contains cross-session artifacts
-✅ Phase 3: Run concept-enhanced with session and context path
-✅ Verify ANALYSIS_RESULTS.md contains test strategy and code targets
-✅ Phase 4: Run task-generate to create IMPL-001.json
-✅ Verify task has meta.type="test-fix" and meta.agent="@test-fix-agent"
-✅ Verify flow_control includes analysis insights and code targets
-✅ Update TodoWrite after each phase
-✅ Return summary after Phase 4 (execution is separate user action)
-
-## Required Tool Modifications
-
-### `/workflow:session:start`
-- Support `--new` flag for test session creation
-- Auto-detect test session pattern from task description
-- Write `workflow_type: "test_session"` and `source_session_id` to metadata
-
-### `/workflow:tools:context-gather`
-- Read session metadata to detect `workflow_type: "test_session"`
-- Auto-extract `source_session_id` from metadata
-- Gather cross-session context from source session artifacts
-- Include git log analysis from source session creation time
-
-### `/workflow:tools:concept-enhanced`
-- No changes required (already supports cross-session context analysis)
-- Will automatically analyze test strategy based on context-package.json
-- Generates ANALYSIS_RESULTS.md with code targets and test execution plan
-
-### `/workflow:tools:task-generate`
-- Recognize test session context and generate appropriate task
-- Create `IMPL-001.json` with `meta.type: "test-fix"`
-- Extract test strategy from ANALYSIS_RESULTS.md
-- Include code targets and cross-session references in flow_control
-
-### `/workflow:execute`
-- No changes required (already dispatches by meta.agent)
+1. Run after implementation complete (ensure source session has summaries)
+2. Commit implementation changes before test-gen
+3. Monitor execution with `/workflow:status`
+4. Review iteration logs in `.process/fix-iteration-*`
 
 ## Related Commands
-- `/workflow:plan` - Create implementation workflow (run before test-gen)
-- `/workflow:session:start` - Phase 1 tool for test session creation
-- `/workflow:tools:context-gather` - Phase 2 tool for cross-session context collection
-- `/workflow:tools:concept-enhanced` - Phase 3 tool for implementation analysis and test strategy
-- `/workflow:tools:task-generate` - Phase 4 tool for test task creation
-- `/workflow:execute` - Execute test-fix workflow (user-triggered after test-gen)
-- `/workflow:status` - Check workflow progress
-- `@test-fix-agent` - Agent that executes and fixes tests
+
+- `/workflow:tools:test-context-gather` - Phase 2 (coverage analysis)
+- `/workflow:tools:test-concept-enhanced` - Phase 3 (Gemini test analysis)
+- `/workflow:tools:test-task-generate` - Phase 4 (task generation)
+- `/workflow:execute` - Execute workflow
+- `/workflow:status` - Check progress

.claude/commands/workflow/tools/concept-enhanced.md

@@ -1,7 +1,6 @@
 ---
 name: concept-enhanced
 description: Enhanced intelligent analysis with parallel CLI execution and design blueprint generation
-usage: /workflow:tools:concept-enhanced --session <session_id> --context <context_package_path>
 argument-hint: "--session WFS-session-id --context path/to/context-package.json"
 examples:
   - /workflow:tools:concept-enhanced --session WFS-auth --context .workflow/WFS-auth/.process/context-package.json
@@ -130,6 +129,15 @@ Advanced solution design and feasibility analysis engine with parallel CLI execu
      - Tech stack from tech_stack section
      - Project structure from statistics section
 
+     **ANALYSIS PRIORITY - Use ALL source documents from context-package assets[]**:
+     1. PRIMARY SOURCES (Highest Priority): Individual role analysis.md files (system-architect, ui-designer, product-manager, etc.)
+        - These contain complete technical details, design rationale, ADRs, and decision context
+        - Extract: Technical specs, API schemas, design tokens, caching configs, performance metrics
+     2. SYNTHESIS REFERENCE (Medium Priority): synthesis-specification.md
+        - Use for integrated requirements and cross-role alignment
+        - Validate decisions and identify integration points
+     3. TOPIC FRAMEWORK (Low Priority): topic-framework.md for discussion context
+
      EXPECTED:
      1. CURRENT STATE ANALYSIS: Existing patterns, code structure, integration points, technical debt
      2. SOLUTION DESIGN: Core architecture principles, system design, key design decisions with rationale

.claude/commands/workflow/tools/context-gather.md

@@ -1,7 +1,6 @@
 ---
 name: gather
 description: Intelligently collect project context based on task description and package into standardized JSON
-usage: /workflow:tools:context-gather --session <session_id> "<task_description>"
 argument-hint: "--session WFS-session-id \"task description\""
 examples:
   - /workflow:tools:context-gather --session WFS-user-auth "Implement user authentication system"

.claude/commands/workflow/tools/docs.md

@@ -1,256 +1,665 @@
 ---
 name: docs
-description: Generate hierarchical architecture and API documentation using doc-generator agent with flow_control
-usage: /workflow:docs <type> [scope]
-argument-hint: "architecture"|"api"|"all"
+description: Documentation planning and orchestration - creates structured documentation tasks for execution
+argument-hint: "[path] [--tool <gemini|qwen|codex>] [--cli-generate]"
 examples:
-  - /workflow:docs all
-  - /workflow:docs architecture src/modules
-  - /workflow:docs api --scope api/
+  - /workflow:docs                              # Current directory (root: full docs, subdir: module only)
+  - /workflow:docs src/modules                  # Module documentation only
+  - /workflow:docs . --tool qwen                # Root directory with Qwen
+  - /workflow:docs --cli-generate               # Use CLI for doc generation (not just analysis)
 ---
 
-# Workflow Documentation Command
+# Documentation Workflow (/workflow:docs)
+
+## Overview
+Lightweight planner that analyzes project structure, decomposes documentation work into tasks, and generates execution plans. Does NOT generate documentation content itself - delegates to doc-generator agent.
+
+**Two Execution Modes**:
+- **Default**: CLI analyzes in `pre_analysis` (MODE=analysis), agent writes docs in `implementation_approach`
+- **--cli-generate**: CLI generates docs in `implementation_approach` (MODE=write)
+
+## Parameters
 
-## Usage
 ```bash
-/workflow:docs <type> [scope]
+/workflow:docs [path] [--tool <gemini|qwen|codex>] [--cli-generate]
 ```
 
-## Input Detection
-- **Document Types**: `architecture`, `api`, `all` → Creates appropriate documentation tasks
-- **Scope**: Optional module/directory filtering → Focuses documentation generation
-- **Default**: `all` → Complete documentation suite
+- **path**: Target directory (default: current directory)
+  - Project root → Full documentation (modules + project-level docs)
+  - Subdirectory → Module documentation only (API.md + README.md)
 
-## Core Workflow
+- **--tool**: CLI tool selection (default: gemini)
+  - `gemini`: Comprehensive documentation, pattern recognition
+  - `qwen`: Architecture analysis, system design focus
+  - `codex`: Implementation validation, code quality
 
-### Planning & Task Creation Process
-The command performs structured planning and task creation:
+- **--cli-generate**: Enable CLI-based documentation generation (optional)
+  - When enabled: CLI generates docs with MODE=write in implementation_approach
+  - When disabled (default): CLI analyzes with MODE=analysis in pre_analysis
 
-**0. Pre-Planning Architecture Analysis** ⚠️ MANDATORY FIRST STEP
-- **System Structure Analysis**: MUST run `bash(~/.claude/scripts/get_modules_by_depth.sh)` for dynamic task decomposition
-- **Module Boundary Identification**: Understand module organization and dependencies
-- **Architecture Pattern Recognition**: Identify architectural styles and design patterns
-- **Foundation for documentation**: Use structure analysis to guide task decomposition
+## Planning Workflow
 
-**1. Documentation Planning**
-- **Type Analysis**: Determine documentation scope (architecture/api/all)
-- **Module Discovery**: Use architecture analysis results to identify components
-- **Dynamic Task Decomposition**: Analyze project structure to determine optimal task count and module grouping
-- **Session Management**: Create or use existing documentation session
+### Phase 1: Initialize Session
+```bash
+# Parse arguments
+path="${1:-.}"
+tool="gemini"
+cli_generate=false
 
-**2. Task Generation**
-- **Create session**: `.workflow/WFS-docs-[timestamp]/`
-- **Create active marker**: `.workflow/.active-WFS-docs-[timestamp]` (must match session folder name)
-- **Generate IMPL_PLAN.md**: Documentation requirements and task breakdown
-- **Create task.json files**: Individual documentation tasks with flow_control
-- **Setup TODO_LIST.md**: Progress tracking for documentation generation
+# Parse options
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --tool) tool="$2"; shift 2 ;;
+    --cli-generate) cli_generate=true; shift ;;
+    *) shift ;;
+  esac
+done
 
-### Session Management ⚠️ CRITICAL
-- **Check for active sessions**: Look for `.workflow/.active-WFS-docs-*` markers
-- **Marker naming**: Active marker must exactly match session folder name
-- **Session creation**: `WFS-docs-[timestamp]` folder with matching `.active-WFS-docs-[timestamp]` marker
-- **Task execution**: Use `/workflow:execute` to run individual documentation tasks within active session
-- **Session isolation**: Each documentation session maintains independent context and state
+# Detect project root
+bash(git rev-parse --show-toplevel)
+project_root=$(pwd)
+target_path=$(cd "$path" && pwd)
+is_root=false
+[[ "$target_path" == "$project_root" ]] && is_root=true
 
-## Output Structure
-```
-.workflow/docs/
-├── README.md              # System navigation
-├── modules/               # Level 1: Module documentation
-│   ├── [module-1]/
-│   │   ├── overview.md
-│   │   ├── api.md
-│   │   ├── dependencies.md
-│   │   └── examples.md
-│   └── [module-n]/...
-├── architecture/          # Level 2: System architecture
-│   ├── system-design.md
-│   ├── module-map.md
-│   ├── data-flow.md
-│   └── tech-stack.md
-└── api/                   # Level 2: Unified API docs
-    ├── unified-api.md
-    └── openapi.yaml
+# Create session structure
+timestamp=$(date +%Y%m%d-%H%M%S)
+session_dir=".workflow/WFS-docs-${timestamp}"
+
+bash(mkdir -p "${session_dir}"/{.task,.process,.summaries})
+bash(touch ".workflow/.active-WFS-docs-${timestamp}")
+
+# Record configuration
+bash(cat > "${session_dir}/.process/config.txt" <<EOF
+path=$path
+target_path=$target_path
+is_root=$is_root
+tool=$tool
+cli_generate=$cli_generate
+EOF
+)
 ```
 
-## Task Decomposition Standards
+### Phase 2: Analyze Structure
+```bash
+# Step 1: Discover module hierarchy
+bash(~/.claude/scripts/get_modules_by_depth.sh)
+# Output: depth:N|path:<PATH>|files:N|size:N|has_claude:yes/no
 
-### Dynamic Task Planning Rules
-**Module Grouping**: Max 3 modules per task, max 30 files per task
-**Task Count**: Calculate based on `total_modules ÷ 3 (rounded up) + base_tasks`
-**File Limits**: Split tasks when file count exceeds 30 in any module group
-**Base Tasks**: System overview (1) + Architecture (1) + API consolidation (1)
-**Module Tasks**: Group related modules by dependency depth and functional similarity
+# Step 2: Classify folders by type
+bash(cat > "${session_dir}/.process/classify-folders.sh" <<'SCRIPT'
+while IFS='|' read -r depth_info path_info files_info size_info claude_info; do
+  folder_path=$(echo "$path_info" | cut -d':' -f2-)
 
-### Documentation Task Types
-**IMPL-001**: System Overview Documentation
-- Project structure analysis
-- Technology stack documentation
-- Main navigation creation
+  # Count code files (maxdepth 1)
+  code_files=$(find "$folder_path" -maxdepth 1 -type f \
+    \( -name "*.ts" -o -name "*.js" -o -name "*.py" \
+       -o -name "*.go" -o -name "*.java" -o -name "*.rs" \) \
+    2>/dev/null | wc -l)
 
-**IMPL-002**: Module Documentation (per module)
-- Individual module analysis
-- API surface documentation
-- Dependencies and relationships
-- Usage examples
+  # Count subfolders
+  subfolders=$(find "$folder_path" -maxdepth 1 -type d \
+    -not -path "$folder_path" 2>/dev/null | wc -l)
 
-**IMPL-003**: Architecture Documentation
-- System design patterns
-- Module interaction mapping
-- Data flow documentation
-- Design principles
+  # Determine type
+  if [[ $code_files -gt 0 ]]; then
+    folder_type="code"  # API.md + README.md
+  elif [[ $subfolders -gt 0 ]]; then
+    folder_type="navigation"  # README.md only
+  else
+    folder_type="skip"  # Empty
+  fi
 
-**IMPL-004**: API Documentation
-- Endpoint discovery and analysis
-- OpenAPI specification generation
-- Authentication documentation
-- Integration examples
+  echo "${folder_path}|${folder_type}|code:${code_files}|dirs:${subfolders}"
+done
+SCRIPT
+)
 
-### Task JSON Schema (5-Field Architecture)
-Each documentation task uses the workflow-architecture.md 5-field schema:
-- **id**: IMPL-N format
-- **title**: Documentation task name
-- **status**: pending|active|completed|blocked
-- **meta**: { type: "documentation", agent: "@doc-generator" }
-- **context**: { requirements, focus_paths, acceptance, scope }
-- **flow_control**: { pre_analysis[], implementation_approach, target_files[] }
+bash(~/.claude/scripts/get_modules_by_depth.sh | bash "${session_dir}/.process/classify-folders.sh" > "${session_dir}/.process/folder-analysis.txt")
 
-## Document Generation
+# Step 3: Group by top-level directories
+bash(awk -F'|' '{split($1, parts, "/"); if (length(parts) >= 2) print parts[1] "/" parts[2]}' \
+  "${session_dir}/.process/folder-analysis.txt" | sort -u > "${session_dir}/.process/top-level-dirs.txt")
+```
 
-### Workflow Process
-**Input Analysis** → **Session Creation** → **IMPL_PLAN.md** → **.task/IMPL-NNN.json** → **TODO_LIST.md** → **Execute Tasks**
+### Phase 3: Detect Update Mode
+```bash
+# Check existing documentation
+bash(find "$target_path" -name "API.md" -o -name "README.md" -o -name "ARCHITECTURE.md" -o -name "EXAMPLES.md" 2>/dev/null | grep -v ".workflow" | wc -l)
 
-**Always Created**:
-- **IMPL_PLAN.md**: Documentation requirements and task breakdown
-- **Session state**: Task references and documentation paths
+existing_docs=$(...)
 
-**Auto-Created (based on scope)**:
-- **TODO_LIST.md**: Progress tracking for documentation tasks
-- **.task/IMPL-*.json**: Individual documentation tasks with flow_control
-- **.process/ANALYSIS_RESULTS.md**: Documentation analysis artifacts
+if [[ $existing_docs -gt 0 ]]; then
+  bash(find "$target_path" -name "*.md" 2>/dev/null | grep -v ".workflow" > "${session_dir}/.process/existing-docs.txt")
+  echo "mode=update" >> "${session_dir}/.process/config.txt"
+else
+  echo "mode=create" >> "${session_dir}/.process/config.txt"
+fi
+
+# Record strategy
+bash(cat > "${session_dir}/.process/strategy.md" <<EOF
+**Path**: ${target_path}
+**Is Root**: ${is_root}
+**Tool**: ${tool}
+**CLI Generate**: ${cli_generate}
+**Mode**: $(grep 'mode=' "${session_dir}/.process/config.txt" | cut -d'=' -f2)
+**Existing Docs**: ${existing_docs} files
+EOF
+)
+```
+
+### Phase 4: Decompose Tasks
+
+**Task Hierarchy**:
+```
+Level 1: Module Tree Tasks (Always generated, can execute in parallel)
+  ├─ IMPL-001: Document tree 'src/modules/'
+  ├─ IMPL-002: Document tree 'src/utils/'
+  └─ IMPL-003: Document tree 'lib/'
+
+Level 2: Project README (Only if is_root=true, depends on Level 1)
+  └─ IMPL-004: Generate Project README
+
+Level 3: Architecture & Examples (Only if is_root=true, depends on Level 2)
+  ├─ IMPL-005: Generate ARCHITECTURE.md
+  ├─ IMPL-006: Generate EXAMPLES.md
+  └─ IMPL-007: Generate HTTP API docs (optional)
+```
+
+**Implementation**:
+```bash
+# Generate Level 1 tasks (always)
+task_count=0
+while read -r top_dir; do
+  task_count=$((task_count + 1))
+  # Create IMPL-00${task_count}.json for module tree
+done < "${session_dir}/.process/top-level-dirs.txt"
+
+# Generate Level 2-3 tasks (only if root)
+if [[ "$is_root" == "true" ]]; then
+  # IMPL-00$((task_count+1)).json: Project README
+  # IMPL-00$((task_count+2)).json: ARCHITECTURE.md
+  # IMPL-00$((task_count+3)).json: EXAMPLES.md
+  # IMPL-00$((task_count+4)).json: HTTP API (optional)
+fi
+```
+
+### Phase 5: Generate Task JSONs
+
+```bash
+# Read configuration
+cli_generate=$(grep 'cli_generate=' "${session_dir}/.process/config.txt" | cut -d'=' -f2)
+tool=$(grep 'tool=' "${session_dir}/.process/config.txt" | cut -d'=' -f2)
+
+# Determine CLI command placement
+if [[ "$cli_generate" == "true" ]]; then
+  # CLI generates docs: MODE=write, place in implementation_approach
+  mode="write"
+  placement="implementation_approach"
+  approval_flag="--approval-mode yolo"
+else
+  # CLI for analysis only: MODE=analysis, place in pre_analysis
+  mode="analysis"
+  placement="pre_analysis"
+  approval_flag=""
+fi
+
+# Build tool-specific command
+if [[ "$tool" == "codex" ]]; then
+  cmd="codex -C ${dir} --full-auto exec \"...\" --skip-git-repo-check -s danger-full-access"
+else
+  cmd="bash(cd ${dir} && ~/.claude/scripts/${tool}-wrapper ${approval_flag} -p \"...MODE: ${mode}...\")"
+fi
+```
+
+## Task Templates
+
+### Level 1: Module Tree Task
+
+**Default Mode (cli_generate=false)**:
+```json
+{
+  "id": "IMPL-001",
+  "title": "Document Module Tree: 'src/modules/'",
+  "status": "pending",
+  "meta": {
+    "type": "docs-tree",
+    "agent": "@doc-generator",
+    "tool": "gemini",
+    "cli_generate": false
+  },
+  "context": {
+    "requirements": [
+      "Recursively process all folders in src/modules/",
+      "For code folders: generate API.md + README.md",
+      "For navigation folders: generate README.md only"
+    ],
+    "focus_paths": ["src/modules"],
+    "folder_analysis_file": "${session_dir}/.process/folder-analysis.txt"
+  },
+  "flow_control": {
+    "pre_analysis": [
+      {
+        "step": "load_existing_docs",
+        "command": "bash(find src/modules -name '*.md' 2>/dev/null | xargs cat || echo 'No existing docs')",
+        "output_to": "existing_module_docs"
+      },
+      {
+        "step": "load_folder_analysis",
+        "command": "bash(grep '^src/modules' ${session_dir}/.process/folder-analysis.txt)",
+        "output_to": "target_folders"
+      },
+      {
+        "step": "analyze_module_tree",
+        "command": "bash(cd src/modules && ~/.claude/scripts/gemini-wrapper -p \"PURPOSE: Analyze module structure\\nTASK: Generate documentation outline\\nMODE: analysis\\nCONTEXT: @{**/*} [target_folders]\\nEXPECTED: Structure outline\\nRULES: Analyze only\")",
+        "output_to": "tree_outline",
+        "note": "CLI for analysis only"
+      }
+    ],
+    "implementation_approach": [
+      {
+        "step": 1,
+        "title": "Generate module tree documentation",
+        "description": "Process target folders and generate appropriate documentation files based on folder types",
+        "modification_points": ["Parse folder types from [target_folders]", "Parse structure from [tree_outline]", "Generate API.md for code folders", "Generate README.md for all folders"],
+        "logic_flow": ["Parse [target_folders] to get folder types", "Parse [tree_outline] for structure", "For each folder: if type == 'code': Generate API.md + README.md; elif type == 'navigation': Generate README.md only"],
+        "depends_on": [],
+        "output": "module_docs"
+      }
+    ],
+    "target_files": [
+      ".workflow/docs/modules/*/API.md",
+      ".workflow/docs/modules/*/README.md"
+    ]
+  }
+}
+```
+
+**CLI Generate Mode (cli_generate=true)**:
+```json
+{
+  "id": "IMPL-001",
+  "title": "Document Module Tree: 'src/modules/'",
+  "status": "pending",
+  "meta": {
+    "type": "docs-tree",
+    "agent": "@doc-generator",
+    "tool": "gemini",
+    "cli_generate": true
+  },
+  "context": {
+    "requirements": [
+      "Recursively process all folders in src/modules/",
+      "CLI generates documentation files directly"
+    ],
+    "focus_paths": ["src/modules"]
+  },
+  "flow_control": {
+    "pre_analysis": [
+      {
+        "step": "load_existing_docs",
+        "command": "bash(find src/modules -name '*.md' 2>/dev/null | xargs cat || echo 'No existing docs')",
+        "output_to": "existing_module_docs"
+      },
+      {
+        "step": "load_folder_analysis",
+        "command": "bash(grep '^src/modules' ${session_dir}/.process/folder-analysis.txt)",
+        "output_to": "target_folders"
+      }
+    ],
+    "implementation_approach": [
+      {
+        "step": 1,
+        "title": "Parse folder analysis",
+        "description": "Parse [target_folders] to get folder types and structure",
+        "modification_points": ["Extract folder types", "Identify code vs navigation folders"],
+        "logic_flow": ["Parse [target_folders] to get folder types", "Prepare folder list for CLI generation"],
+        "depends_on": [],
+        "output": "folder_types"
+      },
+      {
+        "step": 2,
+        "title": "Generate documentation via CLI",
+        "description": "Call CLI to generate documentation files for each folder using MODE=write",
+        "modification_points": ["Execute CLI generation command", "Generate API.md and README.md files"],
+        "logic_flow": ["Call CLI to generate documentation files for each folder"],
+        "command": "bash(cd src/modules && ~/.claude/scripts/gemini-wrapper --approval-mode yolo -p \"PURPOSE: Generate module docs\\nTASK: Create documentation files\\nMODE: write\\nCONTEXT: @{**/*} [target_folders] [existing_module_docs]\\nEXPECTED: API.md and README.md files\\nRULES: Generate complete docs\")",
+        "depends_on": [1],
+        "output": "generated_docs"
+      }
+    ],
+    "target_files": [
+      ".workflow/docs/modules/*/API.md",
+      ".workflow/docs/modules/*/README.md"
+    ]
+  }
+}
+```
+
+### Level 2: Project README Task
+
+**Default Mode**:
+```json
+{
+  "id": "IMPL-004",
+  "title": "Generate Project README",
+  "status": "pending",
+  "depends_on": ["IMPL-001", "IMPL-002", "IMPL-003"],
+  "meta": {
+    "type": "docs",
+    "agent": "@doc-generator",
+    "tool": "gemini",
+    "cli_generate": false
+  },
+  "flow_control": {
+    "pre_analysis": [
+      {
+        "step": "load_existing_readme",
+        "command": "bash(cat .workflow/docs/README.md 2>/dev/null || echo 'No existing README')",
+        "output_to": "existing_readme"
+      },
+      {
+        "step": "load_module_docs",
+        "command": "bash(find .workflow/docs/modules -name '*.md' | xargs cat)",
+        "output_to": "all_module_docs"
+      },
+      {
+        "step": "analyze_project",
+        "command": "bash(~/.claude/scripts/gemini-wrapper -p \"PURPOSE: Analyze project structure\\nTASK: Extract overview from modules\\nMODE: analysis\\nCONTEXT: [all_module_docs]\\nEXPECTED: Project outline\")",
+        "output_to": "project_outline"
+      }
+    ],
+    "implementation_approach": [
+      {
+        "step": 1,
+        "title": "Generate project README",
+        "description": "Generate project README with navigation links while preserving existing user modifications",
+        "modification_points": ["Parse [project_outline] and [all_module_docs]", "Generate project README structure", "Add navigation links to modules", "Preserve [existing_readme] user modifications"],
+        "logic_flow": ["Parse [project_outline] and [all_module_docs]", "Generate project README with navigation links", "Preserve [existing_readme] user modifications"],
+        "depends_on": [],
+        "output": "project_readme"
+      }
+    ],
+    "target_files": [".workflow/docs/README.md"]
+  }
+}
+```
+
+### Level 3: Architecture Documentation Task
+
+**Default Mode**:
+```json
+{
+  "id": "IMPL-005",
+  "title": "Generate Architecture Documentation",
+  "status": "pending",
+  "depends_on": ["IMPL-004"],
+  "meta": {
+    "type": "docs",
+    "agent": "@doc-generator",
+    "tool": "gemini",
+    "cli_generate": false
+  },
+  "flow_control": {
+    "pre_analysis": [
+      {
+        "step": "load_existing_arch",
+        "command": "bash(cat .workflow/docs/ARCHITECTURE.md 2>/dev/null || echo 'No existing ARCHITECTURE')",
+        "output_to": "existing_architecture"
+      },
+      {
+        "step": "load_all_docs",
+        "command": "bash(cat .workflow/docs/README.md && find .workflow/docs/modules -name '*.md' | xargs cat)",
+        "output_to": "all_docs"
+      },
+      {
+        "step": "analyze_architecture",
+        "command": "bash(~/.claude/scripts/gemini-wrapper -p \"PURPOSE: Analyze system architecture\\nTASK: Synthesize architectural overview\\nMODE: analysis\\nCONTEXT: [all_docs]\\nEXPECTED: Architecture outline\")",
+        "output_to": "arch_outline"
+      }
+    ],
+    "implementation_approach": [
+      {
+        "step": 1,
+        "title": "Generate architecture documentation",
+        "description": "Generate ARCHITECTURE.md while preserving existing user modifications",
+        "modification_points": ["Parse [arch_outline] and [all_docs]", "Generate ARCHITECTURE.md structure", "Document system design and patterns", "Preserve [existing_architecture] modifications"],
+        "logic_flow": ["Parse [arch_outline] and [all_docs]", "Generate ARCHITECTURE.md", "Preserve [existing_architecture] modifications"],
+        "depends_on": [],
+        "output": "architecture_doc"
+      }
+    ],
+    "target_files": [".workflow/docs/ARCHITECTURE.md"]
+  }
+}
+```
+
+### Level 3: Examples Documentation Task
+
+**Default Mode**:
+```json
+{
+  "id": "IMPL-006",
+  "title": "Generate Examples Documentation",
+  "status": "pending",
+  "depends_on": ["IMPL-004"],
+  "meta": {
+    "type": "docs",
+    "agent": "@doc-generator",
+    "tool": "gemini",
+    "cli_generate": false
+  },
+  "flow_control": {
+    "pre_analysis": [
+      {
+        "step": "load_existing_examples",
+        "command": "bash(cat .workflow/docs/EXAMPLES.md 2>/dev/null || echo 'No existing EXAMPLES')",
+        "output_to": "existing_examples"
+      },
+      {
+        "step": "load_project_readme",
+        "command": "bash(cat .workflow/docs/README.md)",
+        "output_to": "project_readme"
+      },
+      {
+        "step": "generate_examples_outline",
+        "command": "bash(~/.claude/scripts/gemini-wrapper -p \"PURPOSE: Generate usage examples\\nTASK: Extract example patterns\\nMODE: analysis\\nCONTEXT: [project_readme]\\nEXPECTED: Examples outline\")",
+        "output_to": "examples_outline"
+      }
+    ],
+    "implementation_approach": [
+      {
+        "step": 1,
+        "title": "Generate examples documentation",
+        "description": "Generate EXAMPLES.md with code snippets while preserving existing user modifications",
+        "modification_points": ["Parse [examples_outline] and [project_readme]", "Generate EXAMPLES.md structure", "Add code snippets and usage examples", "Preserve [existing_examples] modifications"],
+        "logic_flow": ["Parse [examples_outline] and [project_readme]", "Generate EXAMPLES.md with code snippets", "Preserve [existing_examples] modifications"],
+        "depends_on": [],
+        "output": "examples_doc"
+      }
+    ],
+    "target_files": [".workflow/docs/EXAMPLES.md"]
+  }
+}
+```
+
+### Level 3: HTTP API Documentation Task (Optional)
+
+**Default Mode**:
+```json
+{
+  "id": "IMPL-007",
+  "title": "Generate HTTP API Documentation",
+  "status": "pending",
+  "depends_on": ["IMPL-004"],
+  "meta": {
+    "type": "docs",
+    "agent": "@doc-generator",
+    "tool": "gemini",
+    "cli_generate": false
+  },
+  "flow_control": {
+    "pre_analysis": [
+      {
+        "step": "discover_api_endpoints",
+        "command": "mcp__code-index__search_code_advanced(pattern='router\\.|@(Get|Post)', file_pattern='*.{ts,js}')",
+        "output_to": "endpoint_discovery"
+      },
+      {
+        "step": "load_existing_api_docs",
+        "command": "bash(cat .workflow/docs/api/README.md 2>/dev/null || echo 'No existing API docs')",
+        "output_to": "existing_api_docs"
+      },
+      {
+        "step": "analyze_api",
+        "command": "bash(~/.claude/scripts/gemini-wrapper -p \"PURPOSE: Document HTTP API\\nTASK: Analyze API endpoints\\nMODE: analysis\\nCONTEXT: @{src/api/**/*} [endpoint_discovery]\\nEXPECTED: API outline\")",
+        "output_to": "api_outline"
+      }
+    ],
+    "implementation_approach": [
+      {
+        "step": 1,
+        "title": "Generate HTTP API documentation",
+        "description": "Generate HTTP API documentation while preserving existing user modifications",
+        "modification_points": ["Parse [api_outline] and [endpoint_discovery]", "Generate HTTP API documentation", "Document endpoints and request/response formats", "Preserve [existing_api_docs] modifications"],
+        "logic_flow": ["Parse [api_outline] and [endpoint_discovery]", "Generate HTTP API documentation", "Preserve [existing_api_docs] modifications"],
+        "depends_on": [],
+        "output": "api_docs"
+      }
+    ],
+    "target_files": [".workflow/docs/api/README.md"]
+  }
+}
+```
+
+## Session Structure
 
-**Document Structure**:
 ```
 .workflow/
-├── .active-WFS-docs-20231201-143022  # Active session marker (matches folder name)
-└── WFS-docs-20231201-143022/         # Documentation session folder
-    ├── IMPL_PLAN.md                  # Main documentation plan
-    ├── TODO_LIST.md                  # Progress tracking
+├── .active-WFS-docs-20240120-143022
+└── WFS-docs-20240120-143022/
+    ├── IMPL_PLAN.md              # Implementation plan
+    ├── TODO_LIST.md              # Progress tracker
     ├── .process/
-    │   └── ANALYSIS_RESULTS.md       # Documentation analysis
+    │   ├── config.txt            # path, is_root, tool, cli_generate, mode
+    │   ├── strategy.md           # Documentation strategy summary
+    │   ├── folder-analysis.txt   # Folder type classification
+    │   ├── top-level-dirs.txt    # Top-level directory list
+    │   └── existing-docs.txt     # Existing documentation files
     └── .task/
-        ├── IMPL-001.json             # System overview task
-        ├── IMPL-002.json             # Module documentation task
-        ├── IMPL-003.json             # Architecture documentation task
-        └── IMPL-004.json             # API documentation task
+        ├── IMPL-001.json         # Module tree task
+        ├── IMPL-002.json         # Module tree task
+        ├── IMPL-003.json         # Module tree task
+        ├── IMPL-004.json         # Project README (if root)
+        ├── IMPL-005.json         # Architecture (if root)
+        ├── IMPL-006.json         # Examples (if root)
+        └── IMPL-007.json         # HTTP API (if root, optional)
 ```
 
-### Task Flow Control Templates
+## Generated Documentation
 
-**System Overview Task (IMPL-001)**:
-```json
-"flow_control": {
-  "pre_analysis": [
-    {
-      "step": "system_architecture_analysis",
-      "action": "Discover system architecture and module hierarchy",
-      "command": "bash(~/.claude/scripts/get_modules_by_depth.sh)",
-      "output_to": "system_structure"
-    },
-    {
-      "step": "project_discovery",
-      "action": "Discover project structure and entry points",
-      "command": "bash(find . -type f -name '*.json' -o -name '*.md' -o -name 'package.json' | head -20)",
-      "output_to": "project_structure"
-    },
-    {
-      "step": "analyze_tech_stack",
-      "action": "Analyze technology stack and dependencies using structure analysis",
-      "command": "~/.claude/scripts/gemini-wrapper -p \"Analyze project technology stack and dependencies based on: [system_structure]\"",
-      "output_to": "tech_analysis"
-    }
-  ],
-  "target_files": [".workflow/docs/README.md"]
-}
+```
+.workflow/docs/
+├── modules/                           # Level 1 output
+│   ├── README.md                      # Navigation for modules/
+│   ├── auth/
+│   │   ├── API.md                     # Auth module API signatures
+│   │   ├── README.md                  # Auth module documentation
+│   │   └── middleware/
+│   │       ├── API.md                 # Middleware API
+│   │       └── README.md              # Middleware docs
+│   └── api/
+│       ├── API.md                     # API module signatures
+│       └── README.md                  # API module docs
+├── README.md                          # Level 2 output (root only)
+├── ARCHITECTURE.md                    # Level 3 output (root only)
+├── EXAMPLES.md                        # Level 3 output (root only)
+└── api/                               # Level 3 output (optional)
+    └── README.md                      # HTTP API reference
 ```
 
-**Module Documentation Task (IMPL-002)**:
-```json
-"flow_control": {
-  "pre_analysis": [
-    {
-      "step": "load_system_structure",
-      "action": "Load system architecture analysis from previous task",
-      "command": "bash(cat .workflow/WFS-docs-*/IMPL-001-system_structure.output 2>/dev/null || ~/.claude/scripts/get_modules_by_depth.sh)",
-      "output_to": "system_context"
-    },
-    {
-      "step": "module_analysis",
-      "action": "Analyze specific module structure and API within system context",
-      "command": "~/.claude/scripts/gemini-wrapper -p \"Analyze module [MODULE_NAME] structure and exported API within system: [system_context]\"",
-      "output_to": "module_context"
-    }
-  ],
-  "target_files": [".workflow/docs/modules/[MODULE_NAME]/overview.md"]
-}
-```
+## Execution Commands
 
-## Analysis Templates
-
-### Project Structure Analysis Rules
-- Identify main modules and purposes
-- Map directory organization patterns
-- Extract entry points and configuration files
-- Recognize architectural styles and design patterns
-- Analyze module relationships and dependencies
-- Document technology stack and requirements
-
-### Module Analysis Rules
-- Identify module boundaries and entry points
-- Extract exported functions, classes, interfaces
-- Document internal organization and structure
-- Analyze API surfaces with types and parameters
-- Map dependencies within and between modules
-- Extract usage patterns and examples
-
-### API Analysis Rules
-- Classify endpoint types (REST, GraphQL, WebSocket, RPC)
-- Extract request/response parameters and schemas
-- Document authentication and authorization requirements
-- Generate OpenAPI 3.0 specification structure
-- Create comprehensive endpoint documentation
-- Provide usage examples and integration guides
-
-## Error Handling
-- **Invalid document type**: Clear error message with valid options
-- **Module not found**: Skip missing modules with warning
-- **Analysis failures**: Fall back to file-based analysis
-- **Permission issues**: Clear guidance on directory access
-
-## Key Benefits
-
-### Structured Documentation Process
-- **Task-based approach**: Documentation broken into manageable, trackable tasks
-- **Flow control integration**: Systematic analysis ensures completeness
-- **Progress visibility**: TODO_LIST.md provides clear completion status
-- **Quality assurance**: Each task has defined acceptance criteria
-
-### Workflow Integration
-- **Planning foundation**: Documentation provides context for implementation planning
-- **Execution consistency**: Same task execution model as implementation
-- **Context accumulation**: Documentation builds comprehensive project understanding
-
-## Usage Examples
-
-### Complete Documentation Workflow
+### Root Directory (Full Documentation)
 ```bash
-# Step 1: Create documentation plan and tasks
-/workflow:docs all
+# Level 1 - Module documentation (parallel)
+/workflow:execute IMPL-001
+/workflow:execute IMPL-002
+/workflow:execute IMPL-003
 
-# Step 2: Execute documentation tasks (after planning)
-/workflow:execute IMPL-001  # System overview
-/workflow:execute IMPL-002  # Module documentation
-/workflow:execute IMPL-003  # Architecture documentation
-/workflow:execute IMPL-004  # API documentation
+# Level 2 - Project README (after Level 1)
+/workflow:execute IMPL-004
+
+# Level 3 - Architecture & Examples (after Level 2, parallel)
+/workflow:execute IMPL-005
+/workflow:execute IMPL-006
+/workflow:execute IMPL-007  # if HTTP API present
 ```
-The system creates structured documentation tasks with proper session management, task.json files, and integration with the broader workflow system for systematic and trackable documentation generation.
+
+### Subdirectory (Module Only)
+```bash
+# Only Level 1 task generated
+/workflow:execute IMPL-001
+```
+
+## Simple Bash Commands
+
+### Check Documentation Status
+```bash
+# List existing documentation
+bash(find . -name "API.md" -o -name "README.md" -o -name "ARCHITECTURE.md" 2>/dev/null | grep -v ".workflow")
+
+# Count documentation files
+bash(find . -name "*.md" 2>/dev/null | grep -v ".workflow" | wc -l)
+```
+
+### Analyze Module Structure
+```bash
+# Discover modules
+bash(~/.claude/scripts/get_modules_by_depth.sh)
+
+# Count code files in directory
+bash(find src/modules -maxdepth 1 -type f \( -name "*.ts" -o -name "*.js" \) | wc -l)
+
+# Count subdirectories
+bash(find src/modules -maxdepth 1 -type d -not -path "src/modules" | wc -l)
+```
+
+### Session Management
+```bash
+# Create session directories
+bash(mkdir -p .workflow/WFS-docs-20240120/.{task,process,summaries})
+
+# Mark session as active
+bash(touch .workflow/.active-WFS-docs-20240120)
+
+# Read session configuration
+bash(cat .workflow/WFS-docs-20240120/.process/config.txt)
+
+# List session tasks
+bash(ls .workflow/WFS-docs-20240120/.task/*.json)
+```
+
+## Template Reference
+
+**Available Templates**:
+- `api.txt`: Unified template for Code API (Part A) and HTTP API (Part B)
+- `module-readme.txt`: Module purpose, usage, dependencies
+- `folder-navigation.txt`: Navigation README for folders with subdirectories
+- `project-readme.txt`: Project overview, getting started, module navigation
+- `project-architecture.txt`: System structure, module map, design patterns
+- `project-examples.txt`: End-to-end usage examples
+
+**Template Location**: `~/.claude/workflows/cli-templates/prompts/documentation/`
+
+## CLI Generate Mode Summary
+
+| Mode | CLI Placement | CLI MODE | Agent Role |
+|------|---------------|----------|------------|
+| **Default** | pre_analysis | analysis | Generates documentation files |
+| **--cli-generate** | implementation_approach | write | Validates and coordinates CLI output |
+
+## Related Commands
+- `/workflow:execute` - Execute documentation tasks
+- `/workflow:status` - View task progress
+- `/workflow:session:complete` - Mark session complete

.claude/commands/workflow/tools/status.md

@@ -1,258 +0,0 @@
----
-name: workflow:status
-description: Generate on-demand views from JSON task data
-usage: /workflow:status [task-id] [--format=<format>] [--validate]
-argument-hint: [optional: task-id, format, validation]
-examples:
-  - /workflow:status
-  - /workflow:status impl-1
-  - /workflow:status --format=hierarchy
-  - /workflow:status --validate
----
-
-# Workflow Status Command (/workflow:status)
-
-## Overview
-Generates on-demand views from JSON task data. No synchronization needed - all views are calculated from the current state of JSON files.
-
-## Core Principles
-**Data Source:** @~/.claude/workflows/workflow-architecture.md
-
-## Key Features
-
-### Pure View Generation
-- **No Sync**: Views are generated, not synchronized
-- **Always Current**: Reads latest JSON data every time
-- **No Persistence**: Views are temporary, not saved
-- **Single Source**: All data comes from JSON files only
-
-### Multiple View Formats
-- **Overview** (default): Current tasks and status
-- **Hierarchy**: Task relationships and structure
-- **Details**: Specific task information
-
-## Usage
-
-### Default Overview
-```bash
-/workflow:status
-```
-
-Generates current workflow overview:
-```markdown
-# Workflow Overview
-**Session**: WFS-user-auth
-**Phase**: IMPLEMENT
-**Type**: medium
-
-## Active Tasks
-- [⚠️] impl-1: Build authentication module (code-developer)
-- [⚠️] impl-2: Setup user management (code-developer)
-
-## Completed Tasks
-- [✅] impl-0: Project setup
-
-## Stats
-- **Total**: 8 tasks
-- **Completed**: 3
-- **Active**: 2
-- **Remaining**: 3
-```
-
-### Specific Task View
-```bash
-/workflow:status impl-1
-```
-
-Shows detailed task information:
-```markdown
-# Task: impl-1
-
-**Title**: Build authentication module
-**Status**: active
-**Agent**: @code-developer
-**Type**: feature
-
-## Context
-- **Requirements**: JWT authentication, OAuth2 support
-- **Scope**: src/auth/*, tests/auth/*
-- **Acceptance**: Module handles JWT tokens, OAuth2 flow implemented
-- **Inherited From**: WFS-user-auth
-
-## Relations
-- **Parent**: none
-- **Subtasks**: impl-1.1, impl-1.2
-- **Dependencies**: impl-0
-
-## Execution
-- **Attempts**: 0
-- **Last Attempt**: never
-
-## Metadata
-- **Created**: 2025-09-05T10:30:00Z
-- **Updated**: 2025-09-05T10:35:00Z
-```
-
-### Hierarchy View
-```bash
-/workflow:status --format=hierarchy
-```
-
-Shows task relationships:
-```markdown
-# Task Hierarchy
-
-## Main Tasks
-- impl-0: Project setup ✅
-- impl-1: Build authentication module ⚠️
-  - impl-1.1: Design auth schema
-  - impl-1.2: Implement auth logic
-- impl-2: Setup user management ⚠️
-
-## Dependencies
-- impl-1 → depends on → impl-0
-- impl-2 → depends on → impl-1
-```
-
-## View Generation Process
-
-### Data Loading
-```pseudo
-function generate_workflow_status(task_id, format):
-  // Load all current data
-  session = load_workflow_session()
-  all_tasks = load_all_task_json_files()
-
-  // Filter if specific task requested
-  if task_id:
-    target_task = find_task(all_tasks, task_id)
-    return generate_task_detail_view(target_task)
-
-  // Generate requested format
-  switch format:
-    case 'hierarchy':
-      return generate_hierarchy_view(all_tasks)
-    default:
-      return generate_overview(session, all_tasks)
-```
-
-### Real-Time Calculation
-- **Task Counts**: Calculated from JSON file status fields
-- **Relationships**: Built from JSON relations fields
-- **Status**: Read directly from current JSON state
-
-## Validation Mode
-
-### Basic Validation
-```bash
-/workflow:status --validate
-```
-
-Performs integrity checks:
-```markdown
-# Validation Results
-
-## JSON File Validation
-✅ All task JSON files are valid
-✅ Session file is valid and readable
-
-## Relationship Validation
-✅ All parent-child relationships are valid
-✅ All dependencies reference existing tasks
-✅ No circular dependencies detected
-
-## Hierarchy Validation
-✅ Task hierarchy within depth limits (max 3 levels)
-✅ All subtask references are bidirectional
-
-## Issues Found
-⚠️ impl-3: No subtasks defined (expected for leaf task)
-
-**Status**: All systems operational
-```
-
-### Validation Checks
-- **JSON Schema**: All files parse correctly
-- **References**: All task IDs exist
-- **Hierarchy**: Parent-child relationships are valid
-- **Dependencies**: No circular dependencies
-- **Depth**: Task hierarchy within limits
-
-## Error Handling
-
-### Missing Files
-```bash
-❌ Session file not found
-→ Initialize new workflow session? (y/n)
-
-❌ Task impl-5 not found
-→ Available tasks: impl-1, impl-2, impl-3, impl-4
-```
-
-### Invalid Data
-```bash
-❌ Invalid JSON in impl-2.json
-→ Cannot generate view for impl-2
-→ Repair file manually or recreate task
-
-⚠️ Circular dependency detected: impl-1 → impl-2 → impl-1
-→ Task relationships may be incorrect
-```
-
-## Performance Benefits
-
-### Fast Generation
-- **No File Writes**: Only reads JSON files
-- **No Sync Logic**: No complex synchronization
-- **Instant Results**: Generate views on demand
-- **No Conflicts**: No state consistency issues
-
-### Scalability
-- **Large Task Sets**: Handles hundreds of tasks efficiently
-- **Complex Hierarchies**: No performance degradation
-- **Concurrent Access**: Multiple views can be generated simultaneously
-
-## Integration
-
-### Workflow Integration
-- Use after task creation to see current state
-- Use for debugging task relationships
-
-### Command Integration
-```bash
-# Common workflow
-/task:create "New feature"
-/workflow:status                    # Check current state
-/task:breakdown impl-1
-/workflow:status --format=hierarchy # View new structure
-/task:execute impl-1.1
-```
-
-## Output Formats
-
-### Supported Formats
-- `overview` (default): General workflow status
-- `hierarchy`: Task relationships
-- `tasks`: Simple task list
-- `details`: Comprehensive information
-
-### Custom Filtering
-```bash
-# Show only active tasks
-/workflow:status --format=tasks --filter=active
-
-# Show completed tasks only
-/workflow:status --format=tasks --filter=completed
-
-# Show tasks for specific agent
-/workflow:status --format=tasks --agent=@code-developer
-```
-
-## Related Commands
-
-- `/task:create` - Create tasks (generates JSON data)
-- `/task:execute` - Execute tasks (updates JSON data)
-- `/task:breakdown` - Create subtasks (generates more JSON data)
-- `/workflow:vibe` - Coordinate agents (uses workflow status for coordination)
-
-This workflow status system provides instant, accurate views of workflow state without any synchronization complexity or performance overhead.

.claude/commands/workflow/tools/task-generate-agent.md

@@ -1,7 +1,6 @@
 ---
 name: task-generate-agent
 description: Autonomous task generation using action-planning-agent with discovery and output phases
-usage: /workflow:tools:task-generate-agent --session <session_id>
 argument-hint: "--session WFS-session-id"
 examples:
   - /workflow:tools:task-generate-agent --session WFS-auth
@@ -169,7 +168,21 @@ Task(
       {
         "type": "synthesis_specification",
         "path": "{synthesis_spec_path}",
-        "priority": "highest"
+        "priority": "highest",
+        "usage": "Primary requirement source - use for consolidated requirements and cross-role alignment"
+      },
+      {
+        "type": "role_analysis",
+        "path": "{role_analysis_path}",
+        "priority": "high",
+        "usage": "Technical/design/business details from specific roles. Common roles: system-architect (ADRs, APIs, caching), ui-designer (design tokens, layouts), product-manager (user stories, metrics)",
+        "note": "Dynamically discovered - multiple role analysis files included based on brainstorming results"
+      },
+      {
+        "type": "topic_framework",
+        "path": "{topic_framework_path}",
+        "priority": "low",
+        "usage": "Discussion context and framework structure"
       }
     ]
   },
@@ -202,16 +215,29 @@ Task(
         "on_error": "fail"
       }
     ],
-    "implementation_approach": {
-      "task_description": "Implement '[title]' following synthesis specification",
-      "modification_points": ["Apply requirements from synthesis"],
-      "logic_flow": [
-        "Load synthesis specification",
-        "Analyze existing patterns",
-        "Implement following specification",
-        "Validate against acceptance criteria"
-      ]
-    },
+    "implementation_approach": [
+      {
+        "step": 1,
+        "title": "Implement task following synthesis specification",
+        "description": "Implement '[title]' following synthesis specification. PRIORITY: Use synthesis-specification.md as primary requirement source. When implementation needs technical details (e.g., API schemas, caching configs, design tokens), refer to artifacts[] for detailed specifications from original role analyses.",
+        "modification_points": [
+          "Apply consolidated requirements from synthesis-specification.md",
+          "Follow technical guidelines from synthesis",
+          "Consult artifacts for implementation details when needed",
+          "Integrate with existing patterns"
+        ],
+        "logic_flow": [
+          "Load synthesis specification and relevant role artifacts",
+          "Execute MCP code-index discovery for relevant files",
+          "Analyze existing patterns and identify modification targets",
+          "Implement following specification",
+          "Consult artifacts for technical details when needed",
+          "Validate against acceptance criteria"
+        ],
+        "depends_on": [],
+        "output": "implementation"
+      }
+    ],
     "target_files": ["file:function:lines", "path/to/NewFile.ts"]
   }
 }
@@ -223,35 +249,231 @@ Task(
 \`\`\`markdown
 ---
 identifier: WFS-{session-id}
-source: "User requirements"
+source: "User requirements" | "File: path" | "Issue: ISS-001"
 analysis: .workflow/{session-id}/.process/ANALYSIS_RESULTS.md
+artifacts: .workflow/{session-id}/.brainstorming/
+context_package: .workflow/{session-id}/.process/context-package.json  # CCW smart context
+workflow_type: "standard | tdd | design"  # Indicates execution model
+verification_history:  # CCW quality gates
+  concept_verify: "passed | skipped | pending"
+  action_plan_verify: "pending"
+phase_progression: "brainstorm → context → analysis → concept_verify → planning"  # CCW workflow phases
 ---
 
 # Implementation Plan: {Project Title}
 
-## Summary
-Core requirements, objectives, and technical approach.
+## 1. Summary
+Core requirements, objectives, technical approach summary (2-3 paragraphs max).
 
-## Context Analysis
-- **Project**: Type, patterns, tech stack
-- **Modules**: Components and integration points
-- **Dependencies**: External libraries and constraints
-- **Patterns**: Code conventions and guidelines
+**Core Objectives**:
+- [Key objective 1]
+- [Key objective 2]
 
-## Brainstorming Artifacts
-- synthesis-specification.md (Highest priority)
-- topic-framework.md (Medium priority)
-- Role analyses: ui-designer, system-architect, etc.
+**Technical Approach**:
+- [High-level approach]
 
-## Task Breakdown
-- **Task Count**: N tasks, complexity level
-- **Hierarchy**: Flat/Two-level structure
-- **Dependencies**: Task dependency graph
+## 2. Context Analysis
 
-## Implementation Plan
-- **Execution Strategy**: Sequential/Parallel approach
-- **Resource Requirements**: Tools, dependencies, artifacts
-- **Success Criteria**: Metrics and acceptance conditions
+### CCW Workflow Context
+**Phase Progression**:
+- ✅ Phase 1: Brainstorming (synthesis-specification.md generated)
+- ✅ Phase 2: Context Gathering (context-package.json: {N} files, {M} modules analyzed)
+- ✅ Phase 3: Enhanced Analysis (ANALYSIS_RESULTS.md: Gemini/Qwen/Codex parallel insights)
+- ✅ Phase 4: Concept Verification ({X} clarifications answered, synthesis updated | skipped)
+- ⏳ Phase 5: Action Planning (current phase - generating IMPL_PLAN.md)
+
+**Quality Gates**:
+- concept-verify: ✅ Passed (0 ambiguities remaining) | ⏭️ Skipped (user decision) | ⏳ Pending
+- action-plan-verify: ⏳ Pending (recommended before /workflow:execute)
+
+**Context Package Summary**:
+- **Focus Paths**: {list key directories from context-package.json}
+- **Key Files**: {list primary files for modification}
+- **Module Depth Analysis**: {from get_modules_by_depth.sh output}
+- **Smart Context**: {total file count} files, {module count} modules, {dependency count} dependencies identified
+
+### Project Profile
+- **Type**: Greenfield/Enhancement/Refactor
+- **Scale**: User count, data volume, complexity
+- **Tech Stack**: Primary technologies
+- **Timeline**: Duration and milestones
+
+### Module Structure
+\`\`\`
+[Directory tree showing key modules]
+\`\`\`
+
+### Dependencies
+**Primary**: [Core libraries and frameworks]
+**APIs**: [External services]
+**Development**: [Testing, linting, CI/CD tools]
+
+### Patterns & Conventions
+- **Architecture**: [Key patterns like DI, Event-Driven]
+- **Component Design**: [Design patterns]
+- **State Management**: [State strategy]
+- **Code Style**: [Naming, TypeScript coverage]
+
+## 3. Brainstorming Artifacts Reference
+
+### Artifact Usage Strategy
+**Primary Reference (synthesis-specification.md)**:
+- **What**: Comprehensive implementation blueprint from multi-role synthesis
+- **When**: Every task references this first for requirements and design decisions
+- **How**: Extract architecture decisions, UI/UX patterns, functional requirements, non-functional requirements
+- **Priority**: Authoritative - overrides role-specific analyses when conflicts arise
+- **CCW Value**: Consolidates insights from all brainstorming roles into single source of truth
+
+**Context Intelligence (context-package.json)**:
+- **What**: Smart context gathered by CCW's context-gather phase
+- **Content**: Focus paths, dependency graph, existing patterns, module structure
+- **Usage**: Tasks load this via \`flow_control.preparatory_steps\` for environment setup
+- **CCW Value**: Automated intelligent context discovery replacing manual file exploration
+
+**Technical Analysis (ANALYSIS_RESULTS.md)**:
+- **What**: Gemini/Qwen/Codex parallel analysis results
+- **Content**: Optimization strategies, risk assessment, architecture review, implementation patterns
+- **Usage**: Referenced in task planning for technical guidance and risk mitigation
+- **CCW Value**: Multi-model parallel analysis providing comprehensive technical intelligence
+
+### Integrated Specifications (Highest Priority)
+- **synthesis-specification.md**: Comprehensive implementation blueprint
+  - Contains: Architecture design, UI/UX guidelines, functional/non-functional requirements, implementation roadmap, risk assessment
+
+### Supporting Artifacts (Reference)
+- **topic-framework.md**: Role-specific discussion points and analysis framework
+- **system-architect/analysis.md**: Detailed architecture specifications
+- **ui-designer/analysis.md**: Layout and component specifications
+- **product-manager/analysis.md**: Product vision and user stories
+
+**Artifact Priority in Development**:
+1. synthesis-specification.md (primary reference for all tasks)
+2. context-package.json (smart context for execution environment)
+3. ANALYSIS_RESULTS.md (technical analysis and optimization strategies)
+4. Role-specific analyses (fallback for detailed specifications)
+
+## 4. Implementation Strategy
+
+### Execution Strategy
+**Execution Model**: [Sequential | Parallel | Phased | TDD Cycles]
+
+**Rationale**: [Why this execution model fits the project]
+
+**Parallelization Opportunities**:
+- [List independent workstreams]
+
+**Serialization Requirements**:
+- [List critical dependencies]
+
+### Architectural Approach
+**Key Architecture Decisions**:
+- [ADR references from synthesis]
+- [Justification for architecture patterns]
+
+**Integration Strategy**:
+- [How modules communicate]
+- [State management approach]
+
+### Key Dependencies
+**Task Dependency Graph**:
+\`\`\`
+[High-level dependency visualization]
+\`\`\`
+
+**Critical Path**: [Identify bottleneck tasks]
+
+### Testing Strategy
+**Testing Approach**:
+- Unit testing: [Tools, scope]
+- Integration testing: [Key integration points]
+- E2E testing: [Critical user flows]
+
+**Coverage Targets**:
+- Lines: ≥70%
+- Functions: ≥70%
+- Branches: ≥65%
+
+**Quality Gates**:
+- [CI/CD gates]
+- [Performance budgets]
+
+## 5. Task Breakdown Summary
+
+### Task Count
+**{N} tasks** (flat hierarchy | two-level hierarchy, sequential | parallel execution)
+
+### Task Structure
+- **IMPL-1**: [Main task title]
+- **IMPL-2**: [Main task title]
+...
+
+### Complexity Assessment
+- **High**: [List with rationale]
+- **Medium**: [List]
+- **Low**: [List]
+
+### Dependencies
+[Reference Section 4.3 for dependency graph]
+
+**Parallelization Opportunities**:
+- [Specific task groups that can run in parallel]
+
+## 6. Implementation Plan (Detailed Phased Breakdown)
+
+### Execution Strategy
+
+**Phase 1 (Weeks 1-2): [Phase Name]**
+- **Tasks**: IMPL-1, IMPL-2
+- **Deliverables**:
+  - [Specific deliverable 1]
+  - [Specific deliverable 2]
+- **Success Criteria**:
+  - [Measurable criterion]
+
+**Phase 2 (Weeks 3-N): [Phase Name]**
+...
+
+### Resource Requirements
+
+**Development Team**:
+- [Team composition and skills]
+
+**External Dependencies**:
+- [Third-party services, APIs]
+
+**Infrastructure**:
+- [Development, staging, production environments]
+
+## 7. Risk Assessment & Mitigation
+
+| Risk | Impact | Probability | Mitigation Strategy | Owner |
+|------|--------|-------------|---------------------|-------|
+| [Risk description] | High/Med/Low | High/Med/Low | [Strategy] | [Role] |
+
+**Critical Risks** (High impact + High probability):
+- [Risk 1]: [Detailed mitigation plan]
+
+**Monitoring Strategy**:
+- [How risks will be monitored]
+
+## 8. Success Criteria
+
+**Functional Completeness**:
+- [ ] All requirements from synthesis-specification.md implemented
+- [ ] All acceptance criteria from task.json files met
+
+**Technical Quality**:
+- [ ] Test coverage ≥70%
+- [ ] Bundle size within budget
+- [ ] Performance targets met
+
+**Operational Readiness**:
+- [ ] CI/CD pipeline operational
+- [ ] Monitoring and logging configured
+- [ ] Documentation complete
+
+**Business Metrics**:
+- [ ] [Key business metrics from synthesis]
 \`\`\`
 
 #### 3. TODO_LIST.md

.claude/commands/workflow/tools/task-generate-tdd.md

@@ -1,11 +1,7 @@
 ---
 name: task-generate-tdd
 description: Generate TDD task chains with Red-Green-Refactor dependencies
-usage: /workflow:tools:task-generate-tdd --session <session_id> [--agent]
 argument-hint: "--session WFS-session-id [--agent]"
-examples:
-  - /workflow:tools:task-generate-tdd --session WFS-auth
-  - /workflow:tools:task-generate-tdd --session WFS-auth --agent
 allowed-tools: Read(*), Write(*), Bash(gemini-wrapper:*), TodoWrite(*)
 ---
 
@@ -20,6 +16,9 @@ Generate TDD-specific task chains from analysis results with enforced Red-Green-
 - **Phase-Explicit**: Each task marked with Red/Green/Refactor phase
 - **Artifact-Aware**: Integrates brainstorming outputs
 - **Memory-First**: Reuse loaded documents from memory
+- **Context-Aware**: Analyzes existing codebase and test patterns
+- **Iterative Green Phase**: Auto-diagnose and fix test failures with Gemini + optional Codex
+- **Safety-First**: Auto-revert on max iterations to prevent broken state
 
 ## Core Responsibilities
 - Parse analysis results and identify testable features
@@ -47,32 +46,18 @@ Generate TDD-specific task chains from analysis results with enforced Red-Green-
    - Else: Scan `.workflow/{session_id}/.brainstorming/` directory
    - Detect: synthesis-specification.md, topic-framework.md, role analyses
 
-### Phase 2: TDD Task Analysis
+### Phase 2: TDD Task JSON Generation
 
-#### Gemini TDD Breakdown
-```bash
-cd project-root && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: Generate TDD task breakdown with Red-Green-Refactor chains
-TASK: Analyze ANALYSIS_RESULTS.md and create TDD-structured task breakdown
-CONTEXT: @{.workflow/{session_id}/ANALYSIS_RESULTS.md,.workflow/{session_id}/.brainstorming/*}
-EXPECTED:
-- Feature list with testable requirements (identify 3-8 features)
-- Test cases for each feature (Red phase) - specific test scenarios
-- Implementation requirements (Green phase) - minimal code to pass
-- Refactoring opportunities (Refactor phase) - quality improvements
+**Input**: Use `.process/ANALYSIS_RESULTS.md` directly (enhanced with TDD structure from concept-enhanced phase)
+
+**Note**: The ANALYSIS_RESULTS.md now includes TDD-specific breakdown:
+- Feature list with testable requirements
+- Test cases for Red phase
+- Implementation requirements for Green phase
+- Refactoring opportunities
 - Task dependencies and execution order
-- Focus paths for each phase
-RULES:
-- Each feature must have TEST → IMPL → REFACTOR chain
-- Tests must define clear failure conditions
-- Implementation must be minimal to pass tests
-- Refactoring must maintain green tests
-- Output structured markdown for task generation
-- Maximum 10 features (30 total tasks)
-" > .workflow/{session_id}/.process/TDD_TASK_BREAKDOWN.md
-```
 
-### Phase 3: TDD Task JSON Generation
+### Phase 3: Enhanced IMPL_PLAN.md Generation
 
 #### Task Chain Structure
 For each feature, generate 3 tasks with ID format:
@@ -145,19 +130,23 @@ For each feature, generate 3 tasks with ID format:
   "meta": {
     "type": "feature",
     "agent": "@code-developer",
-    "tdd_phase": "green"
+    "tdd_phase": "green",
+    "max_iterations": 3,
+    "use_codex": false
   },
   "context": {
     "requirements": [
       "Implement minimal AuthService to pass TEST-1.1",
       "Handle valid and invalid credentials",
-      "Return appropriate success/error responses"
+      "Return appropriate success/error responses",
+      "If tests fail after implementation, diagnose and fix iteratively"
     ],
     "focus_paths": ["src/auth/AuthService.ts", "tests/auth/login.test.ts"],
     "acceptance": [
       "All tests in TEST-1.1 pass",
       "Implementation is minimal and focused",
-      "No over-engineering or premature optimization"
+      "No over-engineering or premature optimization",
+      "Test failures resolved within iteration limit"
     ],
     "depends_on": ["TEST-1.1"]
   },
@@ -172,21 +161,85 @@ For each feature, generate 3 tasks with ID format:
       },
       {
         "step": "verify_tests_failing",
-        "action": "Confirm tests are currently failing",
+        "action": "Confirm tests are currently failing (Red phase validation)",
         "command": "bash(npm test -- tests/auth/login.test.ts || echo 'Tests failing as expected')",
         "output_to": "initial_test_status",
         "on_error": "warn"
+      },
+      {
+        "step": "load_test_context",
+        "action": "Load test patterns and framework info",
+        "command": "bash(cat .workflow/WFS-xxx/.process/test-context-package.json 2>/dev/null || echo '{}')",
+        "output_to": "test_context",
+        "on_error": "skip_optional"
+      }
+    ],
+    "implementation_approach": [
+      {
+        "step": 1,
+        "title": "Implement minimal code to pass tests",
+        "description": "Write minimal code based on test requirements following TDD principles - no over-engineering",
+        "modification_points": [
+          "Load test requirements from TEST phase",
+          "Create/modify implementation files",
+          "Implement only what tests require",
+          "Focus on passing tests, not perfection"
+        ],
+        "logic_flow": [
+          "Load test requirements from [test_requirements]",
+          "Parse test expectations and edge cases",
+          "Write minimal implementation code",
+          "Avoid premature optimization or abstraction"
+        ],
+        "depends_on": [],
+        "output": "initial_implementation"
+      },
+      {
+        "step": 2,
+        "title": "Test and iteratively fix until passing",
+        "description": "Run tests and enter iterative fix cycle if needed (max 3 iterations with auto-revert on failure)",
+        "modification_points": [
+          "Execute test suite",
+          "If tests fail: diagnose with Gemini",
+          "Apply fixes (manual or Codex if meta.use_codex=true)",
+          "Retest and iterate"
+        ],
+        "logic_flow": [
+          "Run test suite",
+          "If all tests pass → Complete",
+          "If tests fail → Enter iteration loop (max 3):",
+          "  Extract failure messages and stack traces",
+          "  Use Gemini bug-fix template for diagnosis",
+          "  Generate targeted fix recommendations",
+          "  Apply fixes (manual or Codex)",
+          "  Rerun tests",
+          "  If pass → Complete, if fail → Continue iteration",
+          "If max_iterations reached → Trigger auto-revert"
+        ],
+        "command": "bash(npm test -- tests/auth/login.test.ts)",
+        "depends_on": [1],
+        "output": "test_results"
       }
     ],
     "post_completion": [
       {
         "step": "verify_tests_passing",
-        "action": "Confirm all tests now pass",
+        "action": "Confirm all tests now pass (Green phase achieved)",
         "command": "bash(npm test -- tests/auth/login.test.ts)",
         "output_to": "final_test_status",
         "on_error": "fail"
       }
-    ]
+    ],
+    "error_handling": {
+      "max_iterations_reached": {
+        "action": "revert_all_changes",
+        "commands": [
+          "bash(git reset --hard HEAD)",
+          "bash(echo 'TDD Green phase failed: Unable to pass tests within 3 iterations' > .workflow/WFS-xxx/.process/green-phase-failure.md)"
+        ],
+        "report": "Generate failure report in .summaries/IMPL-1.1-failure-report.md"
+      }
+    }
   }
 }
 ```
@@ -248,19 +301,283 @@ For each feature, generate 3 tasks with ID format:
 }
 ```
 
-### Phase 4: TDD_PLAN.md Generation
+### Phase 4: Unified IMPL_PLAN.md Generation
 
-Generate TDD-specific plan with:
-- Feature breakdown
-- Red-Green-Refactor chains
-- Execution order
-- TDD compliance checkpoints
+Generate single comprehensive IMPL_PLAN.md with enhanced 8-section structure:
 
-### Phase 5: Enhanced IMPL_PLAN.md Generation
+**Frontmatter**:
+```yaml
+---
+identifier: WFS-{session-id}
+source: "User requirements" | "File: path" | "Issue: ISS-001"
+analysis: .workflow/{session-id}/.process/ANALYSIS_RESULTS.md
+artifacts: .workflow/{session-id}/.brainstorming/
+context_package: .workflow/{session-id}/.process/context-package.json  # CCW smart context
+workflow_type: "tdd"  # TDD-specific workflow
+verification_history:  # CCW quality gates
+  concept_verify: "passed | skipped | pending"
+  action_plan_verify: "pending"
+phase_progression: "brainstorm → context → test_context → analysis → concept_verify → tdd_planning"  # TDD workflow phases
+feature_count: N
+task_count: 3N
+tdd_chains: N
+---
+```
 
-Generate standard IMPL_PLAN.md with TDD context reference.
+**Complete Structure** (8 Sections):
 
-### Phase 6: TODO_LIST.md Generation
+```markdown
+# Implementation Plan: {Project Title}
+
+## 1. Summary
+Core requirements, objectives, and TDD-specific technical approach (2-3 paragraphs max).
+
+**Core Objectives**:
+- [Key objective 1]
+- [Key objective 2]
+
+**Technical Approach**:
+- TDD-driven development with Red-Green-Refactor cycles
+- [Other high-level approaches]
+
+## 2. Context Analysis
+
+### CCW Workflow Context
+**Phase Progression** (TDD-specific):
+- ✅ Phase 1: Brainstorming (synthesis-specification.md generated)
+- ✅ Phase 2: Context Gathering (context-package.json: {N} files, {M} modules analyzed)
+- ✅ Phase 3: Test Coverage Analysis (test-context-package.json: existing test patterns identified)
+- ✅ Phase 4: TDD Analysis (ANALYSIS_RESULTS.md: test-first requirements with Gemini/Qwen insights)
+- ✅ Phase 5: Concept Verification ({X} clarifications answered, test requirements clarified | skipped)
+- ⏳ Phase 6: TDD Task Generation (current phase - generating IMPL_PLAN.md with TDD chains)
+
+**Quality Gates**:
+- concept-verify: ✅ Passed (test requirements clarified, 0 ambiguities) | ⏭️ Skipped (user decision) | ⏳ Pending
+- action-plan-verify: ⏳ Pending (recommended before /workflow:execute for TDD dependency validation)
+
+**Context Package Summary**:
+- **Focus Paths**: {list key directories from context-package.json}
+- **Key Files**: {list primary files for modification}
+- **Test Context**: {existing test patterns, coverage baseline, test framework detected}
+- **Module Depth Analysis**: {from get_modules_by_depth.sh output}
+- **Smart Context**: {total file count} files, {module count} modules, {test file count} tests identified
+
+### Project Profile
+- **Type**: Greenfield/Enhancement/Refactor
+- **Scale**: User count, data volume, complexity
+- **Tech Stack**: Primary technologies
+- **Timeline**: Duration and milestones
+- **TDD Framework**: Testing framework and tools
+
+### Module Structure
+```
+[Directory tree showing key modules and test directories]
+```
+
+### Dependencies
+**Primary**: [Core libraries and frameworks]
+**Testing**: [Test framework, mocking libraries]
+**Development**: [Linting, CI/CD tools]
+
+### Patterns & Conventions
+- **Architecture**: [Key patterns]
+- **Testing Patterns**: [Unit, integration, E2E patterns]
+- **Code Style**: [Naming, TypeScript coverage]
+
+## 3. Brainstorming Artifacts Reference
+
+### Artifact Usage Strategy
+**Primary Reference (synthesis-specification.md)**:
+- **What**: Comprehensive implementation blueprint from multi-role synthesis
+- **When**: Every TDD task (TEST/IMPL/REFACTOR) references this for requirements and acceptance criteria
+- **How**: Extract testable requirements, architecture decisions, expected behaviors
+- **Priority**: Authoritative - defines what to test and how to implement
+- **CCW Value**: Consolidates insights from all brainstorming roles into single source of truth for TDD
+
+**Context Intelligence (context-package.json & test-context-package.json)**:
+- **What**: Smart context from CCW's context-gather and test-context-gather phases
+- **Content**: Focus paths, dependency graph, existing test patterns, test framework configuration
+- **Usage**: RED phase loads test patterns, GREEN phase loads implementation context
+- **CCW Value**: Automated discovery of existing tests and patterns for TDD consistency
+
+**Technical Analysis (ANALYSIS_RESULTS.md)**:
+- **What**: Gemini/Qwen parallel analysis with TDD-specific breakdown
+- **Content**: Testable requirements, test scenarios, implementation strategies, risk assessment
+- **Usage**: RED phase references test cases, GREEN phase references implementation approach
+- **CCW Value**: Multi-model analysis providing comprehensive TDD guidance
+
+### Integrated Specifications (Highest Priority)
+- **synthesis-specification.md**: Comprehensive implementation blueprint
+  - Contains: Architecture design, functional/non-functional requirements
+
+### Supporting Artifacts (Reference)
+- **topic-framework.md**: Discussion framework
+- **system-architect/analysis.md**: Architecture specifications
+- **Role-specific analyses**: [Other relevant analyses]
+
+**Artifact Priority in Development**:
+1. synthesis-specification.md (primary reference for test cases and implementation)
+2. test-context-package.json (existing test patterns for TDD consistency)
+3. context-package.json (smart context for execution environment)
+4. ANALYSIS_RESULTS.md (technical analysis with TDD breakdown)
+5. Role-specific analyses (supplementary)
+
+## 4. Implementation Strategy
+
+### Execution Strategy
+**Execution Model**: TDD Cycles (Red-Green-Refactor)
+
+**Rationale**: Test-first approach ensures correctness and reduces bugs
+
+**TDD Cycle Pattern**:
+- RED: Write failing test
+- GREEN: Implement minimal code to pass (with test-fix cycle if needed)
+- REFACTOR: Improve code quality while keeping tests green
+
+**Parallelization Opportunities**:
+- [Independent features that can be developed in parallel]
+
+### Architectural Approach
+**Key Architecture Decisions**:
+- [ADR references from synthesis]
+- [TDD-compatible architecture patterns]
+
+**Integration Strategy**:
+- [How modules communicate]
+- [Test isolation strategy]
+
+### Key Dependencies
+**Task Dependency Graph**:
+```
+Feature 1:
+  TEST-1.1 (RED)
+      ↓
+  IMPL-1.1 (GREEN) [with test-fix cycle]
+      ↓
+  REFACTOR-1.1 (REFACTOR)
+
+Feature 2:
+  TEST-2.1 (RED) [depends on REFACTOR-1.1 if related]
+      ↓
+  IMPL-2.1 (GREEN)
+      ↓
+  REFACTOR-2.1 (REFACTOR)
+```
+
+**Critical Path**: [Identify bottleneck features]
+
+### Testing Strategy
+**TDD Testing Approach**:
+- Unit testing: Each feature has comprehensive unit tests
+- Integration testing: Cross-feature integration
+- E2E testing: Critical user flows after all TDD cycles
+
+**Coverage Targets**:
+- Lines: ≥80% (TDD ensures high coverage)
+- Functions: ≥80%
+- Branches: ≥75%
+
+**Quality Gates**:
+- All tests must pass before moving to next phase
+- Refactor phase must maintain test success
+
+## 5. TDD Task Chains (TDD-Specific Section)
+
+### Feature-by-Feature TDD Chains
+
+**Feature 1: {Feature Name}**
+```
+🔴 TEST-1.1: Write failing test for {feature}
+    ↓
+🟢 IMPL-1.1: Implement to pass tests (includes test-fix cycle: max 3 iterations)
+    ↓
+🔵 REFACTOR-1.1: Refactor implementation while keeping tests green
+```
+
+**Feature 2: {Feature Name}**
+```
+🔴 TEST-2.1: Write failing test for {feature}
+    ↓
+🟢 IMPL-2.1: Implement to pass tests (includes test-fix cycle)
+    ↓
+🔵 REFACTOR-2.1: Refactor implementation
+```
+
+[Continue for all N features]
+
+### TDD Task Breakdown Summary
+- **Total Features**: {N}
+- **Total Tasks**: {3N} (N TEST + N IMPL + N REFACTOR)
+- **TDD Chains**: {N}
+
+## 6. Implementation Plan (Detailed Phased Breakdown)
+
+### Execution Strategy
+
+**TDD Cycle Execution**: Feature-by-feature sequential TDD cycles
+
+**Phase 1 (Weeks 1-2): Foundation Features**
+- **Features**: Feature 1, Feature 2
+- **Tasks**: TEST-1.1, IMPL-1.1, REFACTOR-1.1, TEST-2.1, IMPL-2.1, REFACTOR-2.1
+- **Deliverables**:
+  - Complete TDD cycles for foundation features
+  - All tests passing
+- **Success Criteria**:
+  - ≥80% test coverage
+  - All RED-GREEN-REFACTOR cycles completed
+
+**Phase 2 (Weeks 3-N): Advanced Features**
+[Continue with remaining features]
+
+### Resource Requirements
+
+**Development Team**:
+- [Team composition with TDD experience]
+
+**External Dependencies**:
+- [Testing frameworks, mocking services]
+
+**Infrastructure**:
+- [CI/CD with test automation]
+
+## 7. Risk Assessment & Mitigation
+
+| Risk | Impact | Probability | Mitigation Strategy | Owner |
+|------|--------|-------------|---------------------|-------|
+| Tests fail repeatedly in GREEN phase | High | Medium | Test-fix cycle (max 3 iterations) with auto-revert | Dev Team |
+| Complex features hard to test | High | Medium | Break down into smaller testable units | Architect |
+| [Other risks] | Med/Low | Med/Low | [Strategies] | [Owner] |
+
+**Critical Risks** (TDD-Specific):
+- **GREEN phase failures**: Mitigated by test-fix cycle with Gemini diagnosis
+- **Test coverage gaps**: Mitigated by TDD-first approach ensuring tests before code
+
+**Monitoring Strategy**:
+- Track TDD cycle completion rate
+- Monitor test success rate per iteration
+
+## 8. Success Criteria
+
+**Functional Completeness**:
+- [ ] All features implemented through TDD cycles
+- [ ] All RED-GREEN-REFACTOR cycles completed successfully
+
+**Technical Quality**:
+- [ ] Test coverage ≥80% (ensured by TDD)
+- [ ] All tests passing (GREEN state achieved)
+- [ ] Code refactored for quality (REFACTOR phase completed)
+
+**Operational Readiness**:
+- [ ] CI/CD pipeline with automated test execution
+- [ ] Test failure alerting configured
+
+**TDD Compliance**:
+- [ ] Every feature has TEST → IMPL → REFACTOR chain
+- [ ] No implementation without tests (RED-first principle)
+- [ ] Refactoring did not break tests
+```
+
+### Phase 5: TODO_LIST.md Generation
 
 Generate task list with TDD phase indicators:
 ```markdown
@@ -270,7 +587,7 @@ Generate task list with TDD phase indicators:
 - [ ] **REFACTOR-1.1**: Refactor implementation (🔵 REFACTOR) [depends: IMPL-1.1] → [📋](./.task/REFACTOR-1.1.json)
 ```
 
-### Phase 7: Session State Update
+### Phase 6: Session State Update
 
 Update workflow-session.json with TDD metadata:
 ```json
@@ -285,18 +602,18 @@ Update workflow-session.json with TDD metadata:
 ## Output Files Structure
 ```
 .workflow/{session-id}/
-├── IMPL_PLAN.md                     # Standard implementation plan
-├── TDD_PLAN.md                      # TDD-specific plan ⭐ NEW
+├── IMPL_PLAN.md                     # Unified plan with TDD Task Chains section
 ├── TODO_LIST.md                     # Progress tracking with TDD phases
 ├── .task/
 │   ├── TEST-1.1.json                # Red phase task
-│   ├── IMPL-1.1.json                # Green phase task
+│   ├── IMPL-1.1.json                # Green phase task (with test-fix-cycle)
 │   ├── REFACTOR-1.1.json            # Refactor phase task
 │   └── ...
 └── .process/
-    ├── ANALYSIS_RESULTS.md          # Input from concept-enhanced
-    ├── TDD_TASK_BREAKDOWN.md        # Gemini TDD breakdown ⭐ NEW
-    └── context-package.json         # Input from context-gather
+    ├── ANALYSIS_RESULTS.md          # Enhanced with TDD breakdown from concept-enhanced
+    ├── test-context-package.json    # Test coverage analysis
+    ├── context-package.json         # Input from context-gather
+    └── green-fix-iteration-*.md     # Fix logs from Green phase
 ```
 
 ## Validation Rules
@@ -356,13 +673,49 @@ Structure:
 - Feature 2: TEST-2.1 → IMPL-2.1 → REFACTOR-2.1
 
 Plans generated:
-- TDD Plan: .workflow/WFS-auth/TDD_PLAN.md
-- Implementation Plan: .workflow/WFS-auth/IMPL_PLAN.md
+- Unified Plan: .workflow/WFS-auth/IMPL_PLAN.md (includes TDD Task Chains section)
 
 Next: /workflow:execute or /workflow:tdd-verify
 ```
 
+## Test Coverage Analysis Integration
+
+The TDD workflow includes test coverage analysis (via `/workflow:tools:test-context-gather`) to:
+- Detect existing test patterns and conventions
+- Identify current test coverage gaps
+- Discover test framework and configuration
+- Enable integration with existing tests
+
+This makes TDD workflow context-aware instead of assuming greenfield scenarios.
+
+## Iterative Green Phase with Test-Fix Cycle
+
+IMPL (Green phase) tasks include automatic test-fix cycle:
+
+**Process Flow**:
+1. **Initial Implementation**: Write minimal code to pass tests
+2. **Test Execution**: Run test suite
+3. **Success Path**: Tests pass → Complete task
+4. **Failure Path**: Tests fail → Enter iterative fix cycle:
+   - **Gemini Diagnosis**: Analyze failures with bug-fix template
+   - **Fix Application**: Manual (default) or Codex (if meta.use_codex=true)
+   - **Retest**: Verify fix resolves failures
+   - **Repeat**: Up to max_iterations (default: 3)
+5. **Safety Net**: Auto-revert all changes if max iterations reached
+
+**Key Benefits**:
+- ✅ Faster feedback loop within Green phase
+- ✅ Autonomous recovery from initial implementation errors
+- ✅ Systematic debugging with Gemini's bug-fix template
+- ✅ Safe rollback prevents broken TDD state
+
+## Configuration Options
+- **meta.max_iterations**: Number of fix attempts (default: 3 for TDD, 5 for test-gen)
+- **meta.use_codex**: Enable Codex automated fixes (default: false, manual)
+
 ## Related Commands
-- `/workflow:tdd-plan` - Orchestrates TDD workflow planning
+- `/workflow:tdd-plan` - Orchestrates TDD workflow planning (6 phases)
+- `/workflow:tools:test-context-gather` - Analyzes test coverage
 - `/workflow:execute` - Executes TDD tasks in order
 - `/workflow:tdd-verify` - Verifies TDD compliance
+- `/workflow:test-gen` - Post-implementation test generation

.claude/commands/workflow/tools/task-generate.md

@@ -1,10 +1,10 @@
 ---
 name: task-generate
 description: Generate task JSON files and IMPL_PLAN.md from analysis results with artifacts integration
-usage: /workflow:tools:task-generate --session <session_id>
-argument-hint: "--session WFS-session-id"
+argument-hint: "--session WFS-session-id [--cli-execute]"
 examples:
   - /workflow:tools:task-generate --session WFS-auth
+  - /workflow:tools:task-generate --session WFS-auth --cli-execute
 ---
 
 # Task Generation Command
@@ -12,12 +12,30 @@ examples:
 ## Overview
 Generate task JSON files and IMPL_PLAN.md from analysis results with automatic artifact detection and integration.
 
+## Execution Modes
+
+### Agent Mode (Default)
+Tasks execute within agent context using agent's capabilities:
+- Agent reads synthesis specifications
+- Agent implements following requirements
+- Agent validates implementation
+- **Benefit**: Seamless context within single agent execution
+
+### CLI Execute Mode (`--cli-execute`)
+Tasks execute using Codex CLI with resume mechanism:
+- Each task uses `codex exec` command in `implementation_approach`
+- First task establishes Codex session
+- Subsequent tasks use `codex exec "..." resume --last` for context continuity
+- **Benefit**: Codex's autonomous development capabilities with persistent context
+- **Use Case**: Complex implementation requiring Codex's reasoning and iteration
+
 ## Core Philosophy
 - **Analysis-Driven**: Generate from ANALYSIS_RESULTS.md
 - **Artifact-Aware**: Auto-detect brainstorming outputs
 - **Context-Rich**: Embed comprehensive context in task JSON
 - **Flow-Control Ready**: Pre-define implementation steps
 - **Memory-First**: Reuse loaded documents from memory
+- **CLI-Aware**: Support Codex resume mechanism for persistent context
 
 ## Core Responsibilities
 - Parse analysis results and extract tasks
@@ -84,21 +102,22 @@ Generate task JSON files and IMPL_PLAN.md from analysis results with automatic a
         "source": "brainstorm_synthesis",
         "path": ".workflow/WFS-[session]/.brainstorming/synthesis-specification.md",
         "priority": "highest",
-        "contains": "complete_integrated_specification"
+        "usage": "Primary requirement source - use for consolidated requirements and cross-role alignment"
+      },
+      {
+        "type": "role_analysis",
+        "source": "brainstorm_roles",
+        "path": ".workflow/WFS-[session]/.brainstorming/[role-name]/analysis.md",
+        "priority": "high",
+        "usage": "Technical/design/business details from specific roles. Common roles: system-architect (ADRs, APIs, caching), ui-designer (design tokens, layouts), product-manager (user stories, metrics)",
+        "note": "Dynamically discovered - multiple role analysis files may be included based on brainstorming results"
       },
       {
         "type": "topic_framework",
         "source": "brainstorm_framework",
         "path": ".workflow/WFS-[session]/.brainstorming/topic-framework.md",
-        "priority": "medium",
-        "contains": "discussion_framework_structure"
-      },
-      {
-        "type": "individual_role_analysis",
-        "source": "brainstorm_roles",
-        "path": ".workflow/WFS-[session]/.brainstorming/[role]/analysis.md",
         "priority": "low",
-        "contains": "role_specific_analysis_fallback"
+        "usage": "Discussion context and framework structure"
       }
     ]
   },
@@ -115,14 +134,16 @@ Generate task JSON files and IMPL_PLAN.md from analysis results with automatic a
         "on_error": "skip_optional"
       },
       {
-        "step": "load_individual_role_artifacts",
-        "action": "Load individual role analyses as fallback",
+        "step": "load_role_analysis_artifacts",
+        "action": "Load role-specific analysis documents for technical details",
+        "note": "These artifacts contain implementation details not in synthesis. Consult when needing: API schemas, caching configs, design tokens, ADRs, performance metrics.",
         "commands": [
           "bash(find .workflow/WFS-[session]/.brainstorming/ -name 'analysis.md' 2>/dev/null | head -8)",
+          "Read(.workflow/WFS-[session]/.brainstorming/system-architect/analysis.md)",
           "Read(.workflow/WFS-[session]/.brainstorming/ui-designer/analysis.md)",
-          "Read(.workflow/WFS-[session]/.brainstorming/system-architect/analysis.md)"
+          "Read(.workflow/WFS-[session]/.brainstorming/product-manager/analysis.md)"
         ],
-        "output_to": "individual_artifacts",
+        "output_to": "role_analysis_artifacts",
         "on_error": "skip_optional"
       },
       {
@@ -151,21 +172,52 @@ Generate task JSON files and IMPL_PLAN.md from analysis results with automatic a
         "on_error": "fail"
       }
     ],
-    "implementation_approach": {
-      "task_description": "Implement '[title]' following synthesis specification",
-      "modification_points": [
-        "Apply consolidated requirements from synthesis-specification.md",
-        "Follow technical guidelines from synthesis",
-        "Integrate with existing patterns"
-      ],
-      "logic_flow": [
-        "Load synthesis specification",
-        "Extract requirements and design",
-        "Analyze existing patterns",
-        "Implement following specification",
-        "Validate against acceptance criteria"
-      ]
-    },
+    "implementation_approach": [
+      {
+        "step": 1,
+        "title": "Implement task following synthesis specification",
+        "description": "Implement '[title]' following synthesis specification. PRIORITY: Use synthesis-specification.md as primary requirement source. When implementation needs technical details (e.g., API schemas, caching configs, design tokens), refer to artifacts[] for detailed specifications from original role analyses.",
+        "modification_points": [
+          "Apply consolidated requirements from synthesis-specification.md",
+          "Follow technical guidelines from synthesis",
+          "Consult artifacts for implementation details when needed",
+          "Integrate with existing patterns"
+        ],
+        "logic_flow": [
+          "Load synthesis specification",
+          "Extract requirements and design",
+          "Analyze existing patterns",
+          "Implement following specification",
+          "Consult artifacts for technical details when needed",
+          "Validate against acceptance criteria"
+        ],
+        "depends_on": [],
+        "output": "implementation"
+      }
+    ],
+
+    // CLI Execute Mode: Use Codex command (when --cli-execute flag present)
+    "implementation_approach": [
+      {
+        "step": 1,
+        "title": "Execute implementation with Codex",
+        "description": "Use Codex CLI to implement '[title]' following synthesis specification with autonomous development capabilities",
+        "modification_points": [
+          "Codex loads synthesis specification and artifacts",
+          "Codex implements following requirements",
+          "Codex validates and tests implementation"
+        ],
+        "logic_flow": [
+          "Establish or resume Codex session",
+          "Pass synthesis specification to Codex",
+          "Codex performs autonomous implementation",
+          "Codex validates against acceptance criteria"
+        ],
+        "command": "bash(codex -C [focus_paths] --full-auto exec \"PURPOSE: [title] TASK: [requirements] MODE: auto CONTEXT: @{[synthesis_path],[artifacts_paths]} EXPECTED: [acceptance] RULES: Follow synthesis-specification.md\" [resume_flag] --skip-git-repo-check -s danger-full-access)",
+        "depends_on": [],
+        "output": "implementation"
+      }
+    ],
     "target_files": ["file:function:lines"]
   }
 }
@@ -177,7 +229,37 @@ Generate task JSON files and IMPL_PLAN.md from analysis results with automatic a
 3. Generate task context (requirements, focus_paths, acceptance)
 4. **Determine modification targets**: Extract specific code locations from analysis
 5. Build flow_control with artifact loading steps and target_files
-6. Create individual task JSON files in `.task/`
+6. **CLI Execute Mode**: If `--cli-execute` flag present, generate Codex commands
+7. Create individual task JSON files in `.task/`
+
+#### Codex Resume Mechanism (CLI Execute Mode)
+
+**Session Continuity Strategy**:
+- **First Task** (no depends_on or depends_on=[]): Establish new Codex session
+  - Command: `codex -C [path] --full-auto exec "[prompt]" --skip-git-repo-check -s danger-full-access`
+  - Creates new session context
+
+- **Subsequent Tasks** (has depends_on): Resume previous Codex session
+  - Command: `codex --full-auto exec "[prompt]" resume --last --skip-git-repo-check -s danger-full-access`
+  - Maintains context from previous implementation
+  - **Critical**: `resume --last` flag enables context continuity
+
+**Resume Flag Logic**:
+```javascript
+// Determine resume flag based on task dependencies
+const resumeFlag = task.context.depends_on && task.context.depends_on.length > 0
+  ? "resume --last"
+  : "";
+
+// First task (IMPL-001): no resume flag
+// Later tasks (IMPL-002, IMPL-003): use "resume --last"
+```
+
+**Benefits**:
+- ✅ Shared context across related tasks
+- ✅ Codex learns from previous implementations
+- ✅ Consistent patterns and conventions
+- ✅ Reduced redundant analysis
 
 #### Target Files Generation (Critical)
 **Purpose**: Identify specific code locations for modification AND new files to create
@@ -235,33 +317,229 @@ Generate task JSON files and IMPL_PLAN.md from analysis results with automatic a
 identifier: WFS-{session-id}
 source: "User requirements" | "File: path" | "Issue: ISS-001"
 analysis: .workflow/{session-id}/.process/ANALYSIS_RESULTS.md
+artifacts: .workflow/{session-id}/.brainstorming/
+context_package: .workflow/{session-id}/.process/context-package.json  # CCW smart context
+workflow_type: "standard | tdd | design"  # Indicates execution model
+verification_history:  # CCW quality gates
+  concept_verify: "passed | skipped | pending"
+  action_plan_verify: "pending"
+phase_progression: "brainstorm → context → analysis → concept_verify → planning"  # CCW workflow phases
 ---
 
 # Implementation Plan: {Project Title}
 
-## Summary
-Core requirements, objectives, and technical approach.
+## 1. Summary
+Core requirements, objectives, technical approach summary (2-3 paragraphs max).
 
-## Context Analysis
-- **Project**: Type, patterns, tech stack
-- **Modules**: Components and integration points
-- **Dependencies**: External libraries and constraints
-- **Patterns**: Code conventions and guidelines
+**Core Objectives**:
+- [Key objective 1]
+- [Key objective 2]
 
-## Brainstorming Artifacts
-- synthesis-specification.md (Highest priority)
-- topic-framework.md (Medium priority)
-- Role analyses: ui-designer, system-architect, etc.
+**Technical Approach**:
+- [High-level approach]
 
-## Task Breakdown
-- **Task Count**: N tasks, complexity level
-- **Hierarchy**: Flat/Two-level structure
-- **Dependencies**: Task dependency graph
+## 2. Context Analysis
 
-## Implementation Plan
-- **Execution Strategy**: Sequential/Parallel approach
-- **Resource Requirements**: Tools, dependencies, artifacts
-- **Success Criteria**: Metrics and acceptance conditions
+### CCW Workflow Context
+**Phase Progression**:
+- ✅ Phase 1: Brainstorming (synthesis-specification.md generated)
+- ✅ Phase 2: Context Gathering (context-package.json: {N} files, {M} modules analyzed)
+- ✅ Phase 3: Enhanced Analysis (ANALYSIS_RESULTS.md: Gemini/Qwen/Codex parallel insights)
+- ✅ Phase 4: Concept Verification ({X} clarifications answered, synthesis updated | skipped)
+- ⏳ Phase 5: Action Planning (current phase - generating IMPL_PLAN.md)
+
+**Quality Gates**:
+- concept-verify: ✅ Passed (0 ambiguities remaining) | ⏭️ Skipped (user decision) | ⏳ Pending
+- action-plan-verify: ⏳ Pending (recommended before /workflow:execute)
+
+**Context Package Summary**:
+- **Focus Paths**: {list key directories from context-package.json}
+- **Key Files**: {list primary files for modification}
+- **Module Depth Analysis**: {from get_modules_by_depth.sh output}
+- **Smart Context**: {total file count} files, {module count} modules, {dependency count} dependencies identified
+
+### Project Profile
+- **Type**: Greenfield/Enhancement/Refactor
+- **Scale**: User count, data volume, complexity
+- **Tech Stack**: Primary technologies
+- **Timeline**: Duration and milestones
+
+### Module Structure
+```
+[Directory tree showing key modules]
+```
+
+### Dependencies
+**Primary**: [Core libraries and frameworks]
+**APIs**: [External services]
+**Development**: [Testing, linting, CI/CD tools]
+
+### Patterns & Conventions
+- **Architecture**: [Key patterns like DI, Event-Driven]
+- **Component Design**: [Design patterns]
+- **State Management**: [State strategy]
+- **Code Style**: [Naming, TypeScript coverage]
+
+## 3. Brainstorming Artifacts Reference
+
+### Artifact Usage Strategy
+**Primary Reference (synthesis-specification.md)**:
+- **What**: Comprehensive implementation blueprint from multi-role synthesis
+- **When**: Every task references this first for requirements and design decisions
+- **How**: Extract architecture decisions, UI/UX patterns, functional requirements, non-functional requirements
+- **Priority**: Authoritative - overrides role-specific analyses when conflicts arise
+- **CCW Value**: Consolidates insights from all brainstorming roles into single source of truth
+
+**Context Intelligence (context-package.json)**:
+- **What**: Smart context gathered by CCW's context-gather phase
+- **Content**: Focus paths, dependency graph, existing patterns, module structure
+- **Usage**: Tasks load this via `flow_control.preparatory_steps` for environment setup
+- **CCW Value**: Automated intelligent context discovery replacing manual file exploration
+
+**Technical Analysis (ANALYSIS_RESULTS.md)**:
+- **What**: Gemini/Qwen/Codex parallel analysis results
+- **Content**: Optimization strategies, risk assessment, architecture review, implementation patterns
+- **Usage**: Referenced in task planning for technical guidance and risk mitigation
+- **CCW Value**: Multi-model parallel analysis providing comprehensive technical intelligence
+
+### Integrated Specifications (Highest Priority)
+- **synthesis-specification.md**: Comprehensive implementation blueprint
+  - Contains: Architecture design, UI/UX guidelines, functional/non-functional requirements, implementation roadmap, risk assessment
+
+### Supporting Artifacts (Reference)
+- **topic-framework.md**: Role-specific discussion points and analysis framework
+- **system-architect/analysis.md**: Detailed architecture specifications
+- **ui-designer/analysis.md**: Layout and component specifications
+- **product-manager/analysis.md**: Product vision and user stories
+
+**Artifact Priority in Development**:
+1. synthesis-specification.md (primary reference for all tasks)
+2. context-package.json (smart context for execution environment)
+3. ANALYSIS_RESULTS.md (technical analysis and optimization strategies)
+4. Role-specific analyses (fallback for detailed specifications)
+
+## 4. Implementation Strategy
+
+### Execution Strategy
+**Execution Model**: [Sequential | Parallel | Phased | TDD Cycles]
+
+**Rationale**: [Why this execution model fits the project]
+
+**Parallelization Opportunities**:
+- [List independent workstreams]
+
+**Serialization Requirements**:
+- [List critical dependencies]
+
+### Architectural Approach
+**Key Architecture Decisions**:
+- [ADR references from synthesis]
+- [Justification for architecture patterns]
+
+**Integration Strategy**:
+- [How modules communicate]
+- [State management approach]
+
+### Key Dependencies
+**Task Dependency Graph**:
+```
+[High-level dependency visualization]
+```
+
+**Critical Path**: [Identify bottleneck tasks]
+
+### Testing Strategy
+**Testing Approach**:
+- Unit testing: [Tools, scope]
+- Integration testing: [Key integration points]
+- E2E testing: [Critical user flows]
+
+**Coverage Targets**:
+- Lines: ≥70%
+- Functions: ≥70%
+- Branches: ≥65%
+
+**Quality Gates**:
+- [CI/CD gates]
+- [Performance budgets]
+
+## 5. Task Breakdown Summary
+
+### Task Count
+**{N} tasks** (flat hierarchy | two-level hierarchy, sequential | parallel execution)
+
+### Task Structure
+- **IMPL-1**: [Main task title]
+- **IMPL-2**: [Main task title]
+...
+
+### Complexity Assessment
+- **High**: [List with rationale]
+- **Medium**: [List]
+- **Low**: [List]
+
+### Dependencies
+[Reference Section 4.3 for dependency graph]
+
+**Parallelization Opportunities**:
+- [Specific task groups that can run in parallel]
+
+## 6. Implementation Plan (Detailed Phased Breakdown)
+
+### Execution Strategy
+
+**Phase 1 (Weeks 1-2): [Phase Name]**
+- **Tasks**: IMPL-1, IMPL-2
+- **Deliverables**:
+  - [Specific deliverable 1]
+  - [Specific deliverable 2]
+- **Success Criteria**:
+  - [Measurable criterion]
+
+**Phase 2 (Weeks 3-N): [Phase Name]**
+...
+
+### Resource Requirements
+
+**Development Team**:
+- [Team composition and skills]
+
+**External Dependencies**:
+- [Third-party services, APIs]
+
+**Infrastructure**:
+- [Development, staging, production environments]
+
+## 7. Risk Assessment & Mitigation
+
+| Risk | Impact | Probability | Mitigation Strategy | Owner |
+|------|--------|-------------|---------------------|-------|
+| [Risk description] | High/Med/Low | High/Med/Low | [Strategy] | [Role] |
+
+**Critical Risks** (High impact + High probability):
+- [Risk 1]: [Detailed mitigation plan]
+
+**Monitoring Strategy**:
+- [How risks will be monitored]
+
+## 8. Success Criteria
+
+**Functional Completeness**:
+- [ ] All requirements from synthesis-specification.md implemented
+- [ ] All acceptance criteria from task.json files met
+
+**Technical Quality**:
+- [ ] Test coverage ≥70%
+- [ ] Bundle size within budget
+- [ ] Performance targets met
+
+**Operational Readiness**:
+- [ ] CI/CD pipeline operational
+- [ ] Monitoring and logging configured
+- [ ] Documentation complete
+
+**Business Metrics**:
+- [ ] [Key business metrics from synthesis]
 ```
 
 ### Phase 5: TODO_LIST.md Generation
@@ -342,8 +620,82 @@ Core requirements, objectives, and technical approach.
 /workflow:tools:task-generate --session WFS-auth
 ```
 
+## CLI Execute Mode Examples
+
+### Example 1: First Task (Establish Session)
+```json
+{
+  "id": "IMPL-001",
+  "title": "Implement user authentication module",
+  "context": {
+    "depends_on": [],
+    "focus_paths": ["src/auth"],
+    "requirements": ["JWT-based authentication", "Login and registration endpoints"]
+  },
+  "flow_control": {
+    "implementation_approach": [{
+      "step": 1,
+      "title": "Execute implementation with Codex",
+      "command": "bash(codex -C src/auth --full-auto exec \"PURPOSE: Implement user authentication module TASK: JWT-based authentication with login and registration MODE: auto CONTEXT: @{.workflow/WFS-session/.brainstorming/synthesis-specification.md} EXPECTED: Complete auth module with tests RULES: Follow synthesis specification\" --skip-git-repo-check -s danger-full-access)",
+      "depends_on": [],
+      "output": "implementation"
+    }]
+  }
+}
+```
+
+### Example 2: Subsequent Task (Resume Session)
+```json
+{
+  "id": "IMPL-002",
+  "title": "Add password reset functionality",
+  "context": {
+    "depends_on": ["IMPL-001"],
+    "focus_paths": ["src/auth"],
+    "requirements": ["Password reset via email", "Token validation"]
+  },
+  "flow_control": {
+    "implementation_approach": [{
+      "step": 1,
+      "title": "Execute implementation with Codex",
+      "command": "bash(codex --full-auto exec \"PURPOSE: Add password reset functionality TASK: Password reset via email with token validation MODE: auto CONTEXT: Previous auth implementation from session EXPECTED: Password reset endpoints with email integration RULES: Maintain consistency with existing auth patterns\" resume --last --skip-git-repo-check -s danger-full-access)",
+      "depends_on": [],
+      "output": "implementation"
+    }]
+  }
+}
+```
+
+### Example 3: Third Task (Continue Session)
+```json
+{
+  "id": "IMPL-003",
+  "title": "Implement role-based access control",
+  "context": {
+    "depends_on": ["IMPL-001", "IMPL-002"],
+    "focus_paths": ["src/auth"],
+    "requirements": ["User roles and permissions", "Middleware for route protection"]
+  },
+  "flow_control": {
+    "implementation_approach": [{
+      "step": 1,
+      "title": "Execute implementation with Codex",
+      "command": "bash(codex --full-auto exec \"PURPOSE: Implement role-based access control TASK: User roles, permissions, and route protection middleware MODE: auto CONTEXT: Existing auth system from session EXPECTED: RBAC system integrated with current auth RULES: Use established patterns from session context\" resume --last --skip-git-repo-check -s danger-full-access)",
+      "depends_on": [],
+      "output": "implementation"
+    }]
+  }
+}
+```
+
+**Pattern Summary**:
+- IMPL-001: Fresh start with `-C src/auth` and full prompt
+- IMPL-002: Resume with `resume --last`, references "previous auth implementation"
+- IMPL-003: Resume with `resume --last`, references "existing auth system"
+
 ## Related Commands
 - `/workflow:plan` - Orchestrates entire planning
+- `/workflow:plan --cli-execute` - Planning with CLI execution mode
 - `/workflow:tools:context-gather` - Provides context package
 - `/workflow:tools:concept-enhanced` - Provides analysis results
 - `/workflow:execute` - Executes generated tasks

.claude/commands/workflow/tools/tdd-coverage-analysis.md

@@ -1,10 +1,7 @@
 ---
 name: tdd-coverage-analysis
 description: Analyze test coverage and TDD cycle execution
-usage: /workflow:tools:tdd-coverage-analysis --session <session_id>
 argument-hint: "--session WFS-session-id"
-examples:
-  - /workflow:tools:tdd-coverage-analysis --session WFS-auth
 allowed-tools: Read(*), Write(*), Bash(*)
 ---
 

.claude/commands/workflow/tools/test-concept-enhanced.md

@@ -0,0 +1,467 @@
+---
+name: test-concept-enhanced
+description: Analyze test requirements and generate test generation strategy using Gemini
+argument-hint: "--session WFS-test-session-id --context path/to/test-context-package.json"
+examples:
+  - /workflow:tools:test-concept-enhanced --session WFS-test-auth --context .workflow/WFS-test-auth/.process/test-context-package.json
+---
+
+# Test Concept Enhanced Command
+
+## Overview
+Specialized analysis tool for test generation workflows that uses Gemini to analyze test coverage gaps, implementation context, and generate comprehensive test generation strategies.
+
+## Core Philosophy
+- **Coverage-Driven**: Focus on identified test gaps from context analysis
+- **Pattern-Based**: Learn from existing tests and project conventions
+- **Gemini-Powered**: Use Gemini for test requirement analysis and strategy design
+- **Single-Round Analysis**: Comprehensive test analysis in one execution
+- **No Code Generation**: Strategy and planning only, actual test generation happens in task execution
+
+## Core Responsibilities
+- Parse test-context-package.json from test-context-gather
+- Analyze implementation summaries and coverage gaps
+- Study existing test patterns and conventions
+- Generate test generation strategy using Gemini
+- Produce TEST_ANALYSIS_RESULTS.md for task generation
+
+## Execution Lifecycle
+
+### Phase 1: Validation & Preparation
+
+1. **Session Validation**
+   - Load `.workflow/{test_session_id}/workflow-session.json`
+   - Verify test session type is "test-gen"
+   - Extract source session reference
+
+2. **Context Package Validation**
+   - Read `test-context-package.json`
+   - Validate required sections: metadata, source_context, test_coverage, test_framework
+   - Extract coverage gaps and framework details
+
+3. **Strategy Determination**
+   - **Simple Test Generation** (1-3 files): Single Gemini analysis
+   - **Medium Test Generation** (4-6 files): Gemini comprehensive analysis
+   - **Complex Test Generation** (>6 files): Gemini analysis with modular approach
+
+### Phase 2: Gemini Test Analysis
+
+**Tool Configuration**:
+```bash
+cd .workflow/{test_session_id}/.process && ~/.claude/scripts/gemini-wrapper -p "
+PURPOSE: Analyze test coverage gaps and design comprehensive test generation strategy
+TASK: Study implementation context, existing tests, and generate test requirements for missing coverage
+MODE: analysis
+CONTEXT: @{.workflow/{test_session_id}/.process/test-context-package.json}
+
+**MANDATORY FIRST STEP**: Read and analyze test-context-package.json to understand:
+- Test coverage gaps from test_coverage.missing_tests[]
+- Implementation context from source_context.implementation_summaries[]
+- Existing test patterns from test_framework.conventions
+- Changed files requiring tests from source_context.implementation_summaries[].changed_files
+
+**ANALYSIS REQUIREMENTS**:
+
+1. **Implementation Understanding**
+   - Load all implementation summaries from source session
+   - Understand implemented features, APIs, and business logic
+   - Extract key functions, classes, and modules
+   - Identify integration points and dependencies
+
+2. **Existing Test Pattern Analysis**
+   - Study existing test files for patterns and conventions
+   - Identify test structure (describe/it, test suites, fixtures)
+   - Analyze assertion patterns and mocking strategies
+   - Extract test setup/teardown patterns
+
+3. **Coverage Gap Assessment**
+   - For each file in missing_tests[], analyze:
+     - File purpose and functionality
+     - Public APIs requiring test coverage
+     - Critical paths and edge cases
+     - Integration points requiring tests
+   - Prioritize tests: high (core logic), medium (utilities), low (helpers)
+
+4. **Test Requirements Specification**
+   - For each missing test file, specify:
+     - **Test scope**: What needs to be tested
+     - **Test scenarios**: Happy path, error cases, edge cases, integration
+     - **Test data**: Required fixtures, mocks, test data
+     - **Dependencies**: External services, databases, APIs to mock
+     - **Coverage targets**: Functions/methods requiring tests
+
+5. **Test Generation Strategy**
+   - Determine test generation approach for each file
+   - Identify reusable test patterns from existing tests
+   - Plan test data and fixture requirements
+   - Define mocking strategy for dependencies
+   - Specify expected test file structure
+
+EXPECTED OUTPUT - Write to gemini-test-analysis.md:
+
+# Test Generation Analysis
+
+## 1. Implementation Context Summary
+- **Source Session**: {source_session_id}
+- **Implemented Features**: {feature_summary}
+- **Changed Files**: {list_of_implementation_files}
+- **Tech Stack**: {technologies_used}
+
+## 2. Test Coverage Assessment
+- **Existing Tests**: {count} files
+- **Missing Tests**: {count} files
+- **Coverage Percentage**: {percentage}%
+- **Priority Breakdown**:
+  - High Priority: {count} files (core business logic)
+  - Medium Priority: {count} files (utilities, helpers)
+  - Low Priority: {count} files (configuration, constants)
+
+## 3. Existing Test Pattern Analysis
+- **Test Framework**: {framework_name_and_version}
+- **File Naming Convention**: {pattern}
+- **Test Structure**: {describe_it_or_other}
+- **Assertion Style**: {expect_assert_should}
+- **Mocking Strategy**: {mocking_framework_and_patterns}
+- **Setup/Teardown**: {beforeEach_afterEach_patterns}
+- **Test Data**: {fixtures_factories_builders}
+
+## 4. Test Requirements by File
+
+### File: {implementation_file_path}
+**Test File**: {suggested_test_file_path}
+**Priority**: {high|medium|low}
+
+#### Scope
+- {description_of_what_needs_testing}
+
+#### Test Scenarios
+1. **Happy Path Tests**
+   - {scenario_1}
+   - {scenario_2}
+
+2. **Error Handling Tests**
+   - {error_scenario_1}
+   - {error_scenario_2}
+
+3. **Edge Case Tests**
+   - {edge_case_1}
+   - {edge_case_2}
+
+4. **Integration Tests** (if applicable)
+   - {integration_scenario_1}
+   - {integration_scenario_2}
+
+#### Test Data & Fixtures
+- {required_test_data}
+- {required_mocks}
+- {required_fixtures}
+
+#### Dependencies to Mock
+- {external_service_1}
+- {external_service_2}
+
+#### Coverage Targets
+- Function: {function_name} - {test_requirements}
+- Function: {function_name} - {test_requirements}
+
+---
+[Repeat for each missing test file]
+---
+
+## 5. Test Generation Strategy
+
+### Overall Approach
+- {strategy_description}
+
+### Test Generation Order
+1. {file_1} - {rationale}
+2. {file_2} - {rationale}
+3. {file_3} - {rationale}
+
+### Reusable Patterns
+- {pattern_1_from_existing_tests}
+- {pattern_2_from_existing_tests}
+
+### Test Data Strategy
+- {approach_to_test_data_and_fixtures}
+
+### Mocking Strategy
+- {approach_to_mocking_dependencies}
+
+### Quality Criteria
+- Code coverage target: {percentage}%
+- Test scenarios per function: {count}
+- Integration test coverage: {approach}
+
+## 6. Implementation Targets
+
+**Purpose**: Identify new test files to create
+
+**Format**: New test files only (no existing files to modify)
+
+**Test Files to Create**:
+1. **Target**: `tests/auth/TokenValidator.test.ts`
+   - **Type**: Create new test file
+   - **Purpose**: Test TokenValidator class
+   - **Scenarios**: 15 test cases covering validation logic, error handling, edge cases
+   - **Dependencies**: Mock JWT library, test fixtures for tokens
+
+2. **Target**: `tests/middleware/errorHandler.test.ts`
+   - **Type**: Create new test file
+   - **Purpose**: Test error handling middleware
+   - **Scenarios**: 8 test cases for different error types and response formats
+   - **Dependencies**: Mock Express req/res/next, error fixtures
+
+[List all test files to create]
+
+## 7. Success Metrics
+- **Test Coverage Goal**: {target_percentage}%
+- **Test Quality**: All scenarios covered (happy, error, edge, integration)
+- **Convention Compliance**: Follow existing test patterns
+- **Maintainability**: Clear test descriptions, reusable fixtures
+
+RULES:
+- Focus on TEST REQUIREMENTS and GENERATION STRATEGY, NOT code generation
+- Study existing test patterns thoroughly for consistency
+- Prioritize critical business logic tests
+- Specify clear test scenarios and coverage targets
+- Identify all dependencies requiring mocks
+- **MUST write output to .workflow/{test_session_id}/.process/gemini-test-analysis.md**
+- Do NOT generate actual test code or implementation
+- Output ONLY test analysis and generation strategy
+" --approval-mode yolo
+```
+
+**Output Location**: `.workflow/{test_session_id}/.process/gemini-test-analysis.md`
+
+### Phase 3: Results Synthesis
+
+1. **Output Validation**
+   - Verify `gemini-test-analysis.md` exists and is complete
+   - Validate all required sections present
+   - Check test requirements are actionable
+
+2. **Quality Assessment**
+   - Test scenarios cover happy path, errors, edge cases
+   - Dependencies and mocks clearly identified
+   - Test generation strategy is practical
+   - Coverage targets are reasonable
+
+### Phase 4: TEST_ANALYSIS_RESULTS.md Generation
+
+Synthesize Gemini analysis into standardized format:
+
+```markdown
+# Test Generation Analysis Results
+
+## Executive Summary
+- **Test Session**: {test_session_id}
+- **Source Session**: {source_session_id}
+- **Analysis Timestamp**: {timestamp}
+- **Coverage Gap**: {missing_test_count} files require tests
+- **Test Framework**: {framework}
+- **Overall Strategy**: {high_level_approach}
+
+---
+
+## 1. Coverage Assessment
+
+### Current Coverage
+- **Existing Tests**: {count} files
+- **Implementation Files**: {count} files
+- **Coverage Percentage**: {percentage}%
+
+### Missing Tests (Priority Order)
+1. **High Priority** ({count} files)
+   - {file_1} - {reason}
+   - {file_2} - {reason}
+
+2. **Medium Priority** ({count} files)
+   - {file_1} - {reason}
+
+3. **Low Priority** ({count} files)
+   - {file_1} - {reason}
+
+---
+
+## 2. Test Framework & Conventions
+
+### Framework Configuration
+- **Framework**: {framework_name}
+- **Version**: {version}
+- **Test Pattern**: {file_pattern}
+- **Test Directory**: {directory_structure}
+
+### Conventions
+- **File Naming**: {convention}
+- **Test Structure**: {describe_it_blocks}
+- **Assertions**: {assertion_library}
+- **Mocking**: {mocking_framework}
+- **Setup/Teardown**: {beforeEach_afterEach}
+
+### Example Pattern (from existing tests)
+```
+{example_test_structure_from_analysis}
+```
+
+---
+
+## 3. Test Requirements by File
+
+[For each missing test, include:]
+
+### Test File: {test_file_path}
+**Implementation**: {implementation_file}
+**Priority**: {high|medium|low}
+**Estimated Test Count**: {count}
+
+#### Test Scenarios
+1. **Happy Path**: {scenarios}
+2. **Error Handling**: {scenarios}
+3. **Edge Cases**: {scenarios}
+4. **Integration**: {scenarios}
+
+#### Dependencies & Mocks
+- {dependency_1_to_mock}
+- {dependency_2_to_mock}
+
+#### Test Data Requirements
+- {fixture_1}
+- {fixture_2}
+
+---
+
+## 4. Test Generation Strategy
+
+### Generation Approach
+{overall_strategy_description}
+
+### Generation Order
+1. {test_file_1} - {rationale}
+2. {test_file_2} - {rationale}
+3. {test_file_3} - {rationale}
+
+### Reusable Components
+- **Test Fixtures**: {common_fixtures}
+- **Mock Patterns**: {common_mocks}
+- **Helper Functions**: {test_helpers}
+
+### Quality Targets
+- **Coverage Goal**: {percentage}%
+- **Scenarios per Function**: {min_count}
+- **Integration Coverage**: {approach}
+
+---
+
+## 5. Implementation Targets
+
+**Purpose**: New test files to create (code-developer will generate these)
+
+**Test Files to Create**:
+
+1. **Target**: `tests/auth/TokenValidator.test.ts`
+   - **Implementation Source**: `src/auth/TokenValidator.ts`
+   - **Test Scenarios**: 15 (validation, error handling, edge cases)
+   - **Dependencies**: Mock JWT library, token fixtures
+   - **Priority**: High
+
+2. **Target**: `tests/middleware/errorHandler.test.ts`
+   - **Implementation Source**: `src/middleware/errorHandler.ts`
+   - **Test Scenarios**: 8 (error types, response formats)
+   - **Dependencies**: Mock Express, error fixtures
+   - **Priority**: High
+
+[List all test files with full specifications]
+
+---
+
+## 6. Success Criteria
+
+### Coverage Metrics
+- Achieve {target_percentage}% code coverage
+- All public APIs have tests
+- Critical paths fully covered
+
+### Quality Standards
+- All test scenarios covered (happy, error, edge, integration)
+- Follow existing test conventions
+- Clear test descriptions and assertions
+- Maintainable test structure
+
+### Validation Approach
+- Run full test suite after generation
+- Verify coverage with coverage tool
+- Manual review of test quality
+- Integration test validation
+
+---
+
+## 7. Reference Information
+
+### Source Context
+- **Implementation Summaries**: {paths}
+- **Existing Tests**: {example_tests}
+- **Documentation**: {relevant_docs}
+
+### Analysis Tools
+- **Gemini Analysis**: gemini-test-analysis.md
+- **Coverage Tools**: {coverage_tool_if_detected}
+```
+
+**Output Location**: `.workflow/{test_session_id}/.process/TEST_ANALYSIS_RESULTS.md`
+
+## Error Handling
+
+### Validation Errors
+| Error | Cause | Resolution |
+|-------|-------|------------|
+| Missing context package | test-context-gather not run | Run test-context-gather first |
+| No coverage gaps | All files have tests | Skip test generation, proceed to test execution |
+| No test framework detected | Missing test dependencies | Request user to configure test framework |
+| Invalid source session | Source session incomplete | Complete implementation first |
+
+### Gemini Execution Errors
+| Error | Cause | Recovery |
+|-------|-------|----------|
+| Timeout | Large project analysis | Reduce scope, analyze by module |
+| Output incomplete | Token limit exceeded | Retry with focused analysis |
+| No output file | Write permission error | Check directory permissions |
+
+### Fallback Strategy
+- If Gemini fails, generate basic TEST_ANALYSIS_RESULTS.md from context package
+- Use coverage gaps and framework info to create minimal requirements
+- Provide guidance for manual test planning
+
+## Performance Optimization
+
+- **Focused Analysis**: Only analyze files with missing tests
+- **Pattern Reuse**: Study existing tests for quick pattern extraction
+- **Parallel Operations**: Load implementation summaries in parallel
+- **Timeout Management**: 20-minute limit for Gemini analysis
+
+## Integration
+
+### Called By
+- `/workflow:test-gen` (Phase 4: Analysis)
+
+### Requires
+- `/workflow:tools:test-context-gather` output (test-context-package.json)
+
+### Followed By
+- `/workflow:tools:test-task-generate` - Generates test task JSON with code-developer invocation
+
+## Success Criteria
+
+- ✅ Valid TEST_ANALYSIS_RESULTS.md generated
+- ✅ All missing tests documented with requirements
+- ✅ Test scenarios cover happy path, errors, edge cases
+- ✅ Dependencies and mocks identified
+- ✅ Test generation strategy is actionable
+- ✅ Execution time < 20 minutes
+- ✅ Output follows existing test conventions
+
+## Related Commands
+
+- `/workflow:tools:test-context-gather` - Provides input context
+- `/workflow:tools:test-task-generate` - Consumes analysis results
+- `/workflow:test-gen` - Main test generation workflow

.claude/commands/workflow/tools/test-context-gather.md

@@ -0,0 +1,309 @@
+---
+name: test-context-gather
+description: Collect test coverage context and identify files requiring test generation
+argument-hint: "--session WFS-test-session-id"
+examples:
+  - /workflow:tools:test-context-gather --session WFS-test-auth
+  - /workflow:tools:test-context-gather --session WFS-test-payment
+---
+
+# Test Context Gather Command
+
+## Overview
+Specialized context collector for test generation workflows that analyzes test coverage, identifies missing tests, and packages implementation context from source sessions.
+
+## Core Philosophy
+- **Coverage-First**: Analyze existing test coverage before planning
+- **Gap Identification**: Locate implementation files without corresponding tests
+- **Source Context Loading**: Import implementation summaries from source session
+- **Framework Detection**: Auto-detect test framework and patterns
+- **MCP-Powered**: Leverage code-index tools for precise analysis
+
+## Core Responsibilities
+- Load source session implementation context
+- Analyze current test coverage using MCP tools
+- Identify files requiring test generation
+- Detect test framework and conventions
+- Package test context for analysis phase
+
+## Execution Lifecycle
+
+### Phase 1: Session Validation & Source Loading
+
+1. **Test Session Validation**
+   - Load `.workflow/{test_session_id}/workflow-session.json`
+   - Extract `meta.source_session` reference
+   - Validate test session type is "test-gen"
+
+2. **Source Session Context Loading**
+   - Read `.workflow/{source_session_id}/workflow-session.json`
+   - Load implementation summaries from `.workflow/{source_session_id}/.summaries/`
+   - Extract changed files and implementation scope
+   - Identify implementation patterns and tech stack
+
+### Phase 2: Test Coverage Analysis (MCP Tools)
+
+1. **Existing Test Discovery**
+   ```bash
+   # Find all test files
+   mcp__code-index__find_files(pattern="*.test.*")
+   mcp__code-index__find_files(pattern="*.spec.*")
+   mcp__code-index__find_files(pattern="*test_*.py")
+
+   # Search for test patterns
+   mcp__code-index__search_code_advanced(
+     pattern="describe|it|test|@Test",
+     file_pattern="*.test.*",
+     context_lines=0
+   )
+   ```
+
+2. **Coverage Gap Analysis**
+   ```bash
+   # For each implementation file from source session
+   # Check if corresponding test file exists
+
+   # Example: src/auth/AuthService.ts -> tests/auth/AuthService.test.ts
+   #          src/utils/validator.py -> tests/test_validator.py
+
+   # Output: List of files without tests
+   ```
+
+3. **Test Statistics**
+   - Count total test files
+   - Count implementation files from source session
+   - Calculate coverage percentage
+   - Identify coverage gaps by module
+
+### Phase 3: Test Framework Detection
+
+1. **Framework Identification**
+   ```bash
+   # Check package.json or requirements.txt
+   mcp__code-index__search_code_advanced(
+     pattern="jest|mocha|jasmine|pytest|unittest|rspec",
+     file_pattern="package.json|requirements.txt|Gemfile",
+     context_lines=2
+   )
+
+   # Analyze existing test patterns
+   mcp__code-index__search_code_advanced(
+     pattern="describe\\(|it\\(|test\\(|def test_",
+     file_pattern="*.test.*",
+     context_lines=3
+   )
+   ```
+
+2. **Convention Analysis**
+   - Test file naming patterns (*.test.ts vs *.spec.ts)
+   - Test directory structure (tests/ vs __tests__ vs src/**/*.test.*)
+   - Assertion library (expect, assert, should)
+   - Mocking framework (jest.fn, sinon, unittest.mock)
+
+### Phase 4: Context Packaging
+
+Generate `test-context-package.json`:
+
+```json
+{
+  "metadata": {
+    "test_session_id": "WFS-test-auth",
+    "source_session_id": "WFS-auth",
+    "timestamp": "2025-10-04T10:30:00Z",
+    "task_type": "test-generation",
+    "complexity": "medium"
+  },
+  "source_context": {
+    "implementation_summaries": [
+      {
+        "task_id": "IMPL-001",
+        "summary_path": ".workflow/WFS-auth/.summaries/IMPL-001-summary.md",
+        "changed_files": [
+          "src/auth/AuthService.ts",
+          "src/auth/TokenValidator.ts",
+          "src/middleware/auth.ts"
+        ],
+        "implementation_type": "feature"
+      }
+    ],
+    "tech_stack": ["typescript", "express", "jsonwebtoken"],
+    "project_patterns": {
+      "architecture": "layered",
+      "error_handling": "try-catch with custom errors",
+      "async_pattern": "async/await"
+    }
+  },
+  "test_coverage": {
+    "existing_tests": [
+      "tests/auth/AuthService.test.ts",
+      "tests/middleware/auth.test.ts"
+    ],
+    "missing_tests": [
+      {
+        "implementation_file": "src/auth/TokenValidator.ts",
+        "suggested_test_file": "tests/auth/TokenValidator.test.ts",
+        "priority": "high",
+        "reason": "New implementation without tests"
+      }
+    ],
+    "coverage_stats": {
+      "total_implementation_files": 3,
+      "files_with_tests": 2,
+      "files_without_tests": 1,
+      "coverage_percentage": 66.7
+    }
+  },
+  "test_framework": {
+    "framework": "jest",
+    "version": "^29.0.0",
+    "test_pattern": "**/*.test.ts",
+    "test_directory": "tests/",
+    "assertion_library": "expect",
+    "mocking_framework": "jest",
+    "conventions": {
+      "file_naming": "*.test.ts",
+      "test_structure": "describe/it blocks",
+      "setup_teardown": "beforeEach/afterEach"
+    }
+  },
+  "assets": [
+    {
+      "type": "implementation_summary",
+      "path": ".workflow/WFS-auth/.summaries/IMPL-001-summary.md",
+      "relevance": "Source implementation context",
+      "priority": "highest"
+    },
+    {
+      "type": "existing_test",
+      "path": "tests/auth/AuthService.test.ts",
+      "relevance": "Test pattern reference",
+      "priority": "high"
+    },
+    {
+      "type": "source_code",
+      "path": "src/auth/TokenValidator.ts",
+      "relevance": "Implementation requiring tests",
+      "priority": "high"
+    },
+    {
+      "type": "documentation",
+      "path": "CLAUDE.md",
+      "relevance": "Project conventions",
+      "priority": "medium"
+    }
+  ],
+  "focus_areas": [
+    "Generate comprehensive tests for TokenValidator",
+    "Follow existing Jest patterns from AuthService tests",
+    "Cover happy path, error cases, and edge cases",
+    "Include integration tests for middleware"
+  ]
+}
+```
+
+## Output Location
+
+```
+.workflow/{test_session_id}/.process/test-context-package.json
+```
+
+## MCP Tools Usage
+
+### File Discovery
+```bash
+# Test files
+mcp__code-index__find_files(pattern="*.test.*")
+mcp__code-index__find_files(pattern="*.spec.*")
+
+# Implementation files
+mcp__code-index__find_files(pattern="*.ts")
+mcp__code-index__find_files(pattern="*.js")
+```
+
+### Content Search
+```bash
+# Test framework detection
+mcp__code-index__search_code_advanced(
+  pattern="jest|mocha|pytest",
+  file_pattern="package.json|requirements.txt"
+)
+
+# Test pattern analysis
+mcp__code-index__search_code_advanced(
+  pattern="describe|it|test",
+  file_pattern="*.test.*",
+  context_lines=2
+)
+```
+
+### Coverage Analysis
+```bash
+# For each implementation file
+# Check if test exists
+implementation_file="src/auth/AuthService.ts"
+test_file_patterns=(
+  "tests/auth/AuthService.test.ts"
+  "src/auth/AuthService.test.ts"
+  "src/auth/__tests__/AuthService.test.ts"
+)
+
+# Search for test file
+for pattern in "${test_file_patterns[@]}"; do
+  if mcp__code-index__find_files(pattern="$pattern") | grep -q .; then
+    echo "✅ Test exists: $pattern"
+    break
+  fi
+done
+```
+
+## Error Handling
+
+| Error | Cause | Resolution |
+|-------|-------|------------|
+| Source session not found | Invalid source_session reference | Verify test session metadata |
+| No implementation summaries | Source session incomplete | Complete source session first |
+| MCP tools unavailable | MCP not configured | Fallback to bash find/grep |
+| No test framework detected | Missing test dependencies | Request user to specify framework |
+
+## Fallback Strategy (No MCP)
+
+```bash
+# File discovery
+find . -name "*.test.*" -o -name "*.spec.*" | grep -v node_modules
+
+# Framework detection
+grep -r "jest\|mocha\|pytest" package.json requirements.txt 2>/dev/null
+
+# Coverage analysis
+for impl_file in $(cat changed_files.txt); do
+  test_file=$(echo $impl_file | sed 's/src/tests/' | sed 's/\(.*\)\.\(ts\|js\|py\)$/\1.test.\2/')
+  [ ! -f "$test_file" ] && echo "$impl_file → MISSING TEST"
+done
+```
+
+## Integration
+
+### Called By
+- `/workflow:test-gen` (Phase 3: Context Gathering)
+
+### Calls
+- MCP code-index tools for analysis
+- Bash file operations for fallback
+
+### Followed By
+- `/workflow:tools:test-concept-enhanced` - Analyzes context and plans test generation
+
+## Success Criteria
+
+- ✅ Source session context loaded successfully
+- ✅ Test coverage gaps identified with MCP tools
+- ✅ Test framework detected and documented
+- ✅ Valid test-context-package.json generated
+- ✅ All missing tests catalogued with priority
+- ✅ Execution time < 20 seconds
+
+## Related Commands
+
+- `/workflow:test-gen` - Main test generation workflow
+- `/workflow:tools:test-concept-enhanced` - Test generation analysis
+- `/workflow:tools:test-task-generate` - Test task JSON generation

.claude/commands/workflow/tools/test-task-generate.md

@@ -0,0 +1,695 @@
+---
+name: test-task-generate
+description: Generate test-fix task JSON with iterative test-fix-retest cycle specification
+argument-hint: "[--use-codex] [--cli-execute] --session WFS-test-session-id"
+examples:
+  - /workflow:tools:test-task-generate --session WFS-test-auth
+  - /workflow:tools:test-task-generate --use-codex --session WFS-test-auth
+  - /workflow:tools:test-task-generate --cli-execute --session WFS-test-auth
+  - /workflow:tools:test-task-generate --cli-execute --use-codex --session WFS-test-auth
+---
+
+# Test Task Generation Command
+
+## Overview
+Generate specialized test-fix task JSON with comprehensive test-fix-retest cycle specification, including Gemini diagnosis (using bug-fix template) and manual fix workflow (Codex automation only when explicitly requested).
+
+## Execution Modes
+
+### Test Generation (IMPL-001)
+- **Agent Mode (Default)**: @code-developer generates tests within agent context
+- **CLI Execute Mode (`--cli-execute`)**: Use Codex CLI for autonomous test generation
+
+### Test Fix (IMPL-002)
+- **Manual Mode (Default)**: Gemini diagnosis → user applies fixes
+- **Codex Mode (`--use-codex`)**: Gemini diagnosis → Codex applies fixes with resume mechanism
+
+## Core Philosophy
+- **Analysis-Driven Test Generation**: Use TEST_ANALYSIS_RESULTS.md from test-concept-enhanced
+- **Agent-Based Test Creation**: Call @code-developer agent for comprehensive test generation
+- **Coverage-First**: Generate all missing tests before execution
+- **Test Execution**: Execute complete test suite after generation
+- **Gemini Diagnosis**: Use Gemini for root cause analysis and fix suggestions (references bug-fix template)
+- **Manual Fixes First**: Apply fixes manually by default, codex only when explicitly needed
+- **Iterative Refinement**: Repeat test-analyze-fix-retest cycle until all tests pass
+- **Surgical Fixes**: Minimal code changes, no refactoring during test fixes
+- **Auto-Revert**: Rollback all changes if max iterations reached
+
+## Core Responsibilities
+- Parse TEST_ANALYSIS_RESULTS.md from test-concept-enhanced
+- Extract test requirements and generation strategy
+- Parse `--use-codex` flag to determine fix mode (manual vs automated)
+- Generate test generation subtask calling @code-developer
+- Generate test execution and fix cycle task JSON with appropriate fix mode
+- Configure Gemini diagnosis workflow (bug-fix template) and manual/Codex fix application
+- Create test-oriented IMPL_PLAN.md and TODO_LIST.md with test generation phase
+
+## Execution Lifecycle
+
+### Phase 1: Input Validation & Discovery
+
+1. **Parameter Parsing**
+   - Parse `--use-codex` flag from command arguments → Controls IMPL-002 fix mode
+   - Parse `--cli-execute` flag from command arguments → Controls IMPL-001 generation mode
+   - Store flag values for task JSON generation
+
+2. **Test Session Validation**
+   - Load `.workflow/{test-session-id}/workflow-session.json`
+   - Verify `workflow_type: "test_session"`
+   - Extract `source_session_id` from metadata
+
+3. **Test Analysis Results Loading**
+   - **REQUIRED**: Load `.workflow/{test-session-id}/.process/TEST_ANALYSIS_RESULTS.md`
+   - Parse test requirements by file
+   - Extract test generation strategy
+   - Identify test files to create with specifications
+
+4. **Test Context Package Loading**
+   - Load `.workflow/{test-session-id}/.process/test-context-package.json`
+   - Extract test framework configuration
+   - Extract coverage gaps and priorities
+   - Load source session implementation summaries
+
+### Phase 2: Task JSON Generation
+
+Generate **TWO task JSON files**:
+1. **IMPL-001.json** - Test Generation (calls @code-developer)
+2. **IMPL-002.json** - Test Execution and Fix Cycle (calls @test-fix-agent)
+
+#### IMPL-001.json - Test Generation Task
+
+```json
+{
+  "id": "IMPL-001",
+  "title": "Generate comprehensive tests for [sourceSessionId]",
+  "status": "pending",
+  "meta": {
+    "type": "test-gen",
+    "agent": "@code-developer",
+    "source_session": "[sourceSessionId]",
+    "test_framework": "jest|pytest|cargo|detected"
+  },
+  "context": {
+    "requirements": [
+      "Generate comprehensive test files based on TEST_ANALYSIS_RESULTS.md",
+      "Follow existing test patterns and conventions from test framework",
+      "Create tests for all missing coverage identified in analysis",
+      "Include happy path, error handling, edge cases, and integration tests",
+      "Use test data and mocks as specified in analysis",
+      "Ensure tests follow project coding standards"
+    ],
+    "focus_paths": [
+      "tests/**/*",
+      "src/**/*.test.*",
+      "{paths_from_analysis}"
+    ],
+    "acceptance": [
+      "All test files from TEST_ANALYSIS_RESULTS.md section 5 are created",
+      "Tests follow existing test patterns and conventions",
+      "Test scenarios cover happy path, errors, edge cases, integration",
+      "All dependencies are properly mocked",
+      "Test files are syntactically valid and can be executed",
+      "Test coverage meets analysis requirements"
+    ],
+    "depends_on": [],
+    "source_context": {
+      "session_id": "[sourceSessionId]",
+      "test_analysis": ".workflow/[testSessionId]/.process/TEST_ANALYSIS_RESULTS.md",
+      "test_context": ".workflow/[testSessionId]/.process/test-context-package.json",
+      "implementation_summaries": [
+        ".workflow/[sourceSessionId]/.summaries/IMPL-001-summary.md"
+      ]
+    }
+  },
+  "flow_control": {
+    "pre_analysis": [
+      {
+        "step": "load_test_analysis",
+        "action": "Load test generation requirements and strategy",
+        "commands": [
+          "Read(.workflow/[testSessionId]/.process/TEST_ANALYSIS_RESULTS.md)",
+          "Read(.workflow/[testSessionId]/.process/test-context-package.json)"
+        ],
+        "output_to": "test_generation_requirements",
+        "on_error": "fail"
+      },
+      {
+        "step": "load_implementation_context",
+        "action": "Load source implementation for test generation context",
+        "commands": [
+          "bash(for f in .workflow/[sourceSessionId]/.summaries/IMPL-*-summary.md; do echo \"=== $(basename $f) ===\"&& cat \"$f\"; done)"
+        ],
+        "output_to": "implementation_context",
+        "on_error": "skip_optional"
+      },
+      {
+        "step": "load_existing_test_patterns",
+        "action": "Study existing tests for pattern reference",
+        "commands": [
+          "mcp__code-index__find_files(pattern=\"*.test.*\")",
+          "bash(# Read first 2 existing test files as examples)",
+          "bash(test_files=$(mcp__code-index__find_files(pattern=\"*.test.*\") | head -2))",
+          "bash(for f in $test_files; do echo \"=== $f ===\"&& cat \"$f\"; done)"
+        ],
+        "output_to": "existing_test_patterns",
+        "on_error": "skip_optional"
+      }
+    ],
+    // Agent Mode (Default): Agent implements tests
+    "implementation_approach": [
+      {
+        "step": 1,
+        "title": "Generate comprehensive test suite",
+        "description": "Generate comprehensive test suite based on TEST_ANALYSIS_RESULTS.md. Follow test generation strategy and create all test files listed in section 5 (Implementation Targets).",
+        "modification_points": [
+          "Read TEST_ANALYSIS_RESULTS.md sections 3 and 4",
+          "Study existing test patterns",
+          "Create test files with all required scenarios",
+          "Implement happy path, error handling, edge case, and integration tests",
+          "Add required mocks and fixtures"
+        ],
+        "logic_flow": [
+          "Read TEST_ANALYSIS_RESULTS.md section 3 (Test Requirements by File)",
+          "Read TEST_ANALYSIS_RESULTS.md section 4 (Test Generation Strategy)",
+          "Study existing test patterns from test_context.test_framework.conventions",
+          "For each test file in section 5 (Implementation Targets): Create test file with specified scenarios, Implement happy path tests, Implement error handling tests, Implement edge case tests, Implement integration tests (if specified), Add required mocks and fixtures",
+          "Follow test framework conventions and project standards",
+          "Ensure all tests are executable and syntactically valid"
+        ],
+        "depends_on": [],
+        "output": "test_suite"
+      }
+    ],
+
+    // CLI Execute Mode (--cli-execute): Use Codex command (alternative format shown below)
+    "implementation_approach": [{
+      "step": 1,
+      "title": "Generate tests using Codex",
+      "description": "Use Codex CLI to autonomously generate comprehensive test suite based on TEST_ANALYSIS_RESULTS.md",
+      "modification_points": [
+        "Codex loads TEST_ANALYSIS_RESULTS.md and existing test patterns",
+        "Codex generates all test files listed in analysis section 5",
+        "Codex ensures tests follow framework conventions"
+      ],
+      "logic_flow": [
+        "Start new Codex session",
+        "Pass TEST_ANALYSIS_RESULTS.md to Codex",
+        "Codex studies existing test patterns",
+        "Codex generates comprehensive test suite",
+        "Codex validates test syntax and executability"
+      ],
+      "command": "bash(codex -C [focus_paths] --full-auto exec \"PURPOSE: Generate comprehensive test suite TASK: Create test files based on TEST_ANALYSIS_RESULTS.md section 5 MODE: write CONTEXT: @{.workflow/WFS-test-[session]/.process/TEST_ANALYSIS_RESULTS.md,.workflow/WFS-test-[session]/.process/test-context-package.json} EXPECTED: All test files with happy path, error handling, edge cases, integration tests RULES: Follow test framework conventions, ensure tests are executable\" --skip-git-repo-check -s danger-full-access)",
+      "depends_on": [],
+      "output": "test_generation"
+    }],
+    "target_files": [
+      "{test_file_1 from TEST_ANALYSIS_RESULTS.md section 5}",
+      "{test_file_2 from TEST_ANALYSIS_RESULTS.md section 5}",
+      "{test_file_N from TEST_ANALYSIS_RESULTS.md section 5}"
+    ]
+  }
+}
+```
+
+#### IMPL-002.json - Test Execution & Fix Cycle Task
+
+```json
+{
+  "id": "IMPL-002",
+  "title": "Execute and fix tests for [sourceSessionId]",
+  "status": "pending",
+  "meta": {
+    "type": "test-fix",
+    "agent": "@test-fix-agent",
+    "source_session": "[sourceSessionId]",
+    "test_framework": "jest|pytest|cargo|detected",
+    "max_iterations": 5,
+    "use_codex": false  // Set to true if --use-codex flag present
+  },
+  "context": {
+    "requirements": [
+      "Execute complete test suite (generated in IMPL-001)",
+      "Diagnose test failures using Gemini analysis with bug-fix template",
+      "Present fixes to user for manual application (default)",
+      "Use Codex ONLY if user explicitly requests automation",
+      "Iterate until all tests pass or max iterations reached",
+      "Revert changes if unable to fix within iteration limit"
+    ],
+    "focus_paths": [
+      "tests/**/*",
+      "src/**/*.test.*",
+      "{implementation_files_from_source_session}"
+    ],
+    "acceptance": [
+      "All tests pass successfully (100% pass rate)",
+      "No test failures or errors in final run",
+      "Code changes are minimal and surgical",
+      "All fixes are verified through retest",
+      "Iteration logs document fix progression"
+    ],
+    "depends_on": ["IMPL-001"],
+    "source_context": {
+      "session_id": "[sourceSessionId]",
+      "test_generation_summary": ".workflow/[testSessionId]/.summaries/IMPL-001-summary.md",
+      "implementation_summaries": [
+        ".workflow/[sourceSessionId]/.summaries/IMPL-001-summary.md"
+      ]
+    }
+  },
+  "flow_control": {
+    "pre_analysis": [
+      {
+        "step": "load_source_session_summaries",
+        "action": "Load implementation context from source session",
+        "commands": [
+          "bash(find .workflow/[sourceSessionId]/.summaries/ -name 'IMPL-*-summary.md' 2>/dev/null)",
+          "bash(for f in .workflow/[sourceSessionId]/.summaries/IMPL-*-summary.md; do echo \"=== $(basename $f) ===\"&& cat \"$f\"; done)"
+        ],
+        "output_to": "implementation_context",
+        "on_error": "skip_optional"
+      },
+      {
+        "step": "discover_test_framework",
+        "action": "Identify test framework and test command",
+        "commands": [
+          "bash(jq -r '.scripts.test // \"npm test\"' package.json 2>/dev/null || echo 'pytest' || echo 'cargo test')",
+          "bash([ -f 'package.json' ] && echo 'jest/npm' || [ -f 'pytest.ini' ] && echo 'pytest' || [ -f 'Cargo.toml' ] && echo 'cargo' || echo 'unknown')"
+        ],
+        "output_to": "test_command",
+        "on_error": "fail"
+      },
+      {
+        "step": "analyze_test_coverage",
+        "action": "Analyze test coverage and identify missing tests",
+        "commands": [
+          "mcp__code-index__find_files(pattern=\"*.test.*\")",
+          "mcp__code-index__search_code_advanced(pattern=\"test|describe|it|def test_\", file_pattern=\"*.test.*\")",
+          "bash(# Count implementation files vs test files)",
+          "bash(impl_count=$(find [changed_files_dirs] -type f \\( -name '*.ts' -o -name '*.js' -o -name '*.py' \\) ! -name '*.test.*' 2>/dev/null | wc -l))",
+          "bash(test_count=$(mcp__code-index__find_files(pattern=\"*.test.*\") | wc -l))",
+          "bash(echo \"Implementation files: $impl_count, Test files: $test_count\")"
+        ],
+        "output_to": "test_coverage_analysis",
+        "on_error": "skip_optional"
+      },
+      {
+        "step": "identify_files_without_tests",
+        "action": "List implementation files that lack corresponding test files",
+        "commands": [
+          "bash(# For each changed file from source session, check if test exists)",
+          "bash(for file in [changed_files]; do test_file=$(echo $file | sed 's/\\(.*\\)\\.\\(ts\\|js\\|py\\)$/\\1.test.\\2/'); [ ! -f \"$test_file\" ] && echo \"$file\"; done)"
+        ],
+        "output_to": "files_without_tests",
+        "on_error": "skip_optional"
+      },
+      {
+        "step": "prepare_test_environment",
+        "action": "Ensure test environment is ready",
+        "commands": [
+          "bash([ -f 'package.json' ] && npm install 2>/dev/null || true)",
+          "bash([ -f 'requirements.txt' ] && pip install -q -r requirements.txt 2>/dev/null || true)"
+        ],
+        "output_to": "environment_status",
+        "on_error": "skip_optional"
+      }
+    ],
+    "implementation_approach": [
+      {
+        "step": 1,
+        "title": "Execute iterative test-fix-retest cycle",
+        "description": "Execute iterative test-fix-retest cycle using Gemini diagnosis (bug-fix template) and manual fixes (Codex only if meta.use_codex=true). Max 5 iterations with automatic revert on failure.",
+        "test_fix_cycle": {
+          "max_iterations": 5,
+          "cycle_pattern": "test → gemini_diagnose → manual_fix (or codex if needed) → retest",
+          "tools": {
+            "test_execution": "bash(test_command)",
+            "diagnosis": "gemini-wrapper (MODE: analysis, uses bug-fix template)",
+            "fix_application": "manual (default) or codex exec resume --last (if explicitly needed)",
+            "verification": "bash(test_command) + regression_check"
+          },
+          "exit_conditions": {
+            "success": "all_tests_pass",
+            "failure": "max_iterations_reached",
+            "error": "test_command_not_found"
+          }
+        },
+        "modification_points": [
+        "PHASE 1: Initial Test Execution",
+        "  1.1. Discover test command from framework detection",
+        "  1.2. Execute initial test run: bash([test_command])",
+        "  1.3. Parse test output and count failures",
+        "  1.4. If all pass → Skip to PHASE 3 (success)",
+        "  1.5. If failures → Store failure output, proceed to PHASE 2",
+        "",
+        "PHASE 2: Iterative Test-Fix-Retest Cycle (max 5 iterations)",
+        "  Note: This phase handles test failures, NOT test generation failures",
+        "  Initialize: max_iterations=5, current_iteration=0",
+        "  ",
+        "  WHILE (tests failing AND current_iteration < max_iterations):",
+        "    current_iteration++",
+        "    ",
+        "    STEP 2.1: Gemini Diagnosis (using bug-fix template)",
+        "    - Prepare diagnosis context:",
+        "      * Test failure output from previous run",
+        "      * Source files from focus_paths",
+        "      * Implementation summaries from source session",
+        "    - Execute Gemini analysis with bug-fix template:",
+        "      bash(cd .workflow/WFS-test-[session]/.process && ~/.claude/scripts/gemini-wrapper --all-files -p \"",
+        "      PURPOSE: Diagnose test failure iteration [N] and propose minimal fix",
+        "      TASK: Systematic bug analysis and fix recommendations for test failure",
+        "      MODE: analysis",
+        "      CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}",
+        "               Test output: [test_failures]",
+        "               Source files: [focus_paths]",
+        "               Implementation: [implementation_context]",
+        "      EXPECTED: Root cause analysis, code path tracing, targeted fixes",
+        "      RULES: $(cat ~/.claude/prompt-templates/bug-fix.md) | Bug: [test_failure_description]",
+        "             Minimal surgical fixes only - no refactoring",
+        "      \" > fix-iteration-[N]-diagnosis.md)",
+        "    - Parse diagnosis → extract fix_suggestion and target_files",
+        "    - Present fix to user for manual application (default)",
+        "    ",
+        "    STEP 2.2: Apply Fix (Based on meta.use_codex Flag)",
+        "    ",
+        "    IF meta.use_codex = false (DEFAULT):",
+        "    - Present Gemini diagnosis to user for manual fix",
+        "    - User applies fix based on diagnosis recommendations",
+        "    - Stage changes: bash(git add -A)",
+        "    - Store fix log: .process/fix-iteration-[N]-changes.log",
+        "    ",
+        "    IF meta.use_codex = true (--use-codex flag present):",
+        "    - Stage current changes (if valid git repo): bash(git add -A)",
+        "    - First iteration: Start new Codex session",
+        "      codex -C [project_root] --full-auto exec \"",
+        "      PURPOSE: Fix test failure iteration 1",
+        "      TASK: [fix_suggestion from Gemini]",
+        "      MODE: write",
+        "      CONTEXT: Diagnosis: .workflow/.process/fix-iteration-1-diagnosis.md",
+        "               Target files: [target_files]",
+        "               Implementation context: [implementation_context]",
+        "      EXPECTED: Minimal code changes to resolve test failure",
+        "      RULES: Apply ONLY suggested changes, no refactoring",
+        "             Preserve existing code style",
+        "      \" --skip-git-repo-check -s danger-full-access",
+        "    - Subsequent iterations: Resume session for context continuity",
+        "      codex exec \"",
+        "      CONTINUE TO NEXT FIX:",
+        "      Iteration [N] of 5: Fix test failure",
+        "      ",
+        "      PURPOSE: Fix remaining test failures",
+        "      TASK: [fix_suggestion from Gemini iteration N]",
+        "      CONTEXT: Previous fixes applied, diagnosis: .process/fix-iteration-[N]-diagnosis.md",
+        "      EXPECTED: Surgical fix for current failure",
+        "      RULES: Build on previous fixes, maintain consistency",
+        "      \" resume --last --skip-git-repo-check -s danger-full-access",
+        "    - Store fix log: .process/fix-iteration-[N]-changes.log",
+        "    ",
+        "    STEP 2.3: Retest and Verification",
+        "    - Re-execute test suite: bash([test_command])",
+        "    - Capture output: .process/fix-iteration-[N]-retest.log",
+        "    - Count failures: bash(grep -c 'FAIL\\|ERROR' .process/fix-iteration-[N]-retest.log)",
+        "    - Check for regression:",
+        "      IF new_failures > previous_failures:",
+        "        WARN: Regression detected",
+        "        Include in next Gemini diagnosis context",
+        "    - Analyze results:",
+        "      IF all_tests_pass:",
+        "        BREAK loop → Proceed to PHASE 3",
+        "      ELSE:",
+        "        Update test_failures context",
+        "        CONTINUE loop",
+        "  ",
+        "  IF max_iterations reached AND tests still failing:",
+        "    EXECUTE: git reset --hard HEAD (revert all changes)",
+        "    MARK: Task status = blocked",
+        "    GENERATE: Detailed failure report with iteration logs",
+        "    EXIT: Require manual intervention",
+        "",
+        "PHASE 3: Final Validation and Certification",
+        "  3.1. Execute final confirmation test run",
+        "  3.2. Generate success summary:",
+        "       - Iterations required: [current_iteration]",
+        "       - Fixes applied: [summary from iteration logs]",
+        "       - Test results: All passing ✅",
+        "  3.3. Mark task status: completed",
+        "  3.4. Update TODO_LIST.md: Mark as ✅",
+        "  3.5. Certify code: APPROVED for deployment"
+      ],
+      "logic_flow": [
+        "Load source session implementation context",
+        "Discover test framework and command",
+        "PHASE 0: Test Coverage Check",
+        "  Analyze existing test files",
+        "  Identify files without tests",
+        "  IF tests missing:",
+        "    Report to user (no automatic generation)",
+        "    Wait for user to generate tests or request automation",
+        "  ELSE:",
+        "    Skip to Phase 1",
+        "PHASE 1: Initial Test Execution",
+        "  Execute test suite",
+        "  IF all pass → Success (Phase 3)",
+        "  ELSE → Store failures, proceed to Phase 2",
+        "PHASE 2: Iterative Fix Cycle (max 5 iterations)",
+        "  LOOP (max 5 times):",
+        "    1. Gemini diagnoses failure with bug-fix template → fix suggestion",
+        "    2. Check meta.use_codex flag:",
+        "       - IF false (default): Present fix to user for manual application",
+        "       - IF true (--use-codex): Codex applies fix with resume for continuity",
+        "    3. Retest and check results",
+        "    4. IF pass → Exit loop to Phase 3",
+        "    5. ELSE → Continue with updated context",
+        "  IF max iterations → Revert + report failure",
+        "PHASE 3: Final Validation",
+        "  Confirm all tests pass",
+        "  Generate summary (include test generation info)",
+        "  Certify code APPROVED"
+      ],
+        "error_handling": {
+          "max_iterations_reached": {
+            "action": "revert_all_changes",
+            "commands": [
+              "bash(git reset --hard HEAD)",
+              "bash(jq '.status = \"blocked\"' .workflow/[session]/.task/IMPL-001.json > temp.json && mv temp.json .workflow/[session]/.task/IMPL-001.json)"
+            ],
+            "report": "Generate failure report with iteration logs in .summaries/IMPL-001-failure-report.md"
+          },
+          "test_command_fails": {
+            "action": "treat_as_test_failure",
+            "context": "Use stderr as failure context for Gemini diagnosis"
+          },
+          "codex_apply_fails": {
+            "action": "retry_once_then_skip",
+            "fallback": "Mark iteration as skipped, continue to next"
+          },
+          "gemini_diagnosis_fails": {
+            "action": "retry_with_simplified_context",
+            "fallback": "Use previous diagnosis, continue"
+          },
+          "regression_detected": {
+            "action": "log_warning_continue",
+            "context": "Include regression info in next Gemini diagnosis"
+          }
+        },
+        "depends_on": [],
+        "output": "test_fix_results"
+      }
+    ],
+    "target_files": [
+      "Auto-discovered from test failures",
+      "Extracted from Gemini diagnosis each iteration",
+      "Format: file:function:lines or file (for new files)"
+    ],
+    "codex_session": {
+      "strategy": "resume_for_continuity",
+      "first_iteration": "codex exec \"fix iteration 1\" --full-auto",
+      "subsequent_iterations": "codex exec \"fix iteration N\" resume --last",
+      "benefits": [
+        "Maintains conversation context across fixes",
+        "Remembers previous decisions and patterns",
+        "Ensures consistency in fix approach",
+        "Reduces redundant context injection"
+      ]
+    }
+  }
+}
+```
+
+### Phase 3: IMPL_PLAN.md Generation
+
+#### Document Structure
+```markdown
+---
+identifier: WFS-test-[session-id]
+source_session: WFS-[source-session-id]
+workflow_type: test_session
+test_framework: jest|pytest|cargo|detected
+---
+
+# Test Validation Plan: [Source Session Topic]
+
+## Summary
+Execute comprehensive test suite for implementation from session WFS-[source-session-id].
+Diagnose and fix all test failures using iterative Gemini analysis and Codex execution.
+
+## Source Session Context
+- **Implementation Session**: WFS-[source-session-id]
+- **Completed Tasks**: IMPL-001, IMPL-002, ...
+- **Changed Files**: [list from git log]
+- **Implementation Summaries**: [references to source session summaries]
+
+## Test Framework
+- **Detected Framework**: jest|pytest|cargo|other
+- **Test Command**: npm test|pytest|cargo test
+- **Test Files**: [discovered test files]
+- **Coverage**: [estimated test coverage]
+
+## Test-Fix-Retest Cycle
+- **Max Iterations**: 5
+- **Diagnosis Tool**: Gemini (analysis mode with bug-fix template from bug-index.md)
+- **Fix Tool**: Manual (default, meta.use_codex=false) or Codex (if --use-codex flag, meta.use_codex=true)
+- **Verification**: Bash test execution + regression check
+
+### Cycle Workflow
+1. **Initial Test**: Execute full suite, capture failures
+2. **Iterative Fix Loop** (max 5 times):
+   - Gemini diagnoses failure using bug-fix template → surgical fix suggestion
+   - Check meta.use_codex flag:
+     - If false (default): Present fix to user for manual application
+     - If true (--use-codex): Codex applies fix with resume for context continuity
+   - Retest and verify (check for regressions)
+   - Continue until all pass or max iterations reached
+3. **Final Validation**: Confirm all tests pass, certify code
+
+### Error Recovery
+- **Max iterations reached**: Revert all changes, report failure
+- **Test command fails**: Treat as test failure, diagnose with Gemini
+- **Codex fails**: Retry once, skip iteration if still failing
+- **Regression detected**: Log warning, include in next diagnosis
+
+## Task Breakdown
+- **IMPL-001**: Execute and validate tests with iterative fix cycle
+
+## Implementation Strategy
+- **Phase 1**: Initial test execution and failure capture
+- **Phase 2**: Iterative Gemini diagnosis + Codex fix + retest
+- **Phase 3**: Final validation and code certification
+
+## Success Criteria
+- All tests pass (100% pass rate)
+- No test failures or errors in final run
+- Minimal, surgical code changes
+- Iteration logs document fix progression
+- Code certified APPROVED for deployment
+```
+
+### Phase 4: TODO_LIST.md Generation
+
+```markdown
+# Tasks: Test Validation for [Source Session]
+
+## Task Progress
+- [ ] **IMPL-001**: Execute and validate tests with iterative fix cycle → [📋](./.task/IMPL-001.json)
+
+## Execution Details
+- **Source Session**: WFS-[source-session-id]
+- **Test Framework**: jest|pytest|cargo
+- **Max Iterations**: 5
+- **Tools**: Gemini diagnosis + Codex resume fixes
+
+## Status Legend
+- `- [ ]` = Pending
+- `- [x]` = Completed
+```
+
+## Output Files Structure
+```
+.workflow/WFS-test-[session]/
+├── workflow-session.json           # Test session metadata
+├── IMPL_PLAN.md                    # Test validation plan
+├── TODO_LIST.md                    # Progress tracking
+├── .task/
+│   └── IMPL-001.json               # Test-fix task with cycle spec
+├── .process/
+│   ├── ANALYSIS_RESULTS.md         # From concept-enhanced (optional)
+│   ├── context-package.json        # From context-gather
+│   ├── initial-test.log            # Phase 1: Initial test results
+│   ├── fix-iteration-1-diagnosis.md # Gemini diagnosis iteration 1
+│   ├── fix-iteration-1-changes.log  # Codex changes iteration 1
+│   ├── fix-iteration-1-retest.log   # Retest results iteration 1
+│   ├── fix-iteration-N-*.md/log    # Subsequent iterations
+│   └── final-test.log              # Phase 3: Final validation
+└── .summaries/
+    └── IMPL-001-summary.md         # Success report OR failure report
+```
+
+## Error Handling
+
+### Input Validation Errors
+| Error | Cause | Resolution |
+|-------|-------|------------|
+| Not a test session | Missing workflow_type: "test_session" | Verify session created by test-gen |
+| Source session not found | Invalid source_session_id | Check source session exists |
+| No implementation summaries | Source session incomplete | Ensure source session has completed tasks |
+
+### Test Framework Discovery Errors
+| Error | Cause | Resolution |
+|-------|-------|------------|
+| No test command found | Unknown framework | Manual test command specification |
+| No test files found | Tests not written | Request user to write tests first |
+| Test dependencies missing | Incomplete setup | Run dependency installation |
+
+### Generation Errors
+| Error | Cause | Resolution |
+|-------|-------|------------|
+| Invalid JSON structure | Template error | Fix task generation logic |
+| Missing required fields | Incomplete metadata | Validate session metadata |
+
+## Integration & Usage
+
+### Command Chain
+- **Called By**: `/workflow:test-gen` (Phase 4)
+- **Calls**: None (terminal command)
+- **Followed By**: `/workflow:execute` (user-triggered)
+
+### Basic Usage
+```bash
+# Manual fix mode (default)
+/workflow:tools:test-task-generate --session WFS-test-auth
+
+# Automated Codex fix mode
+/workflow:tools:test-task-generate --use-codex --session WFS-test-auth
+```
+
+### Flag Behavior
+- **No flag**: `meta.use_codex=false`, manual fixes presented to user
+- **--use-codex**: `meta.use_codex=true`, Codex automatically applies fixes with resume mechanism
+
+## Related Commands
+- `/workflow:test-gen` - Creates test session and calls this tool
+- `/workflow:tools:context-gather` - Provides cross-session context
+- `/workflow:tools:concept-enhanced` - Provides test strategy analysis
+- `/workflow:execute` - Executes the generated test-fix task
+- `@test-fix-agent` - Agent that executes the iterative test-fix cycle
+
+## Agent Execution Notes
+
+The `@test-fix-agent` will execute the task by following the `flow_control.implementation_approach` specification:
+
+1. **Load task JSON**: Read complete test-fix task from `.task/IMPL-002.json`
+2. **Check meta.use_codex**: Determine fix mode (manual or automated)
+3. **Execute pre_analysis**: Load source context, discover framework, analyze tests
+4. **Phase 1**: Run initial test suite
+5. **Phase 2**: If failures, enter iterative loop:
+   - Use Gemini for diagnosis (analysis mode with bug-fix template)
+   - Check meta.use_codex flag:
+     - If false (default): Present fix suggestions to user for manual application
+     - If true (--use-codex): Use Codex resume for automated fixes (maintains context)
+   - Retest and check for regressions
+   - Repeat max 5 times
+6. **Phase 3**: Generate summary and certify code
+7. **Error Recovery**: Revert changes if max iterations reached
+
+**Bug Diagnosis Template**: Uses bug-fix.md template as referenced in bug-index.md for systematic root cause analysis, code path tracing, and targeted fix recommendations.
+
+**Codex Usage**: The agent uses `codex exec "..." resume --last` pattern ONLY when meta.use_codex=true (--use-codex flag present) to maintain conversation context across multiple fix iterations, ensuring consistency and learning from previous attempts.

.claude/commands/workflow/ui-design/batch-generate.md

@@ -0,0 +1,464 @@
+---
+name: batch-generate
+description: Prompt-driven batch UI generation using target-style-centric parallel execution
+argument-hint: [--targets "<list>"] [--target-type "page|component"] [--device-type "desktop|mobile|tablet|responsive"] [--base-path <path>] [--session <id>] [--style-variants <count>] [--layout-variants <count>]
+allowed-tools: TodoWrite(*), Read(*), Write(*), Task(ui-design-agent), Bash(*), mcp__exa__web_search_exa(*)
+---
+
+# Batch Generate UI Prototypes (/workflow:ui-design:batch-generate)
+
+## Overview
+Prompt-driven UI generation with intelligent target extraction and **target-style-centric batch execution**. Each agent handles all layouts for one target × style combination.
+
+**Strategy**: Prompt → Targets → Batched Generation
+- **Prompt-driven**: Describe what to build, command extracts targets
+- **Agent scope**: Each of `T × S` agents generates `L` layouts
+- **Parallel batching**: Max 6 concurrent agents for optimal throughput
+- **Component isolation**: Complete task independence
+- **Style-aware**: HTML adapts to design_attributes
+- **Self-contained CSS**: Direct token values (no var() refs)
+
+**Supports**: Pages (full layouts) and components (isolated elements)
+
+## Phase 1: Setup & Validation
+
+### Step 1: Parse Prompt & Resolve Configuration
+```bash
+# Parse required parameters
+prompt_text = --prompt
+device_type = --device-type OR "responsive"
+
+# Extract targets from prompt
+IF --targets:
+    target_list = split_and_clean(--targets)
+ELSE:
+    target_list = extract_targets_from_prompt(prompt_text)  # See helpers
+    IF NOT target_list: target_list = ["home"]  # Fallback
+
+# Detect target type
+target_type = --target-type OR detect_target_type(target_list)
+
+# Resolve base path
+IF --base-path:
+    base_path = --base-path
+ELSE IF --session:
+    bash(find .workflow/WFS-{session} -type d -name "design-*" -printf "%T@ %p\n" | sort -nr | head -1 | cut -d' ' -f2)
+ELSE:
+    bash(find .workflow -type d -name "design-*" -printf "%T@ %p\n" | sort -nr | head -1 | cut -d' ' -f2)
+
+# Get variant counts
+style_variants = --style-variants OR bash(ls {base_path}/style-consolidation/style-* -d | wc -l)
+layout_variants = --layout-variants OR 3
+```
+
+**Output**: `base_path`, `target_list[]`, `target_type`, `device_type`, `style_variants`, `layout_variants`
+
+### Step 2: Detect Token Sources
+```bash
+# Check consolidated (priority 1) or proposed (priority 2)
+bash(test -f {base_path}/style-consolidation/style-1/design-tokens.json && echo "consolidated")
+# OR
+bash(test -f {base_path}/style-extraction/style-cards.json && echo "proposed")
+
+# If proposed: Create temp consolidation dirs + write tokens
+FOR style_id IN 1..style_variants:
+    bash(mkdir -p {base_path}/style-consolidation/style-{style_id})
+    Write({base_path}/style-consolidation/style-{style_id}/design-tokens.json, proposed_tokens)
+
+# Load design space analysis (optional)
+IF exists({base_path}/style-extraction/design-space-analysis.json):
+    design_space_analysis = Read({base_path}/style-extraction/design-space-analysis.json)
+```
+
+**Output**: `token_sources{}`, `consolidated_count`, `proposed_count`, `design_space_analysis`
+
+### Step 3: Gather Layout Inspiration
+```bash
+bash(mkdir -p {base_path}/prototypes/_inspirations)
+
+# For each target: Research via MCP
+FOR target IN target_list:
+    search_query = "{target} {target_type} layout patterns variations"
+    mcp__exa__web_search_exa(query=search_query, numResults=5)
+
+    # Extract context from prompt for this target
+    target_requirements = extract_relevant_context_from_prompt(prompt_text, target)
+
+    # Write simple inspiration file
+    Write({base_path}/prototypes/_inspirations/{target}-layout-ideas.txt, inspiration_content)
+```
+
+**Output**: `T` inspiration text files
+
+## Phase 2: Target-Style-Centric Batch Generation (Agent)
+
+**Executor**: `Task(ui-design-agent)` × `T × S` tasks in **batched parallel** (max 6 concurrent)
+
+### Step 1: Calculate Batch Execution Plan
+```bash
+bash(mkdir -p {base_path}/prototypes)
+
+# Build task list: T × S combinations
+MAX_PARALLEL = 6
+total_tasks = T × S
+total_batches = ceil(total_tasks / MAX_PARALLEL)
+
+# Initialize batch tracking
+TodoWrite({todos: [
+  {content: "Batch 1/{batches}: Generate 6 tasks", status: "in_progress"},
+  {content: "Batch 2/{batches}: Generate 6 tasks", status: "pending"},
+  ...
+]})
+```
+
+### Step 2: Launch Batched Agent Tasks
+For each batch (up to 6 parallel tasks):
+```javascript
+Task(ui-design-agent): `
+  [TARGET_STYLE_UI_GENERATION_FROM_PROMPT]
+  🎯 ONE component: {target} × Style-{style_id} ({philosophy_name})
+  Generate: {layout_variants} × 2 files (HTML + CSS per layout)
+
+  PROMPT CONTEXT: {target_requirements}  # Extracted from original prompt
+  TARGET: {target} | TYPE: {target_type} | STYLE: {style_id}/{style_variants}
+  BASE_PATH: {base_path}
+  DEVICE: {device_type}
+  ${design_attributes ? "DESIGN_ATTRIBUTES: " + JSON.stringify(design_attributes) : ""}
+
+  ## Reference
+  - Layout inspiration: Read("{base_path}/prototypes/_inspirations/{target}-layout-ideas.txt")
+  - Design tokens: Read("{base_path}/style-consolidation/style-{style_id}/design-tokens.json")
+    Parse ALL token values (colors, typography, spacing, borders, shadows, breakpoints)
+  ${design_attributes ? "- Adapt DOM to: density, visual_weight, formality, organic_vs_geometric" : ""}
+
+  ## Generation
+  For EACH layout (1 to {layout_variants}):
+
+  1. HTML: {base_path}/prototypes/{target}-style-{style_id}-layout-N.html
+     - Complete HTML5: <!DOCTYPE>, <head>, <body>
+     - CSS ref: <link href="{target}-style-{style_id}-layout-N.css">
+     - Semantic: <header>, <nav>, <main>, <footer>
+     - A11y: ARIA labels, landmarks, responsive meta
+     - Viewport: <meta name="viewport" content="width=device-width, initial-scale=1.0">
+     - Follow user requirements from prompt
+     ${design_attributes ? `
+     - DOM adaptation:
+       * density='spacious' → flatter hierarchy
+       * density='compact' → deeper nesting
+       * visual_weight='heavy' → extra wrappers
+       * visual_weight='minimal' → direct structure` : ""}
+     - Device-specific: Optimize for {device_type}
+
+  2. CSS: {base_path}/prototypes/{target}-style-{style_id}-layout-N.css
+     - Self-contained: Direct token VALUES (no var())
+     - Use tokens: colors, fonts, spacing, borders, shadows
+     - Device-optimized: {device_type} styles
+     ${device_type === 'responsive' ? '- Responsive: Mobile-first @media' : '- Fixed: ' + device_type}
+     ${design_attributes ? `
+     - Token selection: density → spacing, visual_weight → shadows` : ""}
+
+  ## Notes
+  - ✅ Token VALUES directly from design-tokens.json
+  - ✅ Follow prompt requirements for {target}
+  - ✅ Optimize for {device_type}
+  - ❌ NO var() refs, NO external deps
+  - Layouts structurally DISTINCT
+  - Write files IMMEDIATELY (per layout)
+  - CSS filename MUST match HTML <link href>
+`
+
+# After each batch completes
+TodoWrite: Mark batch completed, next batch in_progress
+```
+
+## Phase 3: Verify & Generate Previews
+
+### Step 1: Verify Generated Files
+```bash
+# Count expected vs found
+bash(ls {base_path}/prototypes/{target}-style-*-layout-*.html | wc -l)
+# Expected: S × L × T × 2
+
+# Validate samples
+Read({base_path}/prototypes/{target}-style-{style_id}-layout-{layout_id}.html)
+# Check: <!DOCTYPE html>, correct CSS href, sufficient CSS length
+```
+
+**Output**: `S × L × T × 2` files verified
+
+### Step 2: Run Preview Generation Script
+```bash
+bash(~/.claude/scripts/ui-generate-preview.sh "{base_path}/prototypes")
+```
+
+**Script generates**:
+- `compare.html` (interactive matrix)
+- `index.html` (navigation)
+- `PREVIEW.md` (instructions)
+
+### Step 3: Verify Preview Files
+```bash
+bash(ls {base_path}/prototypes/compare.html {base_path}/prototypes/index.html {base_path}/prototypes/PREVIEW.md)
+```
+
+**Output**: 3 preview files
+
+## Completion
+
+### Todo Update
+```javascript
+TodoWrite({todos: [
+  {content: "Setup and parse prompt", status: "completed", activeForm: "Parsing prompt"},
+  {content: "Detect token sources", status: "completed", activeForm: "Loading design systems"},
+  {content: "Gather layout inspiration", status: "completed", activeForm: "Researching layouts"},
+  {content: "Batch 1/{batches}: Generate 6 tasks", status: "completed", activeForm: "Generating batch 1"},
+  ... (all batches completed)
+  {content: "Verify files & generate previews", status: "completed", activeForm: "Creating previews"}
+]});
+```
+
+### Output Message
+```
+✅ Prompt-driven batch UI generation complete!
+
+Prompt: {prompt_text}
+
+Configuration:
+- Style Variants: {style_variants}
+- Layout Variants: {layout_variants}
+- Target Type: {target_type}
+- Device Type: {device_type}
+- Targets: {target_list} ({T} targets)
+- Total Prototypes: {S × L × T}
+
+Batch Execution:
+- Total tasks: {T × S} (targets × styles)
+- Batches: {batches} (max 6 parallel per batch)
+- Agent scope: {L} layouts per target×style
+- Component isolation: Complete task independence
+- Device-specific: All layouts optimized for {device_type}
+
+Quality:
+- Style-aware: {design_space_analysis ? 'HTML adapts to design_attributes' : 'Standard structure'}
+- CSS: Self-contained (direct token values, no var())
+- Device-optimized: {device_type} layouts
+- Tokens: {consolidated_count} consolidated, {proposed_count} proposed
+{IF proposed_count > 0: '  💡 For production: /workflow:ui-design:consolidate'}
+
+Generated Files:
+{base_path}/prototypes/
+├── _inspirations/ ({T} text files)
+├── {target}-style-{s}-layout-{l}.html ({S×L×T} prototypes)
+├── {target}-style-{s}-layout-{l}.css
+├── compare.html (interactive matrix)
+├── index.html (navigation)
+└── PREVIEW.md (instructions)
+
+Preview:
+1. Open compare.html (recommended)
+2. Open index.html
+3. Read PREVIEW.md
+
+Next: /workflow:ui-design:update
+```
+
+## Simple Bash Commands
+
+### Path Operations
+```bash
+# Find design directory
+bash(find .workflow -type d -name "design-*" -printf "%T@ %p\n" | sort -nr | head -1 | cut -d' ' -f2)
+
+# Count style variants
+bash(ls {base_path}/style-consolidation/style-* -d | wc -l)
+
+# Check token sources
+bash(test -f {base_path}/style-consolidation/style-1/design-tokens.json && echo "consolidated")
+bash(test -f {base_path}/style-extraction/style-cards.json && echo "proposed")
+```
+
+### Validation Commands
+```bash
+# Count generated files
+bash(ls {base_path}/prototypes/{target}-style-*-layout-*.html | wc -l)
+
+# Verify preview
+bash(test -f {base_path}/prototypes/compare.html && echo "exists")
+```
+
+### File Operations
+```bash
+# Create directories
+bash(mkdir -p {base_path}/prototypes/_inspirations)
+
+# Run preview script
+bash(~/.claude/scripts/ui-generate-preview.sh "{base_path}/prototypes")
+```
+
+## Output Structure
+
+```
+{base_path}/
+├── prototypes/
+│   ├── _inspirations/
+│   │   └── {target}-layout-ideas.txt  # Layout inspiration
+│   ├── {target}-style-{s}-layout-{l}.html  # Final prototypes
+│   ├── {target}-style-{s}-layout-{l}.css
+│   ├── compare.html
+│   ├── index.html
+│   └── PREVIEW.md
+└── style-consolidation/
+    └── style-{s}/
+        ├── design-tokens.json
+        └── style-guide.md
+```
+
+## Error Handling
+
+### Common Errors
+```
+ERROR: No token sources found
+→ Run /workflow:ui-design:extract or /workflow:ui-design:consolidate
+
+ERROR: No targets extracted from prompt
+→ Use --targets explicitly or rephrase prompt
+
+ERROR: MCP search failed
+→ Check network, retry
+
+ERROR: Batch {N} agent tasks failed
+→ Check agent output, retry specific target×style combinations
+
+ERROR: Script permission denied
+→ chmod +x ~/.claude/scripts/ui-generate-preview.sh
+```
+
+### Recovery Strategies
+- **Partial success**: Keep successful target×style combinations
+- **Missing design_attributes**: Works without (less style-aware)
+- **Invalid tokens**: Validate design-tokens.json structure
+- **Failed batch**: Re-run command, only failed combinations will retry
+
+## Quality Checklist
+
+- [ ] Prompt clearly describes targets
+- [ ] CSS uses direct token values (no var())
+- [ ] HTML adapts to design_attributes (if available)
+- [ ] Semantic HTML5 structure
+- [ ] ARIA attributes present
+- [ ] Device-optimized layouts
+- [ ] Layouts structurally distinct
+- [ ] compare.html works
+
+## Key Features
+
+- **Prompt-Driven**: Describe what to build, command extracts targets
+- **Target-Style-Centric**: `T×S` agents, each handles `L` layouts
+- **Parallel Batching**: Max 6 concurrent agents with progress tracking
+- **Component Isolation**: Complete task independence
+- **Style-Aware**: HTML adapts to design_attributes
+- **Self-Contained CSS**: Direct token values (no var())
+- **Device-Specific**: Optimized for desktop/mobile/tablet/responsive
+- **Inspiration-Based**: MCP-powered layout research
+- **Production-Ready**: Semantic, accessible, responsive
+
+## Integration
+
+**Input**: Prompt, design-tokens.json, design-space-analysis.json (optional)
+**Output**: S×L×T prototypes for `/workflow:ui-design:update`
+**Compatible**: extract, consolidate, explore-auto, imitate-auto outputs
+
+## Usage Examples
+
+### Basic: Auto-detection
+```bash
+/workflow:ui-design:batch-generate \
+  --prompt "Dashboard with metric cards and charts"
+
+# Auto: latest design run, extracts "dashboard" target
+# Output: S × L × 1 prototypes
+```
+
+### With Session
+```bash
+/workflow:ui-design:batch-generate \
+  --prompt "Auth pages: login, signup, password reset" \
+  --session WFS-auth
+
+# Uses WFS-auth's design run
+# Extracts: ["login", "signup", "password-reset"]
+# Batches: 2 (if S=3: 9 tasks = 6+3)
+# Output: S × L × 3 prototypes
+```
+
+### Components with Device Type
+```bash
+/workflow:ui-design:batch-generate \
+  --prompt "Mobile UI components: navbar, card, footer" \
+  --target-type component \
+  --device-type mobile
+
+# Mobile-optimized component generation
+# Output: S × L × 3 prototypes
+```
+
+### Large Scale (Multi-batch)
+```bash
+/workflow:ui-design:batch-generate \
+  --prompt "E-commerce site" \
+  --targets "home,shop,product,cart,checkout" \
+  --style-variants 4 \
+  --layout-variants 2
+
+# Tasks: 5 × 4 = 20 (4 batches: 6+6+6+2)
+# Output: 4 × 2 × 5 = 40 prototypes
+```
+
+## Helper Functions Reference
+
+### Target Extraction
+```python
+# extract_targets_from_prompt(prompt_text)
+# Patterns: "Create X and Y", "Generate X, Y, Z pages", "Build X"
+# Returns: ["x", "y", "z"] (normalized lowercase with hyphens)
+
+# detect_target_type(target_list)
+# Keywords: page (home, dashboard, login) vs component (navbar, card, button)
+# Returns: "page" or "component"
+
+# extract_relevant_context_from_prompt(prompt_text, target)
+# Extracts sentences mentioning specific target
+# Returns: Relevant context string
+```
+
+## Batch Execution Details
+
+### Parallel Control
+- **Max concurrent**: 6 agents per batch
+- **Task distribution**: T × S tasks = ceil(T×S/6) batches
+- **Progress tracking**: TodoWrite per-batch status
+- **Examples**:
+  - 3 tasks → 1 batch
+  - 9 tasks → 2 batches (6+3)
+  - 20 tasks → 4 batches (6+6+6+2)
+
+### Performance
+| Tasks | Batches | Est. Time | Efficiency |
+|-------|---------|-----------|------------|
+| 1-6   | 1       | 3-5 min   | 100%       |
+| 7-12  | 2       | 6-10 min  | ~85%       |
+| 13-18 | 3       | 9-15 min  | ~80%       |
+| 19-30 | 4-5     | 12-25 min | ~75%       |
+
+### Optimization Tips
+1. **Reduce tasks**: Fewer targets or styles
+2. **Adjust layouts**: L=2 instead of L=3 for faster iteration
+3. **Stage generation**: Core pages first, secondary pages later
+
+## Notes
+
+- **Prompt quality**: Clear descriptions improve target extraction
+- **Token sources**: Consolidated (production) or proposed (fast-track)
+- **Batch parallelism**: Max 6 concurrent for stability
+- **Scalability**: Tested up to 30+ tasks (5+ batches)
+- **Dependencies**: MCP web search, ui-generate-preview.sh script

.claude/commands/workflow/ui-design/capture.md

@@ -0,0 +1,361 @@
+---
+name: capture
+description: Batch screenshot capture for UI design workflows using MCP or local fallback
+argument-hint: --url-map "target:url,..." [--base-path path] [--session id]
+allowed-tools: TodoWrite(*), Read(*), Write(*), Bash(*), Glob(*), ListMcpResourcesTool(*), mcp__chrome-devtools__*, mcp__playwright__*
+---
+
+# Batch Screenshot Capture (/workflow:ui-design:capture)
+
+## Overview
+Batch screenshot tool with MCP-first strategy and multi-tier fallback. Processes multiple URLs in parallel.
+
+**Strategy**: MCP → Playwright → Chrome → Manual
+**Output**: Flat structure `screenshots/{target}.png`
+
+## Phase 1: Initialize & Parse
+
+### Step 1: Determine Base Path
+```bash
+# Priority: --base-path > session > standalone
+bash(if [ -n "$BASE_PATH" ]; then
+  echo "$BASE_PATH"
+elif [ -n "$SESSION_ID" ]; then
+  find .workflow/WFS-$SESSION_ID/design-* -type d | head -1 || \
+  echo ".workflow/WFS-$SESSION_ID/design-run-$(date +%Y%m%d-%H%M%S)"
+else
+  echo ".workflow/.design/run-$(date +%Y%m%d-%H%M%S)"
+fi)
+
+bash(mkdir -p $BASE_PATH/screenshots)
+```
+
+### Step 2: Parse URL Map
+```javascript
+// Input: "home:https://linear.app, pricing:https://linear.app/pricing"
+url_entries = []
+
+FOR pair IN split(params["--url-map"], ","):
+  parts = pair.split(":", 1)
+
+  IF len(parts) != 2:
+    ERROR: "Invalid format: {pair}. Expected: 'target:url'"
+    EXIT 1
+
+  target = parts[0].strip().lower().replace(" ", "-")
+  url = parts[1].strip()
+
+  // Validate target name
+  IF NOT regex_match(target, r"^[a-z0-9][a-z0-9_-]*$"):
+    ERROR: "Invalid target: {target}"
+    EXIT 1
+
+  // Add https:// if missing
+  IF NOT url.startswith("http"):
+    url = f"https://{url}"
+
+  url_entries.append({target, url})
+```
+
+**Output**: `base_path`, `url_entries[]`
+
+### Step 3: Initialize Todos
+```javascript
+TodoWrite({todos: [
+  {content: "Parse url-map", status: "completed", activeForm: "Parsing"},
+  {content: "Detect MCP tools", status: "in_progress", activeForm: "Detecting"},
+  {content: "Capture screenshots", status: "pending", activeForm: "Capturing"},
+  {content: "Verify results", status: "pending", activeForm: "Verifying"}
+]})
+```
+
+## Phase 2: Detect Screenshot Tools
+
+### Step 1: Check MCP Availability
+```javascript
+// List available MCP servers
+all_resources = ListMcpResourcesTool()
+available_servers = unique([r.server for r in all_resources])
+
+// Check Chrome DevTools MCP
+chrome_devtools = "chrome-devtools" IN available_servers
+chrome_screenshot = check_tool_exists("mcp__chrome-devtools__take_screenshot")
+
+// Check Playwright MCP
+playwright_mcp = "playwright" IN available_servers
+playwright_screenshot = check_tool_exists("mcp__playwright__screenshot")
+
+// Determine primary tool
+IF chrome_devtools AND chrome_screenshot:
+  tool = "chrome-devtools"
+ELSE IF playwright_mcp AND playwright_screenshot:
+  tool = "playwright"
+ELSE:
+  tool = null
+```
+
+**Output**: `tool` (chrome-devtools | playwright | null)
+
+### Step 2: Check Local Fallback
+```bash
+# Only if MCP unavailable
+bash(which playwright 2>/dev/null || echo "")
+bash(which google-chrome || which chrome || which chromium 2>/dev/null || echo "")
+```
+
+**Output**: `local_tools[]`
+
+## Phase 3: Capture Screenshots
+
+### Screenshot Format Options
+
+**PNG Format** (default, lossless):
+- **Pros**: Lossless quality, best for detailed UI screenshots
+- **Cons**: Larger file sizes (typically 200-500 KB per screenshot)
+- **Parameters**: `format: "png"` (no quality parameter)
+- **Use case**: High-fidelity UI replication, design system extraction
+
+**WebP Format** (optional, lossy/lossless):
+- **Pros**: Smaller file sizes with good quality (50-70% smaller than PNG)
+- **Cons**: Requires quality parameter, slight quality loss at high compression
+- **Parameters**: `format: "webp", quality: 90` (80-100 recommended)
+- **Use case**: Batch captures, network-constrained environments
+
+**JPEG Format** (optional, lossy):
+- **Pros**: Smallest file sizes
+- **Cons**: Lossy compression, not recommended for UI screenshots
+- **Parameters**: `format: "jpeg", quality: 90`
+- **Use case**: Photo-heavy pages, not recommended for UI design
+
+### Step 1: MCP Capture (If Available)
+```javascript
+IF tool == "chrome-devtools":
+  // Get or create page
+  pages = mcp__chrome-devtools__list_pages()
+
+  IF pages.length == 0:
+    mcp__chrome-devtools__new_page({url: url_entries[0].url})
+    page_idx = 0
+  ELSE:
+    page_idx = 0
+
+  mcp__chrome-devtools__select_page({pageIdx: page_idx})
+
+  // Capture each URL
+  FOR entry IN url_entries:
+    mcp__chrome-devtools__navigate_page({url: entry.url, timeout: 30000})
+    bash(sleep 2)
+
+    // PNG format doesn't support quality parameter
+    // Use PNG for lossless quality (larger files)
+    mcp__chrome-devtools__take_screenshot({
+      fullPage: true,
+      format: "png",
+      filePath: f"{base_path}/screenshots/{entry.target}.png"
+    })
+
+    // Alternative: Use WebP with quality for smaller files
+    // mcp__chrome-devtools__take_screenshot({
+    //   fullPage: true,
+    //   format: "webp",
+    //   quality: 90,
+    //   filePath: f"{base_path}/screenshots/{entry.target}.webp"
+    // })
+
+ELSE IF tool == "playwright":
+  FOR entry IN url_entries:
+    mcp__playwright__screenshot({
+      url: entry.url,
+      output_path: f"{base_path}/screenshots/{entry.target}.png",
+      full_page: true,
+      timeout: 30000
+    })
+```
+
+### Step 2: Local Fallback (If MCP Failed)
+```bash
+# Try Playwright CLI
+bash(playwright screenshot "$url" "$output_file" --full-page --timeout 30000)
+
+# Try Chrome headless
+bash($chrome --headless --screenshot="$output_file" --window-size=1920,1080 "$url")
+```
+
+### Step 3: Manual Mode (If All Failed)
+```
+⚠️ Manual Screenshot Required
+
+Failed URLs:
+  home: https://linear.app
+  Save to: .workflow/.design/run-20250110/screenshots/home.png
+
+Steps:
+  1. Visit URL in browser
+  2. Take full-page screenshot
+  3. Save to path above
+  4. Type 'ready' to continue
+
+Options: ready | skip | abort
+```
+
+## Phase 4: Verification
+
+### Step 1: Scan Captured Files
+```bash
+bash(ls -1 $base_path/screenshots/*.{png,jpg,jpeg,webp} 2>/dev/null)
+bash(du -h $base_path/screenshots/*.png 2>/dev/null)
+```
+
+### Step 2: Generate Metadata
+```javascript
+captured_files = Glob(f"{base_path}/screenshots/*.{{png,jpg,jpeg,webp}}")
+captured_targets = [basename_no_ext(f) for f in captured_files]
+
+metadata = {
+  "timestamp": current_timestamp(),
+  "total_requested": len(url_entries),
+  "total_captured": len(captured_targets),
+  "screenshots": []
+}
+
+FOR entry IN url_entries:
+  is_captured = entry.target IN captured_targets
+
+  metadata.screenshots.append({
+    "target": entry.target,
+    "url": entry.url,
+    "captured": is_captured,
+    "path": f"{base_path}/screenshots/{entry.target}.png" IF is_captured ELSE null,
+    "size_kb": file_size_kb IF is_captured ELSE null
+  })
+
+Write(f"{base_path}/screenshots/capture-metadata.json", JSON.stringify(metadata))
+```
+
+**Output**: `capture-metadata.json`
+
+## Completion
+
+### Todo Update
+```javascript
+TodoWrite({todos: [
+  {content: "Parse url-map", status: "completed", activeForm: "Parsing"},
+  {content: "Detect MCP tools", status: "completed", activeForm: "Detecting"},
+  {content: "Capture screenshots", status: "completed", activeForm: "Capturing"},
+  {content: "Verify results", status: "completed", activeForm: "Verifying"}
+]})
+```
+
+### Output Message
+```
+✅ Batch screenshot capture complete!
+
+Summary:
+- Requested: {total_requested}
+- Captured: {total_captured}
+- Success rate: {success_rate}%
+- Method: {tool || "Local fallback"}
+
+Output:
+{base_path}/screenshots/
+├── home.png (245.3 KB)
+├── pricing.png (198.7 KB)
+└── capture-metadata.json
+
+Next: /workflow:ui-design:extract --images "screenshots/*.png"
+```
+
+## Simple Bash Commands
+
+### Path Operations
+```bash
+# Find design directory
+bash(find .workflow -type d -name "design-*" | head -1)
+
+# Create screenshot directory
+bash(mkdir -p $BASE_PATH/screenshots)
+```
+
+### Tool Detection
+```bash
+# Check MCP
+all_resources = ListMcpResourcesTool()
+
+# Check local tools
+bash(which playwright 2>/dev/null)
+bash(which google-chrome 2>/dev/null)
+```
+
+### Verification
+```bash
+# List captures
+bash(ls -1 $base_path/screenshots/*.png 2>/dev/null)
+
+# File sizes
+bash(du -h $base_path/screenshots/*.png)
+```
+
+## Output Structure
+
+```
+{base_path}/
+└── screenshots/
+    ├── home.png
+    ├── pricing.png
+    ├── about.png
+    └── capture-metadata.json
+```
+
+## Error Handling
+
+### Common Errors
+```
+ERROR: Invalid url-map format
+→ Use: "target:url, target2:url2"
+
+ERROR: png screenshots do not support 'quality'
+→ PNG format is lossless, no quality parameter needed
+→ Remove quality parameter OR switch to webp/jpeg format
+
+ERROR: MCP unavailable
+→ Using local fallback
+
+ERROR: All tools failed
+→ Manual mode activated
+```
+
+### Format-Specific Errors
+```
+❌ Wrong: format: "png", quality: 90
+✅ Right: format: "png"
+
+✅ Or use: format: "webp", quality: 90
+✅ Or use: format: "jpeg", quality: 90
+```
+
+### Recovery
+- **Partial success**: Keep successful captures
+- **Retry**: Re-run with failed targets only
+- **Manual**: Follow interactive guidance
+
+## Quality Checklist
+
+- [ ] All requested URLs processed
+- [ ] File sizes > 1KB (valid images)
+- [ ] Metadata JSON generated
+- [ ] No missing targets (or documented)
+
+## Key Features
+
+- **MCP-first**: Prioritize managed tools
+- **Multi-tier fallback**: 4 layers (MCP → Local → Manual)
+- **Batch processing**: Parallel capture
+- **Error tolerance**: Partial failures handled
+- **Structured output**: Flat, predictable
+
+## Integration
+
+**Input**: `--url-map` (multiple target:url pairs)
+**Output**: `screenshots/*.png` + `capture-metadata.json`
+**Called by**: `/workflow:ui-design:imitate-auto`, `/workflow:ui-design:explore-auto`
+**Next**: `/workflow:ui-design:extract` or `/workflow:ui-design:explore-layers`

.claude/commands/workflow/ui-design/consolidate.md

@@ -0,0 +1,267 @@
+---
+name: consolidate
+description: Consolidate style variants into independent design systems and plan layout strategies
+argument-hint: /workflow:ui-design:consolidate [--base-path <path>] [--session <id>] [--variants <count>] [--layout-variants <count>]
+allowed-tools: TodoWrite(*), Read(*), Write(*), Bash(*), Task(*)
+---
+
+# Design System Consolidation Command
+
+## Overview
+Consolidate style variants into independent production-ready design systems. Refines raw token proposals from `style-extract` into finalized design tokens and style guides.
+
+**Strategy**: Philosophy-Driven Refinement
+- **Agent-Driven**: Uses ui-design-agent for N variant generation
+- **Token Refinement**: Transforms proposed_tokens into complete systems
+- **Production-Ready**: design-tokens.json + style-guide.md per variant
+- **Matrix-Ready**: Provides style variants for generate phase
+
+## Phase 1: Setup & Validation
+
+### Step 1: Resolve Base Path & Load Style Cards
+```bash
+# Determine base path
+bash(find .workflow -type d -name "design-*" | head -1)  # Auto-detect
+# OR use --base-path / --session parameters
+
+# Load style cards
+bash(cat {base_path}/style-extraction/style-cards.json)
+```
+
+### Step 2: Memory Check (Skip if Already Done)
+```bash
+# Check if already consolidated
+bash(test -f {base_path}/style-consolidation/style-1/design-tokens.json && echo "exists")
+```
+
+**If exists**: Skip to completion message
+
+### Step 3: Select Variants
+```bash
+# Determine variant count (default: all from style-cards.json)
+bash(cat style-cards.json | grep -c "\"id\": \"variant-")
+
+# Validate variant count
+# Priority: --variants parameter → total_variants from style-cards.json
+```
+
+**Output**: `variants_count`, `selected_variants[]`
+
+### Step 4: Load Design Context (Optional)
+```bash
+# Load brainstorming context
+bash(test -f {base_path}/.brainstorming/synthesis-specification.md && cat it)
+
+# Load design space analysis
+bash(test -f {base_path}/style-extraction/design-space-analysis.json && cat it)
+```
+
+**Output**: `design_context`, `design_space_analysis`
+
+## Phase 2: Design System Synthesis (Agent)
+
+**Executor**: `Task(ui-design-agent)` for all variants
+
+### Step 1: Create Output Directories
+```bash
+bash(mkdir -p {base_path}/style-consolidation/style-{{1..{variants_count}}})
+```
+
+### Step 2: Launch Agent Task
+For all variants (1 to {variants_count}):
+```javascript
+Task(ui-design-agent): `
+  [DESIGN_TOKEN_GENERATION_TASK]
+  Generate {variants_count} independent design systems using philosophy-driven refinement
+
+  SESSION: {session_id} | MODE: Philosophy-driven refinement | BASE_PATH: {base_path}
+
+  CRITICAL PATH: Use loop index (N) for directories: style-1/, style-2/, ..., style-N/
+
+  VARIANT DATA:
+  {FOR each variant with index N:
+    VARIANT INDEX: {N} | ID: {variant.id} | NAME: {variant.name}
+    Design Philosophy: {variant.design_philosophy}
+    Proposed Tokens: {variant.proposed_tokens}
+    {IF design_space_analysis: Design Attributes: {attributes}, Anti-keywords: {anti_keywords}}
+  }
+
+  ## 参考
+  - Style cards: Each variant's proposed_tokens and design_philosophy
+  - Design space analysis: design_attributes (saturation, weight, formality, organic/geometric, innovation, density)
+  - Anti-keywords: Explicit constraints to avoid
+  - WCAG AA: 4.5:1 text, 3:1 UI (use built-in AI knowledge)
+
+  ## 生成
+  For EACH variant (use loop index N for paths):
+  1. {base_path}/style-consolidation/style-{N}/design-tokens.json
+     - Complete token structure: colors, typography, spacing, border_radius, shadows, breakpoints
+     - All colors in OKLCH format
+     - Apply design_attributes to token values (saturation→chroma, density→spacing, etc.)
+
+  2. {base_path}/style-consolidation/style-{N}/style-guide.md
+     - Expanded design philosophy
+     - Complete color system with accessibility notes
+     - Typography documentation
+     - Usage guidelines
+
+  ## 注意
+  - ✅ Use Write() tool immediately for each file
+  - ✅ Use loop index N for directory names: style-1/, style-2/, etc.
+  - ❌ DO NOT use variant.id in paths (metadata only)
+  - ❌ NO external research or MCP calls (pure AI refinement)
+  - Apply philosophy-driven refinement: design_attributes guide token values
+  - Maintain divergence: Use anti_keywords to prevent variant convergence
+  - Complete each variant's files before moving to next variant
+`
+```
+
+**Output**: Agent generates `variants_count × 2` files
+
+## Phase 3: Verify Output
+
+### Step 1: Check Files Created
+```bash
+# Verify all design systems created
+bash(ls {base_path}/style-consolidation/style-*/design-tokens.json | wc -l)
+
+# Validate structure
+bash(cat {base_path}/style-consolidation/style-1/design-tokens.json | grep -q "colors" && echo "valid")
+```
+
+### Step 2: Verify File Sizes
+```bash
+bash(ls -lh {base_path}/style-consolidation/style-1/)
+```
+
+**Output**: `variants_count × 2` files verified
+
+## Completion
+
+### Todo Update
+```javascript
+TodoWrite({todos: [
+  {content: "Setup and load style cards", status: "completed", activeForm: "Loading style cards"},
+  {content: "Select variants and load context", status: "completed", activeForm: "Loading context"},
+  {content: "Generate design systems (agent)", status: "completed", activeForm: "Generating systems"},
+  {content: "Verify output files", status: "completed", activeForm: "Verifying files"}
+]});
+```
+
+### Output Message
+```
+✅ Design system consolidation complete!
+
+Configuration:
+- Session: {session_id}
+- Variants: {variants_count}
+- Philosophy-driven refinement (zero MCP calls)
+
+Generated Files:
+{base_path}/style-consolidation/
+├── style-1/ (design-tokens.json, style-guide.md)
+├── style-2/ (same structure)
+└── style-{variants_count}/ (same structure)
+
+Next: /workflow:ui-design:generate --session {session_id} --style-variants {variants_count} --targets "dashboard,auth"
+```
+
+## Simple Bash Commands
+
+### Path Operations
+```bash
+# Find design directory
+bash(find .workflow -type d -name "design-*" | head -1)
+
+# Load style cards
+bash(cat {base_path}/style-extraction/style-cards.json)
+
+# Count variants
+bash(cat style-cards.json | grep -c "\"id\": \"variant-")
+```
+
+### Validation Commands
+```bash
+# Check if already consolidated
+bash(test -f {base_path}/style-consolidation/style-1/design-tokens.json && echo "exists")
+
+# Verify output
+bash(ls {base_path}/style-consolidation/style-*/design-tokens.json | wc -l)
+
+# Validate structure
+bash(cat design-tokens.json | grep -q "colors" && echo "valid")
+```
+
+### File Operations
+```bash
+# Create directories
+bash(mkdir -p {base_path}/style-consolidation/style-{{1..3}})
+
+# Check file sizes
+bash(ls -lh {base_path}/style-consolidation/style-1/)
+```
+
+## Output Structure
+
+```
+{base_path}/
+└── style-consolidation/
+    ├── style-1/
+    │   ├── design-tokens.json
+    │   └── style-guide.md
+    ├── style-2/
+    │   ├── design-tokens.json
+    │   └── style-guide.md
+    └── style-N/ (same structure)
+```
+
+## design-tokens.json Format
+
+```json
+{
+  "colors": {
+    "brand": {"primary": "oklch(...)", "secondary": "oklch(...)", "accent": "oklch(...)"},
+    "surface": {"background": "oklch(...)", "elevated": "oklch(...)", "overlay": "oklch(...)"},
+    "semantic": {"success": "oklch(...)", "warning": "oklch(...)", "error": "oklch(...)", "info": "oklch(...)"},
+    "text": {"primary": "oklch(...)", "secondary": "oklch(...)", "tertiary": "oklch(...)", "inverse": "oklch(...)"},
+    "border": {"default": "oklch(...)", "strong": "oklch(...)", "subtle": "oklch(...)"}
+  },
+  "typography": {"font_family": {...}, "font_size": {...}, "font_weight": {...}, "line_height": {...}, "letter_spacing": {...}},
+  "spacing": {"0": "0", "1": "0.25rem", ..., "24": "6rem"},
+  "border_radius": {"none": "0", "sm": "0.25rem", ..., "full": "9999px"},
+  "shadows": {"sm": "...", "md": "...", "lg": "...", "xl": "..."},
+  "breakpoints": {"sm": "640px", ..., "2xl": "1536px"}
+}
+```
+
+**Requirements**: OKLCH colors, complete coverage, semantic naming
+
+## Error Handling
+
+### Common Errors
+```
+ERROR: No style cards found
+→ Run /workflow:ui-design:style-extract first
+
+ERROR: Invalid variant count
+→ List available count, auto-select all
+
+ERROR: Agent file creation failed
+→ Check agent output, verify Write() operations
+```
+
+## Key Features
+
+- **Philosophy-Driven Refinement** - Pure AI token refinement using design_attributes
+- **Agent-Driven** - Uses ui-design-agent for multi-file generation
+- **Separate Design Systems** - N independent systems (one per variant)
+- **Production-Ready** - WCAG AA compliant, OKLCH colors, semantic naming
+- **Zero MCP Calls** - Faster execution, better divergence preservation
+
+## Integration
+
+**Input**: `style-cards.json` from `/workflow:ui-design:style-extract`
+**Output**: `style-consolidation/style-{N}/` for each variant
+**Next**: `/workflow:ui-design:generate --style-variants N`
+
+**Note**: After consolidate, use `/workflow:ui-design:layout-extract` to generate layout templates before running generate.

.claude/commands/workflow/ui-design/explore-auto.md

@@ -0,0 +1,489 @@
+---
+name: explore-auto
+description: Exploratory UI design workflow with style-centric batch generation
+argument-hint: "[--prompt "<desc>"] [--images "<glob>"] [--targets "<list>"] [--target-type "page|component"] [--session <id>] [--style-variants <count>] [--layout-variants <count>] [--batch-plan]""
+allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*), Glob(*), Write(*), Task(conceptual-planning-agent)
+---
+
+# UI Design Auto Workflow Command
+
+## Overview & Execution Model
+
+**Fully autonomous orchestrator**: Executes all design phases sequentially from style extraction to design integration, with optional batch planning.
+
+**Unified Target System**: Generates `style_variants × layout_variants × targets` prototypes, where targets can be:
+- **Pages** (full-page layouts): home, dashboard, settings, etc.
+- **Components** (isolated UI elements): navbar, card, hero, form, etc.
+- **Mixed**: Can combine both in a single workflow
+
+**Autonomous Flow** (⚠️ CONTINUOUS EXECUTION - DO NOT STOP):
+1. User triggers: `/workflow:ui-design:explore-auto [params]`
+2. Phase 0c: Target confirmation → User confirms → **IMMEDIATELY triggers Phase 1**
+3. Phase 1 (style-extract) → **WAIT for completion** → Auto-continues
+4. Phase 2 (style-consolidate) → **WAIT for completion** → Auto-continues
+5. Phase 2.5 (layout-extract) → **WAIT for completion** → Auto-continues
+6. **Phase 3 (ui-assembly)** → **WAIT for completion** → Auto-continues
+7. Phase 4 (design-update) → **WAIT for completion** → Auto-continues
+8. Phase 5 (batch-plan, optional) → Reports completion
+
+**Phase Transition Mechanism**:
+- **Phase 0c (User Interaction)**: User confirms targets → IMMEDIATELY triggers Phase 1
+- **Phase 1-5 (Autonomous)**: `SlashCommand` is BLOCKING - execution pauses until completion
+- Upon each phase completion: Automatically process output and execute next phase
+- No additional user interaction after Phase 0c confirmation
+
+**Auto-Continue Mechanism**: TodoWrite tracks phase status. Upon each phase completion, you MUST immediately construct and execute the next phase command. No user intervention required. The workflow is NOT complete until reaching Phase 4 (or Phase 5 if --batch-plan).
+
+**Target Type Detection**: Automatically inferred from prompt/targets, or explicitly set via `--target-type`.
+
+## Core Rules
+
+1. **Start Immediately**: TodoWrite initialization → Phase 1 execution
+2. **No Preliminary Validation**: Sub-commands handle their own validation
+3. **Parse & Pass**: Extract data from each output for next phase
+4. **Default to All**: When selecting variants/prototypes, use ALL generated items
+5. **Track Progress**: Update TodoWrite after each phase
+6. **⚠️ CRITICAL: DO NOT STOP** - This is a continuous multi-phase workflow. After each SlashCommand completes, you MUST wait for completion, then immediately execute the next phase. Workflow is NOT complete until Phase 4 (or Phase 5 if --batch-plan).
+
+## Parameter Requirements
+
+**Optional Parameters** (all have smart defaults):
+- `--targets "<list>"`: Comma-separated targets (pages/components) to generate (inferred from prompt/session if omitted)
+- `--target-type "page|component|auto"`: Explicitly set target type (default: `auto` - intelligent detection)
+- `--device-type "desktop|mobile|tablet|responsive|auto"`: Device type for layout optimization (default: `auto` - intelligent detection)
+  - **Desktop**: 1920×1080px - Mouse-driven, spacious layouts
+  - **Mobile**: 375×812px - Touch-friendly, compact layouts
+  - **Tablet**: 768×1024px - Hybrid touch/mouse layouts
+  - **Responsive**: 1920×1080px base with mobile-first breakpoints
+- `--session <id>`: Workflow session ID (standalone mode if omitted)
+- `--images "<glob>"`: Reference image paths (default: `design-refs/*`)
+- `--prompt "<description>"`: Design style and target description
+- `--style-variants <count>`: Style variants (default: inferred from prompt or 3, range: 1-5)
+- `--layout-variants <count>`: Layout variants per style (default: inferred or 3, range: 1-5)
+- `--batch-plan`: Auto-generate implementation tasks after design-update
+
+**Legacy Parameters** (maintained for backward compatibility):
+- `--pages "<list>"`: Alias for `--targets` with `--target-type page`
+- `--components "<list>"`: Alias for `--targets` with `--target-type component`
+
+**Input Rules**:
+- Must provide at least one: `--images` or `--prompt` or `--targets`
+- Multiple parameters can be combined for guided analysis
+- If `--targets` not provided, intelligently inferred from prompt/session
+
+**Supported Target Types**:
+- **Pages** (full layouts): home, dashboard, settings, profile, login, etc.
+- **Components** (UI elements):
+  - Navigation: navbar, header, menu, breadcrumb, tabs, sidebar
+  - Content: hero, card, list, table, grid, timeline
+  - Input: form, search, filter, input-group
+  - Feedback: modal, alert, toast, badge, progress
+  - Media: gallery, carousel, video-player, image-card
+  - Other: footer, pagination, dropdown, tooltip, avatar
+
+**Intelligent Prompt Parsing**: Extracts variant counts from natural language:
+- "Generate **3 style variants**" → `--style-variants 3`
+- "**2 layout options**" → `--layout-variants 2`
+- "Create **4 styles** with **2 layouts each**" → `--style-variants 4 --layout-variants 2`
+- Explicit flags override prompt inference
+
+## Execution Modes
+
+**Matrix Mode** (style-centric):
+- Generates `style_variants × layout_variants × targets` prototypes
+- **Phase 1**: `style_variants` style options with design_attributes (extract)
+- **Phase 2**: `style_variants` independent design systems (consolidate)
+- **Phase 3**: Style-centric batch generation (generate)
+  - Sub-phase 1: `targets × layout_variants` target-specific layout plans
+  - **Sub-phase 2**: `S` style-centric agents (each handles `L×T` combinations)
+  - Sub-phase 3: `style_variants × layout_variants × targets` final prototypes
+  - Performance: Efficient parallel execution with S agents
+  - Quality: HTML structure adapts to design_attributes
+  - Pages: Full-page layouts with complete structure
+  - Components: Isolated elements with minimal wrapper
+
+**Integrated vs. Standalone**:
+- `--session` flag determines session integration or standalone execution
+
+## 6-Phase Execution
+
+### Phase 0a: Intelligent Prompt Parsing
+```bash
+# Parse variant counts from prompt or use explicit/default values
+IF --prompt AND (NOT --style-variants OR NOT --layout-variants):
+    style_variants = regex_extract(prompt, r"(\d+)\s*style") OR --style-variants OR 3
+    layout_variants = regex_extract(prompt, r"(\d+)\s*layout") OR --layout-variants OR 3
+ELSE:
+    style_variants = --style-variants OR 3
+    layout_variants = --layout-variants OR 3
+
+VALIDATE: 1 <= style_variants <= 5, 1 <= layout_variants <= 5
+```
+
+### Phase 0a-2: Device Type Inference
+```bash
+# Device type inference
+device_type = "auto"
+
+# Step 1: Explicit parameter (highest priority)
+IF --device-type AND --device-type != "auto":
+    device_type = --device-type
+    device_source = "explicit"
+ELSE:
+    # Step 2: Prompt analysis
+    IF --prompt:
+        device_keywords = {
+            "desktop": ["desktop", "web", "laptop", "widescreen", "large screen"],
+            "mobile": ["mobile", "phone", "smartphone", "ios", "android"],
+            "tablet": ["tablet", "ipad", "medium screen"],
+            "responsive": ["responsive", "adaptive", "multi-device", "cross-platform"]
+        }
+        detected_device = detect_device_from_prompt(--prompt, device_keywords)
+        IF detected_device:
+            device_type = detected_device
+            device_source = "prompt_inference"
+
+    # Step 3: Target type inference
+    IF device_type == "auto":
+        # Components are typically desktop-first, pages can vary
+        device_type = target_type == "component" ? "desktop" : "responsive"
+        device_source = "target_type_inference"
+
+STORE: device_type, device_source
+```
+
+**Device Type Presets**:
+- **Desktop**: 1920×1080px - Mouse-driven, spacious layouts
+- **Mobile**: 375×812px - Touch-friendly, compact layouts
+- **Tablet**: 768×1024px - Hybrid touch/mouse layouts
+- **Responsive**: 1920×1080px base with mobile-first breakpoints
+
+**Detection Keywords**:
+- Prompt contains "mobile", "phone", "smartphone" → mobile
+- Prompt contains "tablet", "ipad" → tablet
+- Prompt contains "desktop", "web", "laptop" → desktop
+- Prompt contains "responsive", "adaptive" → responsive
+- Otherwise: Inferred from target type (components→desktop, pages→responsive)
+
+### Phase 0b: Run Initialization & Directory Setup
+```bash
+run_id = "run-$(date +%Y%m%d-%H%M%S)"
+base_path = --session ? ".workflow/WFS-{session}/design-${run_id}" : ".workflow/.design/${run_id}"
+
+Bash(mkdir -p "${base_path}/{style-extraction,style-consolidation,prototypes}")
+
+Write({base_path}/.run-metadata.json): {
+  "run_id": "${run_id}", "session_id": "${session_id}", "timestamp": "...",
+  "workflow": "ui-design:auto",
+  "architecture": "style-centric-batch-generation",
+  "parameters": { "style_variants": ${style_variants}, "layout_variants": ${layout_variants},
+                  "targets": "${inferred_target_list}", "target_type": "${target_type}",
+                  "prompt": "${prompt_text}", "images": "${images_pattern}",
+                  "device_type": "${device_type}", "device_source": "${device_source}" },
+  "status": "in_progress",
+  "performance_mode": "optimized"
+}
+```
+
+### Phase 0c: Unified Target Inference with Intelligent Type Detection
+```bash
+# Priority: --pages/--components (legacy) → --targets → --prompt analysis → synthesis → default
+target_list = []; target_type = "auto"; target_source = "none"
+
+# Step 1-2: Explicit parameters (legacy or unified)
+IF --pages: target_list = split(--pages); target_type = "page"; target_source = "explicit_legacy"
+ELSE IF --components: target_list = split(--components); target_type = "component"; target_source = "explicit_legacy"
+ELSE IF --targets:
+    target_list = split(--targets); target_source = "explicit"
+    target_type = --target-type != "auto" ? --target-type : detect_target_type(target_list)
+
+# Step 3: Prompt analysis (Claude internal analysis)
+ELSE IF --prompt:
+    analysis_result = analyze_prompt("{prompt_text}")  # Extract targets, types, purpose
+    target_list = analysis_result.targets
+    target_type = analysis_result.primary_type OR detect_target_type(target_list)
+    target_source = "prompt_analysis"
+
+# Step 4: Session synthesis
+ELSE IF --session AND exists(synthesis-specification.md):
+    target_list = extract_targets_from_synthesis(); target_type = "page"; target_source = "synthesis"
+
+# Step 5: Fallback
+IF NOT target_list: target_list = ["home"]; target_type = "page"; target_source = "default"
+
+# Validate and clean
+validated_targets = [normalize(t) for t in target_list if is_valid(t)]
+IF NOT validated_targets: validated_targets = ["home"]; target_type = "page"
+IF --target-type != "auto": target_type = --target-type
+
+# Interactive confirmation
+DISPLAY_CONFIRMATION(target_type, target_source, validated_targets, device_type, device_source):
+  "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+  "{emoji} {LABEL} CONFIRMATION (Style-Centric)"
+  "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+  "Type: {target_type} | Source: {target_source}"
+  "Targets ({count}): {', '.join(validated_targets)}"
+  "Device: {device_type} | Source: {device_source}"
+  "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+  "Performance: {style_variants} agent calls"
+  "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+  "Modification Options:"
+  "  • 'continue/yes/ok' - Proceed with current configuration"
+  "  • 'targets: a,b,c' - Replace target list"
+  "  • 'skip: x,y' - Remove specific targets"
+  "  • 'add: z' - Add new targets"
+  "  • 'type: page|component' - Change target type"
+  "  • 'device: desktop|mobile|tablet|responsive' - Change device type"
+  "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+
+user_input = WAIT_FOR_USER_INPUT()
+
+# Process user modifications
+MATCH user_input:
+  "continue|yes|ok" → proceed
+  "targets: ..." → validated_targets = parse_new_list()
+  "skip: ..." → validated_targets = remove_items()
+  "add: ..." → validated_targets = add_items()
+  "type: ..." → target_type = extract_type()
+  "device: ..." → device_type = extract_device()
+  default → proceed with current list
+
+STORE: inferred_target_list, target_type, target_inference_source
+
+# ⚠️ CRITICAL: User confirmation complete, IMMEDIATELY initialize TodoWrite and execute Phase 1
+# This is the only user interaction point in the workflow
+# After this point, all subsequent phases execute automatically without user intervention
+```
+
+**Helper Function: detect_target_type()**
+```bash
+detect_target_type(target_list):
+    page_keywords = ["home", "dashboard", "settings", "profile", "login", "signup", "auth", ...]
+    component_keywords = ["navbar", "header", "footer", "hero", "card", "button", "form", ...]
+
+    page_matches = count_matches(target_list, page_keywords + ["page", "screen", "view"])
+    component_matches = count_matches(target_list, component_keywords + ["component", "widget"])
+
+    RETURN "component" IF component_matches > page_matches ELSE "page"
+```
+
+### Phase 1: Style Extraction
+```bash
+command = "/workflow:ui-design:style-extract --base-path \"{base_path}\" " +
+          (--images ? "--images \"{images}\" " : "") +
+          (--prompt ? "--prompt \"{prompt}\" " : "") +
+          "--mode explore --variants {style_variants}"
+SlashCommand(command)
+
+# Output: {style_variants} style cards with design_attributes
+# SlashCommand blocks until phase complete
+# Upon completion, IMMEDIATELY execute Phase 2 (auto-continue)
+```
+
+### Phase 2: Style Consolidation
+```bash
+command = "/workflow:ui-design:consolidate --base-path \"{base_path}\" " +
+          "--variants {style_variants}"
+SlashCommand(command)
+
+# Output: {style_variants} independent design systems with tokens.css
+# SlashCommand blocks until phase complete
+# Upon completion, IMMEDIATELY execute Phase 2.5 (auto-continue)
+```
+
+### Phase 2.5: Layout Extraction
+```bash
+targets_string = ",".join(inferred_target_list)
+command = "/workflow:ui-design:layout-extract --base-path \"{base_path}\" " +
+          (--images ? "--images \"{images}\" " : "") +
+          (--prompt ? "--prompt \"{prompt}\" " : "") +
+          "--targets \"{targets_string}\" " +
+          "--mode explore --variants {layout_variants} " +
+          "--device-type \"{device_type}\""
+
+REPORT: "🚀 Phase 2.5: Layout Extraction (explore mode)"
+REPORT: "   → Targets: {targets_string}"
+REPORT: "   → Layout variants: {layout_variants}"
+REPORT: "   → Device: {device_type}"
+
+SlashCommand(command)
+
+# Output: layout-templates.json with {targets × layout_variants} layout structures
+# SlashCommand blocks until phase complete
+# Upon completion, IMMEDIATELY execute Phase 3 (auto-continue)
+```
+
+### Phase 3: UI Assembly
+```bash
+command = "/workflow:ui-design:generate --base-path \"{base_path}\" " +
+          "--style-variants {style_variants} --layout-variants {layout_variants}"
+
+total = style_variants × layout_variants × len(inferred_target_list)
+
+REPORT: "🚀 Phase 3: UI Assembly | Matrix: {s}×{l}×{n} = {total} prototypes"
+REPORT: "   → Pure assembly: Combining layout templates + design tokens"
+REPORT: "   → Device: {device_type} (from layout templates)"
+REPORT: "   → Assembly tasks: {total} combinations"
+
+SlashCommand(command)
+
+# SlashCommand blocks until phase complete
+# Upon completion, IMMEDIATELY execute Phase 4 (auto-continue)
+# Output:
+# - {target}-style-{s}-layout-{l}.html (assembled prototypes)
+# - {target}-style-{s}-layout-{l}.css
+# - compare.html (interactive matrix view)
+# - PREVIEW.md (usage instructions)
+```
+
+### Phase 4: Design System Integration
+```bash
+command = "/workflow:ui-design:update" + (--session ? " --session {session_id}" : "")
+SlashCommand(command)
+
+# SlashCommand blocks until phase complete
+# Upon completion:
+#   - If --batch-plan flag present: IMMEDIATELY execute Phase 5 (auto-continue)
+#   - If no --batch-plan: Workflow complete, display final report
+```
+
+### Phase 5: Batch Task Generation (Optional)
+```bash
+IF --batch-plan:
+    FOR target IN inferred_target_list:
+        task_desc = "Implement {target} {target_type} based on design system"
+        SlashCommand("/workflow:plan --agent \"{task_desc}\"")
+```
+
+## TodoWrite Pattern
+```javascript
+// Initialize IMMEDIATELY after Phase 0c user confirmation to track multi-phase execution
+TodoWrite({todos: [
+  {"content": "Execute style extraction", "status": "in_progress", "activeForm": "Executing..."},
+  {"content": "Execute style consolidation", "status": "pending", "activeForm": "Executing..."},
+  {"content": "Execute layout extraction", "status": "pending", "activeForm": "Executing..."},
+  {"content": "Execute UI assembly", "status": "pending", "activeForm": "Executing..."},
+  {"content": "Execute design integration", "status": "pending", "activeForm": "Executing..."}
+]})
+
+// ⚠️ CRITICAL: After EACH SlashCommand completion (Phase 1-5), you MUST:
+// 1. SlashCommand blocks and returns when phase is complete
+// 2. Update current phase: status → "completed"
+// 3. Update next phase: status → "in_progress"
+// 4. IMMEDIATELY execute next phase SlashCommand (auto-continue)
+// This ensures continuous workflow tracking and prevents premature stopping
+```
+
+## Key Features
+
+- **🚀 Performance**: Style-centric batch generation with S agent calls
+- **🎨 Style-Aware**: HTML structure adapts to design_attributes
+- **✅ Perfect Consistency**: Each style by single agent
+- **📦 Autonomous**: No user intervention required between phases
+- **🧠 Intelligent**: Parses natural language, infers targets/types
+- **🔄 Reproducible**: Deterministic flow with isolated run directories
+- **🎯 Flexible**: Supports pages, components, or mixed targets
+
+## Examples
+
+### 1. Page Mode (Prompt Inference)
+```bash
+/workflow:ui-design:explore-auto --prompt "Modern blog: home, article, author"
+# Result: 27 prototypes (3×3×3) - responsive layouts (default)
+```
+
+### 2. Mobile-First Design
+```bash
+/workflow:ui-design:explore-auto --prompt "Mobile shopping app: home, product, cart" --device-type mobile
+# Result: 27 prototypes (3×3×3) - mobile layouts (375×812px)
+```
+
+### 3. Desktop Application
+```bash
+/workflow:ui-design:explore-auto --targets "dashboard,analytics,settings" --device-type desktop --style-variants 2 --layout-variants 2
+# Result: 12 prototypes (2×2×3) - desktop layouts (1920×1080px)
+```
+
+### 4. Tablet Interface
+```bash
+/workflow:ui-design:explore-auto --prompt "Educational app for tablets" --device-type tablet --targets "courses,lessons,profile"
+# Result: 27 prototypes (3×3×3) - tablet layouts (768×1024px)
+```
+
+### 5. Custom Matrix with Session
+```bash
+/workflow:ui-design:explore-auto --session WFS-ecommerce --images "refs/*.png" --style-variants 2 --layout-variants 2
+# Result: 2×2×N prototypes - device type inferred from session
+```
+
+### 6. Component Mode (Desktop)
+```bash
+/workflow:ui-design:explore-auto --targets "navbar,hero" --target-type "component" --device-type desktop --style-variants 3 --layout-variants 2
+# Result: 12 prototypes (3×2×2) - desktop components
+```
+
+### 7. Intelligent Parsing + Batch Planning
+```bash
+/workflow:ui-design:explore-auto --prompt "Create 4 styles with 2 layouts for mobile dashboard and settings" --batch-plan
+# Result: 16 prototypes (4×2×2) + auto-generated tasks - mobile-optimized (inferred from prompt)
+```
+
+### 8. Large Scale Responsive
+```bash
+/workflow:ui-design:explore-auto --targets "home,dashboard,settings,profile" --device-type responsive --style-variants 3 --layout-variants 3
+# Result: 36 prototypes (3×3×4) - responsive layouts
+```
+
+## Completion Output
+```
+✅ UI Design Explore-Auto Workflow Complete!
+
+Architecture: Style-Centric Batch Generation
+Run ID: {run_id} | Session: {session_id or "standalone"}
+Type: {icon} {target_type} | Device: {device_type} | Matrix: {s}×{l}×{n} = {total} prototypes
+
+Phase 1: {s} style variants with design_attributes (style-extract)
+Phase 2: {s} design systems with tokens.css (consolidate)
+Phase 2.5: {n×l} layout templates (layout-extract explore mode)
+  - Device: {device_type} layouts
+  - {n} targets × {l} layout variants = {n×l} structural templates
+Phase 3: UI Assembly (generate)
+  - Pure assembly: layout templates + design tokens
+  - {s}×{l}×{n} = {total} final prototypes
+Phase 4: Brainstorming artifacts updated
+[Phase 5: {n} implementation tasks created]  # if --batch-plan
+
+Assembly Process:
+✅ Separation of Concerns: Layout (structure) + Style (tokens) kept separate
+✅ Layout Extraction: {n×l} reusable structural templates
+✅ Pure Assembly: No design decisions in generate phase
+✅ Device-Optimized: Layouts designed for {device_type}
+
+Design Quality:
+✅ Token-Driven Styling: 100% var() usage
+✅ Structural Variety: {l} distinct layouts per target
+✅ Style Variety: {s} independent design systems
+✅ Device-Optimized: Layouts designed for {device_type}
+
+📂 {base_path}/
+  ├── style-extraction/       ({s} style cards + design-space-analysis.json)
+  ├── style-consolidation/    ({s} design systems with tokens.css)
+  ├── layout-extraction/      ({n×l} layout templates + layout-space-analysis.json)
+  ├── prototypes/             ({total} assembled prototypes)
+  └── .run-metadata.json      (includes device type)
+
+🌐 Preview: {base_path}/prototypes/compare.html
+  - Interactive {s}×{l} matrix view
+  - Side-by-side comparison
+  - Target-specific layouts with style-aware structure
+  - Toggle between {n} targets
+
+{icon} Targets: {', '.join(targets)} (type: {target_type})
+  - Each target has {l} custom-designed layouts
+  - Each style × target × layout has unique HTML structure (not just CSS!)
+  - Layout plans stored as structured JSON
+  - Optimized for {device_type} viewing
+
+Next: [/workflow:execute] OR [Open compare.html → Select → /workflow:plan]
+```
+

.claude/commands/workflow/ui-design/explore-layers.md

@@ -0,0 +1,589 @@
+---
+name: explore-layers
+description: Interactive deep UI capture with depth-controlled layer exploration
+argument-hint: --url <url> --depth <1-5> [--session id] [--base-path path]
+allowed-tools: TodoWrite(*), Read(*), Write(*), Bash(*), Glob(*), mcp__chrome-devtools__*
+---
+
+# Interactive Layer Exploration (/workflow:ui-design:explore-layers)
+
+## Overview
+Single-URL depth-controlled interactive capture. Progressively explores UI layers from pages to Shadow DOM.
+
+**Depth Levels**:
+- `1` = Page (full-page screenshot)
+- `2` = Elements (key components)
+- `3` = Interactions (modals, dropdowns)
+- `4` = Embedded (iframes, widgets)
+- `5` = Shadow DOM (web components)
+
+**Requirements**: Chrome DevTools MCP
+
+## Phase 1: Setup & Validation
+
+### Step 1: Parse Parameters
+```javascript
+url = params["--url"]
+depth = int(params["--depth"])
+
+// Validate URL
+IF NOT url.startswith("http"):
+  url = f"https://{url}"
+
+// Validate depth
+IF depth NOT IN [1, 2, 3, 4, 5]:
+  ERROR: "Invalid depth: {depth}. Use 1-5"
+  EXIT 1
+```
+
+### Step 2: Determine Base Path
+```bash
+bash(if [ -n "$BASE_PATH" ]; then
+  echo "$BASE_PATH"
+elif [ -n "$SESSION_ID" ]; then
+  find .workflow/WFS-$SESSION_ID/design-* -type d | head -1 || \
+  echo ".workflow/WFS-$SESSION_ID/design-layers-$(date +%Y%m%d-%H%M%S)"
+else
+  echo ".workflow/.design/layers-$(date +%Y%m%d-%H%M%S)"
+fi)
+
+# Create depth directories
+bash(for i in $(seq 1 $depth); do mkdir -p $BASE_PATH/screenshots/depth-$i; done)
+```
+
+**Output**: `url`, `depth`, `base_path`
+
+### Step 3: Validate MCP Availability
+```javascript
+all_resources = ListMcpResourcesTool()
+chrome_devtools = "chrome-devtools" IN [r.server for r in all_resources]
+
+IF NOT chrome_devtools:
+  ERROR: "explore-layers requires Chrome DevTools MCP"
+  ERROR: "Install: npm i -g @modelcontextprotocol/server-chrome-devtools"
+  EXIT 1
+```
+
+### Step 4: Initialize Todos
+```javascript
+todos = [
+  {content: "Setup and validation", status: "completed", activeForm: "Setting up"}
+]
+
+FOR level IN range(1, depth + 1):
+  todos.append({
+    content: f"Depth {level}: {DEPTH_NAMES[level]}",
+    status: "pending",
+    activeForm: f"Capturing depth {level}"
+  })
+
+todos.append({content: "Generate layer map", status: "pending", activeForm: "Mapping"})
+
+TodoWrite({todos})
+```
+
+## Phase 2: Navigate & Load Page
+
+### Step 1: Get or Create Browser Page
+```javascript
+pages = mcp__chrome-devtools__list_pages()
+
+IF pages.length == 0:
+  mcp__chrome-devtools__new_page({url: url, timeout: 30000})
+  page_idx = 0
+ELSE:
+  page_idx = 0
+  mcp__chrome-devtools__select_page({pageIdx: page_idx})
+  mcp__chrome-devtools__navigate_page({url: url, timeout: 30000})
+
+bash(sleep 3)  // Wait for page load
+```
+
+**Output**: `page_idx`
+
+## Phase 3: Depth 1 - Page Level
+
+### Step 1: Capture Full Page
+```javascript
+TodoWrite(mark_in_progress: "Depth 1: Page")
+
+output_file = f"{base_path}/screenshots/depth-1/full-page.png"
+
+mcp__chrome-devtools__take_screenshot({
+  fullPage: true,
+  format: "png",
+  quality: 90,
+  filePath: output_file
+})
+
+layer_map = {
+  "url": url,
+  "depth": depth,
+  "layers": {
+    "depth-1": {
+      "type": "page",
+      "captures": [{
+        "name": "full-page",
+        "path": output_file,
+        "size_kb": file_size_kb(output_file)
+      }]
+    }
+  }
+}
+
+TodoWrite(mark_completed: "Depth 1: Page")
+```
+
+**Output**: `depth-1/full-page.png`
+
+## Phase 4: Depth 2 - Element Level (If depth >= 2)
+
+### Step 1: Analyze Page Structure
+```javascript
+IF depth < 2: SKIP
+
+TodoWrite(mark_in_progress: "Depth 2: Elements")
+
+snapshot = mcp__chrome-devtools__take_snapshot()
+
+// Filter key elements
+key_types = ["nav", "header", "footer", "aside", "button", "form", "article"]
+key_elements = [
+  el for el in snapshot.interactiveElements
+  if el.type IN key_types OR el.role IN ["navigation", "banner", "main"]
+][:10]  // Limit to top 10
+```
+
+### Step 2: Capture Element Screenshots
+```javascript
+depth_2_captures = []
+
+FOR idx, element IN enumerate(key_elements):
+  element_name = sanitize(element.text[:20] or element.type) or f"element-{idx}"
+  output_file = f"{base_path}/screenshots/depth-2/{element_name}.png"
+
+  TRY:
+    mcp__chrome-devtools__take_screenshot({
+      uid: element.uid,
+      format: "png",
+      quality: 85,
+      filePath: output_file
+    })
+
+    depth_2_captures.append({
+      "name": element_name,
+      "type": element.type,
+      "path": output_file,
+      "size_kb": file_size_kb(output_file)
+    })
+  CATCH error:
+    REPORT: f"Skip {element_name}: {error}"
+
+layer_map.layers["depth-2"] = {
+  "type": "elements",
+  "captures": depth_2_captures
+}
+
+TodoWrite(mark_completed: "Depth 2: Elements")
+```
+
+**Output**: `depth-2/{element}.png` × N
+
+## Phase 5: Depth 3 - Interaction Level (If depth >= 3)
+
+### Step 1: Analyze Interactive Triggers
+```javascript
+IF depth < 3: SKIP
+
+TodoWrite(mark_in_progress: "Depth 3: Interactions")
+
+// Detect structure
+structure = mcp__chrome-devtools__evaluate_script({
+  function: `() => ({
+    modals: document.querySelectorAll('[role="dialog"], .modal').length,
+    dropdowns: document.querySelectorAll('[role="menu"], .dropdown').length,
+    tooltips: document.querySelectorAll('[role="tooltip"], [title]').length
+  })`
+})
+
+// Identify triggers
+triggers = []
+FOR element IN snapshot.interactiveElements:
+  IF element.attributes CONTAINS ("data-toggle", "aria-haspopup"):
+    triggers.append({
+      uid: element.uid,
+      type: "modal" IF "modal" IN element.classes ELSE "dropdown",
+      trigger: "click",
+      text: element.text
+    })
+  ELSE IF element.attributes CONTAINS ("title", "data-tooltip"):
+    triggers.append({
+      uid: element.uid,
+      type: "tooltip",
+      trigger: "hover",
+      text: element.text
+    })
+
+triggers = triggers[:10]  // Limit
+```
+
+### Step 2: Trigger Interactions & Capture
+```javascript
+depth_3_captures = []
+
+FOR idx, trigger IN enumerate(triggers):
+  layer_name = f"{trigger.type}-{sanitize(trigger.text[:15]) or idx}"
+  output_file = f"{base_path}/screenshots/depth-3/{layer_name}.png"
+
+  TRY:
+    // Trigger interaction
+    IF trigger.trigger == "click":
+      mcp__chrome-devtools__click({uid: trigger.uid})
+    ELSE:
+      mcp__chrome-devtools__hover({uid: trigger.uid})
+
+    bash(sleep 1)
+
+    // Capture
+    mcp__chrome-devtools__take_screenshot({
+      fullPage: false,  // Viewport only
+      format: "png",
+      quality: 90,
+      filePath: output_file
+    })
+
+    depth_3_captures.append({
+      "name": layer_name,
+      "type": trigger.type,
+      "trigger_method": trigger.trigger,
+      "path": output_file,
+      "size_kb": file_size_kb(output_file)
+    })
+
+    // Dismiss (ESC key)
+    mcp__chrome-devtools__evaluate_script({
+      function: `() => {
+        document.dispatchEvent(new KeyboardEvent('keydown', {key: 'Escape'}));
+      }`
+    })
+    bash(sleep 0.5)
+
+  CATCH error:
+    REPORT: f"Skip {layer_name}: {error}"
+
+layer_map.layers["depth-3"] = {
+  "type": "interactions",
+  "triggers": structure,
+  "captures": depth_3_captures
+}
+
+TodoWrite(mark_completed: "Depth 3: Interactions")
+```
+
+**Output**: `depth-3/{interaction}.png` × N
+
+## Phase 6: Depth 4 - Embedded Level (If depth >= 4)
+
+### Step 1: Detect Iframes
+```javascript
+IF depth < 4: SKIP
+
+TodoWrite(mark_in_progress: "Depth 4: Embedded")
+
+iframes = mcp__chrome-devtools__evaluate_script({
+  function: `() => {
+    return Array.from(document.querySelectorAll('iframe')).map(iframe => ({
+      src: iframe.src,
+      id: iframe.id || 'iframe',
+      title: iframe.title || 'untitled'
+    })).filter(i => i.src && i.src.startsWith('http'));
+  }`
+})
+```
+
+### Step 2: Capture Iframe Content
+```javascript
+depth_4_captures = []
+
+FOR idx, iframe IN enumerate(iframes):
+  iframe_name = f"iframe-{sanitize(iframe.title or iframe.id)}-{idx}"
+  output_file = f"{base_path}/screenshots/depth-4/{iframe_name}.png"
+
+  TRY:
+    // Navigate to iframe URL in new tab
+    mcp__chrome-devtools__new_page({url: iframe.src, timeout: 30000})
+    bash(sleep 2)
+
+    mcp__chrome-devtools__take_screenshot({
+      fullPage: true,
+      format: "png",
+      quality: 90,
+      filePath: output_file
+    })
+
+    depth_4_captures.append({
+      "name": iframe_name,
+      "url": iframe.src,
+      "path": output_file,
+      "size_kb": file_size_kb(output_file)
+    })
+
+    // Close iframe tab
+    current_pages = mcp__chrome-devtools__list_pages()
+    mcp__chrome-devtools__close_page({pageIdx: current_pages.length - 1})
+
+  CATCH error:
+    REPORT: f"Skip {iframe_name}: {error}"
+
+layer_map.layers["depth-4"] = {
+  "type": "embedded",
+  "captures": depth_4_captures
+}
+
+TodoWrite(mark_completed: "Depth 4: Embedded")
+```
+
+**Output**: `depth-4/iframe-*.png` × N
+
+## Phase 7: Depth 5 - Shadow DOM (If depth = 5)
+
+### Step 1: Detect Shadow Roots
+```javascript
+IF depth < 5: SKIP
+
+TodoWrite(mark_in_progress: "Depth 5: Shadow DOM")
+
+shadow_elements = mcp__chrome-devtools__evaluate_script({
+  function: `() => {
+    const elements = Array.from(document.querySelectorAll('*'));
+    return elements
+      .filter(el => el.shadowRoot)
+      .map((el, idx) => ({
+        tag: el.tagName.toLowerCase(),
+        id: el.id || \`shadow-\${idx}\`,
+        innerHTML: el.shadowRoot.innerHTML.substring(0, 100)
+      }));
+  }`
+})
+```
+
+### Step 2: Capture Shadow DOM Components
+```javascript
+depth_5_captures = []
+
+FOR idx, shadow IN enumerate(shadow_elements):
+  shadow_name = f"shadow-{sanitize(shadow.id)}"
+  output_file = f"{base_path}/screenshots/depth-5/{shadow_name}.png"
+
+  TRY:
+    // Inject highlight script
+    mcp__chrome-devtools__evaluate_script({
+      function: `() => {
+        const el = document.querySelector('${shadow.tag}${shadow.id ? "#" + shadow.id : ""}');
+        if (el) {
+          el.scrollIntoView({behavior: 'smooth', block: 'center'});
+          el.style.outline = '3px solid red';
+        }
+      }`
+    })
+
+    bash(sleep 0.5)
+
+    // Full-page screenshot (component highlighted)
+    mcp__chrome-devtools__take_screenshot({
+      fullPage: false,
+      format: "png",
+      quality: 90,
+      filePath: output_file
+    })
+
+    depth_5_captures.append({
+      "name": shadow_name,
+      "tag": shadow.tag,
+      "path": output_file,
+      "size_kb": file_size_kb(output_file)
+    })
+
+  CATCH error:
+    REPORT: f"Skip {shadow_name}: {error}"
+
+layer_map.layers["depth-5"] = {
+  "type": "shadow-dom",
+  "captures": depth_5_captures
+}
+
+TodoWrite(mark_completed: "Depth 5: Shadow DOM")
+```
+
+**Output**: `depth-5/shadow-*.png` × N
+
+## Phase 8: Generate Layer Map
+
+### Step 1: Compile Metadata
+```javascript
+TodoWrite(mark_in_progress: "Generate layer map")
+
+// Calculate totals
+total_captures = sum(len(layer.captures) for layer in layer_map.layers.values())
+total_size_kb = sum(
+  sum(c.size_kb for c in layer.captures)
+  for layer in layer_map.layers.values()
+)
+
+layer_map["summary"] = {
+  "timestamp": current_timestamp(),
+  "total_depth": depth,
+  "total_captures": total_captures,
+  "total_size_kb": total_size_kb
+}
+
+Write(f"{base_path}/screenshots/layer-map.json", JSON.stringify(layer_map, indent=2))
+
+TodoWrite(mark_completed: "Generate layer map")
+```
+
+**Output**: `layer-map.json`
+
+## Completion
+
+### Todo Update
+```javascript
+all_todos_completed = true
+TodoWrite({todos: all_completed_todos})
+```
+
+### Output Message
+```
+✅ Interactive layer exploration complete!
+
+Configuration:
+- URL: {url}
+- Max depth: {depth}
+- Layers explored: {len(layer_map.layers)}
+
+Capture Summary:
+  Depth 1 (Page):        {depth_1_count} screenshot(s)
+  Depth 2 (Elements):    {depth_2_count} screenshot(s)
+  Depth 3 (Interactions): {depth_3_count} screenshot(s)
+  Depth 4 (Embedded):    {depth_4_count} screenshot(s)
+  Depth 5 (Shadow DOM):  {depth_5_count} screenshot(s)
+
+Total: {total_captures} captures ({total_size_kb:.1f} KB)
+
+Output Structure:
+{base_path}/screenshots/
+├── depth-1/
+│   └── full-page.png
+├── depth-2/
+│   ├── navbar.png
+│   └── footer.png
+├── depth-3/
+│   ├── modal-login.png
+│   └── dropdown-menu.png
+├── depth-4/
+│   └── iframe-analytics.png
+├── depth-5/
+│   └── shadow-button.png
+└── layer-map.json
+
+Next: /workflow:ui-design:extract --images "screenshots/**/*.png"
+```
+
+## Simple Bash Commands
+
+### Directory Setup
+```bash
+# Create depth directories
+bash(for i in $(seq 1 $depth); do mkdir -p $BASE_PATH/screenshots/depth-$i; done)
+```
+
+### Validation
+```bash
+# Check MCP
+all_resources = ListMcpResourcesTool()
+
+# Count captures per depth
+bash(ls $base_path/screenshots/depth-{1..5}/*.png 2>/dev/null | wc -l)
+```
+
+### File Operations
+```bash
+# List all captures
+bash(find $base_path/screenshots -name "*.png" -type f)
+
+# Total size
+bash(du -sh $base_path/screenshots)
+```
+
+## Output Structure
+
+```
+{base_path}/screenshots/
+├── depth-1/
+│   └── full-page.png
+├── depth-2/
+│   ├── {element}.png
+│   └── ...
+├── depth-3/
+│   ├── {interaction}.png
+│   └── ...
+├── depth-4/
+│   ├── iframe-*.png
+│   └── ...
+├── depth-5/
+│   ├── shadow-*.png
+│   └── ...
+└── layer-map.json
+```
+
+## Depth Level Details
+
+| Depth | Name | Captures | Time | Use Case |
+|-------|------|----------|------|----------|
+| 1 | Page | Full page | 30s | Quick preview |
+| 2 | Elements | Key components | 1-2min | Component library |
+| 3 | Interactions | Modals, dropdowns | 2-4min | UI flows |
+| 4 | Embedded | Iframes | 3-6min | Complete context |
+| 5 | Shadow DOM | Web components | 4-8min | Full coverage |
+
+## Error Handling
+
+### Common Errors
+```
+ERROR: Chrome DevTools MCP required
+→ Install: npm i -g @modelcontextprotocol/server-chrome-devtools
+
+ERROR: Invalid depth
+→ Use: 1-5
+
+ERROR: Interaction trigger failed
+→ Some modals may be skipped, check layer-map.json
+```
+
+### Recovery
+- **Partial success**: Lower depth captures preserved
+- **Trigger failures**: Interaction layer may be incomplete
+- **Iframe restrictions**: Cross-origin iframes skipped
+
+## Quality Checklist
+
+- [ ] All depths up to specified level captured
+- [ ] layer-map.json generated with metadata
+- [ ] File sizes valid (> 500 bytes)
+- [ ] Interaction triggers executed
+- [ ] Shadow DOM elements highlighted
+
+## Key Features
+
+- **Depth-controlled**: Progressive capture 1-5 levels
+- **Interactive triggers**: Click/hover for hidden layers
+- **Iframe support**: Embedded content captured
+- **Shadow DOM**: Web component internals
+- **Structured output**: Organized by depth
+
+## Integration
+
+**Input**: Single URL + depth level (1-5)
+**Output**: Hierarchical screenshots + layer-map.json
+**Complements**: `/workflow:ui-design:capture` (multi-URL batch)
+**Next**: `/workflow:ui-design:extract` for design analysis

.claude/commands/workflow/ui-design/generate.md

@@ -0,0 +1,320 @@
+---
+name: generate
+description: Assemble UI prototypes by combining layout templates with design tokens (pure assembler)
+argument-hint: [--base-path <path>] [--session <id>] [--style-variants <count>] [--layout-variants <count>]
+allowed-tools: TodoWrite(*), Read(*), Write(*), Task(ui-design-agent), Bash(*)
+---
+
+# Generate UI Prototypes (/workflow:ui-design:generate)
+
+## Overview
+Pure assembler that combines pre-extracted layout templates with design tokens to generate UI prototypes (`style × layout × targets`). No layout design logic - purely combines existing components.
+
+**Strategy**: Pure Assembly
+- **Input**: `layout-templates.json` + `design-tokens.json` (+ reference images if available)
+- **Process**: Combine structure (DOM) with style (tokens)
+- **Output**: Complete HTML/CSS prototypes
+- **No Design Logic**: All layout and style decisions already made
+- **Automatic Image Reference**: If source images exist in layout templates, they're automatically used for visual context
+
+**Prerequisite Commands**:
+- `/workflow:ui-design:style-extract` → Style tokens
+- `/workflow:ui-design:consolidate` → Final design tokens
+- `/workflow:ui-design:layout-extract` → Layout structure
+
+## Phase 1: Setup & Validation
+
+### Step 1: Resolve Base Path & Parse Configuration
+```bash
+# Determine working directory
+bash(find .workflow -type d -name "design-*" | head -1)  # Auto-detect
+
+# Get style count
+bash(ls {base_path}/style-consolidation/style-* -d | wc -l)
+
+# Image reference auto-detected from layout template source_image_path
+```
+
+### Step 2: Load Layout Templates
+```bash
+# Check layout templates exist
+bash(test -f {base_path}/layout-extraction/layout-templates.json && echo "exists")
+
+# Load layout templates
+Read({base_path}/layout-extraction/layout-templates.json)
+# Extract: targets, layout_variants count, device_type, template structures
+```
+
+**Output**: `base_path`, `style_variants`, `layout_templates[]`, `targets[]`, `device_type`
+
+### Step 3: Validate Design Tokens
+```bash
+# Check design tokens exist for all styles
+bash(test -f {base_path}/style-consolidation/style-1/design-tokens.json && echo "valid")
+
+# For each style variant: Load design tokens
+Read({base_path}/style-consolidation/style-{id}/design-tokens.json)
+```
+
+**Output**: `design_tokens[]` for all style variants
+
+## Phase 2: Assembly (Agent)
+
+**Executor**: `Task(ui-design-agent)` × `T × S × L` tasks (can be batched)
+
+### Step 1: Launch Assembly Tasks
+```bash
+bash(mkdir -p {base_path}/prototypes)
+```
+
+For each `target × style_id × layout_id`:
+```javascript
+Task(ui-design-agent): `
+  [LAYOUT_STYLE_ASSEMBLY]
+  🎯 Assembly task: {target} × Style-{style_id} × Layout-{layout_id}
+  Combine: Pre-extracted layout structure + design tokens → Final HTML/CSS
+
+  TARGET: {target} | STYLE: {style_id} | LAYOUT: {layout_id}
+  BASE_PATH: {base_path}
+
+  ## Inputs (READ ONLY - NO DESIGN DECISIONS)
+  1. Layout Template:
+     Read("{base_path}/layout-extraction/layout-templates.json")
+     Find template where: target={target} AND variant_id="layout-{layout_id}"
+     Extract: dom_structure, css_layout_rules, device_type, source_image_path
+
+  2. Design Tokens:
+     Read("{base_path}/style-consolidation/style-{style_id}/design-tokens.json")
+     Extract: ALL token values (colors, typography, spacing, borders, shadows, breakpoints)
+
+  3. Reference Image (AUTO-DETECTED):
+     IF template.source_image_path exists:
+       Read(template.source_image_path)
+       Purpose: Additional visual context for better placeholder content generation
+       Note: This is for reference only - layout and style decisions already made
+     ELSE:
+       Use generic placeholder content
+
+  ## Assembly Process
+  1. Build HTML: {base_path}/prototypes/{target}-style-{style_id}-layout-{layout_id}.html
+     - Recursively build from template.dom_structure
+     - Add: <!DOCTYPE html>, <head>, <meta viewport>
+     - CSS link: <link href="{target}-style-{style_id}-layout-{layout_id}.css">
+     - Inject placeholder content:
+       * Default: Use Lorem ipsum, generic sample data
+       * If reference image available: Generate more contextually appropriate placeholders
+         (e.g., realistic headings, meaningful text snippets that match the visual context)
+     - Preserve all attributes from dom_structure
+
+  2. Build CSS: {base_path}/prototypes/{target}-style-{style_id}-layout-{layout_id}.css
+     - Start with template.css_layout_rules
+     - Replace ALL var(--*) with actual token values from design-tokens.json
+       Example: var(--spacing-4) → 1rem (from tokens.spacing.4)
+       Example: var(--breakpoint-md) → 768px (from tokens.breakpoints.md)
+     - Add visual styling using design tokens:
+       * Colors: tokens.colors.*
+       * Typography: tokens.typography.*
+       * Shadows: tokens.shadows.*
+       * Border radius: tokens.border_radius.*
+     - Device-optimized for template.device_type
+
+  ## Assembly Rules
+  - ✅ Pure assembly: Combine existing structure + existing style
+  - ❌ NO layout design decisions (structure pre-defined)
+  - ❌ NO style design decisions (tokens pre-defined)
+  - ✅ Replace var() with actual values
+  - ✅ Add placeholder content only
+  - Write files IMMEDIATELY
+  - CSS filename MUST match HTML <link href="...">
+`
+```
+
+### Step 2: Verify Generated Files
+```bash
+# Count expected vs found
+bash(ls {base_path}/prototypes/{target}-style-*-layout-*.html | wc -l)
+
+# Validate samples
+Read({base_path}/prototypes/{target}-style-{style_id}-layout-{layout_id}.html)
+# Check: <!DOCTYPE html>, correct CSS href, sufficient CSS length
+```
+
+**Output**: `S × L × T × 2` files verified
+
+## Phase 3: Generate Preview Files
+
+### Step 1: Run Preview Generation Script
+```bash
+bash(~/.claude/scripts/ui-generate-preview.sh "{base_path}/prototypes")
+```
+
+**Script generates**:
+- `compare.html` (interactive matrix)
+- `index.html` (navigation)
+- `PREVIEW.md` (instructions)
+
+### Step 2: Verify Preview Files
+```bash
+bash(ls {base_path}/prototypes/compare.html {base_path}/prototypes/index.html {base_path}/prototypes/PREVIEW.md)
+```
+
+**Output**: 3 preview files
+
+## Completion
+
+### Todo Update
+```javascript
+TodoWrite({todos: [
+  {content: "Setup and validation", status: "completed", activeForm: "Loading design systems"},
+  {content: "Load layout templates", status: "completed", activeForm: "Reading layout templates"},
+  {content: "Assembly (agent)", status: "completed", activeForm: "Assembling prototypes"},
+  {content: "Verify files", status: "completed", activeForm: "Validating output"},
+  {content: "Generate previews", status: "completed", activeForm: "Creating preview files"}
+]});
+```
+
+### Output Message
+```
+✅ UI prototype assembly complete!
+
+Configuration:
+- Style Variants: {style_variants}
+- Layout Variants: {layout_variants} (from layout-templates.json)
+- Device Type: {device_type}
+- Targets: {targets}
+- Total Prototypes: {S × L × T}
+- Image Reference: Auto-detected (uses source images when available in layout templates)
+
+Assembly Process:
+- Pure assembly: Combined pre-extracted layouts + design tokens
+- No design decisions: All structure and style pre-defined
+- Assembly tasks: T×S×L = {T}×{S}×{L} = {T×S×L} combinations
+
+Quality:
+- Structure: From layout-extract (DOM, CSS layout rules)
+- Style: From consolidate (design tokens)
+- CSS: Token values directly applied (var() replaced)
+- Device-optimized: Layouts match device_type from templates
+
+Generated Files:
+{base_path}/prototypes/
+├── _templates/
+│   └── layout-templates.json (input, pre-extracted)
+├── {target}-style-{s}-layout-{l}.html ({S×L×T} prototypes)
+├── {target}-style-{s}-layout-{l}.css
+├── compare.html (interactive matrix)
+├── index.html (navigation)
+└── PREVIEW.md (instructions)
+
+Preview:
+1. Open compare.html (recommended)
+2. Open index.html
+3. Read PREVIEW.md
+
+Next: /workflow:ui-design:update
+```
+
+## Simple Bash Commands
+
+### Path Operations
+```bash
+# Find design directory
+bash(find .workflow -type d -name "design-*" | head -1)
+
+# Count style variants
+bash(ls {base_path}/style-consolidation/style-* -d | wc -l)
+```
+
+### Validation Commands
+```bash
+# Check layout templates exist
+bash(test -f {base_path}/layout-extraction/layout-templates.json && echo "exists")
+
+# Check design tokens exist
+bash(test -f {base_path}/style-consolidation/style-1/design-tokens.json && echo "valid")
+
+# Count generated files
+bash(ls {base_path}/prototypes/{target}-style-*-layout-*.html | wc -l)
+
+# Verify preview
+bash(test -f {base_path}/prototypes/compare.html && echo "exists")
+```
+
+### File Operations
+```bash
+# Create directories
+bash(mkdir -p {base_path}/prototypes)
+
+# Run preview script
+bash(~/.claude/scripts/ui-generate-preview.sh "{base_path}/prototypes")
+```
+
+## Output Structure
+
+```
+{base_path}/
+├── layout-extraction/
+│   └── layout-templates.json      # Input (from layout-extract)
+├── style-consolidation/
+│   └── style-{s}/
+│       ├── design-tokens.json     # Input (from consolidate)
+│       └── style-guide.md
+└── prototypes/
+    ├── {target}-style-{s}-layout-{l}.html  # Assembled prototypes
+    ├── {target}-style-{s}-layout-{l}.css
+    ├── compare.html
+    ├── index.html
+    └── PREVIEW.md
+```
+
+## Error Handling
+
+### Common Errors
+```
+ERROR: Layout templates not found
+→ Run /workflow:ui-design:layout-extract first
+
+ERROR: Design tokens not found
+→ Run /workflow:ui-design:consolidate first
+
+ERROR: Agent assembly failed
+→ Check inputs exist, validate JSON structure
+
+ERROR: Script permission denied
+→ chmod +x ~/.claude/scripts/ui-generate-preview.sh
+```
+
+### Recovery Strategies
+- **Partial success**: Keep successful assembly combinations
+- **Invalid template structure**: Validate layout-templates.json
+- **Invalid tokens**: Validate design-tokens.json structure
+
+## Quality Checklist
+
+- [ ] CSS uses direct token values (var() replaced)
+- [ ] HTML structure matches layout template exactly
+- [ ] Semantic HTML5 structure preserved
+- [ ] ARIA attributes from template present
+- [ ] Device-specific optimizations applied
+- [ ] All token references resolved
+- [ ] compare.html works
+
+## Key Features
+
+- **Pure Assembly**: No design decisions, only combination
+- **Separation of Concerns**: Layout (structure) + Style (tokens) kept separate until final assembly
+- **Token Resolution**: var() placeholders replaced with actual values
+- **Pre-validated**: Inputs already validated by extract/consolidate
+- **Efficient**: Simple assembly vs complex generation
+- **Production-Ready**: Semantic, accessible, token-driven
+
+## Integration
+
+**Prerequisites**:
+- `/workflow:ui-design:style-extract` → `style-cards.json`
+- `/workflow:ui-design:consolidate` → `design-tokens.json`
+- `/workflow:ui-design:layout-extract` → `layout-templates.json`
+
+**Input**: `layout-templates.json` + `design-tokens.json`
+**Output**: S×L×T prototypes for `/workflow:ui-design:update`
+**Called by**: `/workflow:ui-design:explore-auto`, `/workflow:ui-design:imitate-auto`

.claude/commands/workflow/ui-design/imitate-auto.md

@@ -0,0 +1,897 @@
+---
+name: imitate-auto
+description: High-speed multi-page UI replication with batch screenshot and optional token refinement
+argument-hint: --url-map "<map>" [--capture-mode <batch|deep>] [--depth <1-5>] [--session <id>] [--refine-tokens] [--prompt "<desc>"]
+allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Write(*), Bash(*)
+---
+
+# UI Design Imitate-Auto Workflow Command
+
+## Overview & Execution Model
+
+**Fully autonomous replication orchestrator**: Efficiently replicate multiple web pages through sequential execution from screenshot capture to design integration.
+
+**Dual Capture Strategy**: Supports two capture modes for different use cases:
+- **Batch Mode** (default): Fast multi-URL screenshot capture via `/workflow:ui-design:capture`
+- **Deep Mode**: Interactive layer exploration for single URL via `/workflow:ui-design:explore-layers`
+
+**Autonomous Flow** (⚠️ CONTINUOUS EXECUTION - DO NOT STOP):
+1. User triggers: `/workflow:ui-design:imitate-auto --url-map "..."`
+2. Phase 0: Initialize and parse parameters
+3. Phase 1: Screenshot capture (batch or deep mode) → **WAIT for completion** → Auto-continues
+4. Phase 2: Style extraction (visual tokens) → **WAIT for completion** → Auto-continues
+5. Phase 2.5: Layout extraction (structure templates) → **WAIT for completion** → Auto-continues
+6. Phase 3: Token processing (conditional consolidate) → **WAIT for completion** → Auto-continues
+7. Phase 4: Batch UI assembly → **WAIT for completion** → Auto-continues
+8. Phase 5: Design system integration → Reports completion
+
+**Phase Transition Mechanism**:
+- `SlashCommand` is BLOCKING - execution pauses until completion
+- Upon each phase completion: Automatically process output and execute next phase
+- No user interaction required after initial parameter parsing
+
+**Auto-Continue Mechanism**: TodoWrite tracks phase status. Upon each phase completion, you MUST immediately construct and execute the next phase command. No user intervention required. The workflow is NOT complete until reaching Phase 5.
+
+## Core Rules
+
+1. **Start Immediately**: TodoWrite initialization → Phase 1 execution
+2. **No Preliminary Validation**: Sub-commands handle their own validation
+3. **Parse & Pass**: Extract data from each output for next phase
+4. **Track Progress**: Update TodoWrite after each phase
+5. **⚠️ CRITICAL: DO NOT STOP** - This is a continuous multi-phase workflow. After each SlashCommand completes, you MUST wait for completion, then immediately execute the next phase. Workflow is NOT complete until Phase 5.
+
+## Parameter Requirements
+
+**Required Parameters**:
+- `--url-map "<map>"`: Target page mapping
+  - Format: `"target1:url1, target2:url2, ..."`
+  - Example: `"home:https://linear.app, pricing:https://linear.app/pricing"`
+  - First target serves as primary style source
+
+**Optional Parameters**:
+- `--capture-mode <batch|deep>` (Optional, default: batch): Screenshot capture strategy
+  - `batch` (default): Multi-URL fast batch capture via `/workflow:ui-design:capture`
+  - `deep`: Single-URL interactive depth exploration via `/workflow:ui-design:explore-layers`
+  - **Note**: `deep` mode only uses first URL from url-map
+
+- `--depth <1-5>` (Optional, default: 3): Capture depth for deep mode
+  - `1`: Page level (full-page screenshot)
+  - `2`: Element level (+ key components)
+  - `3`: Interaction level (+ modals, dropdowns)
+  - `4`: Embedded level (+ iframes)
+  - `5`: Shadow DOM (+ web components)
+  - **Only applies when** `--capture-mode deep`
+
+- `--session <id>` (Optional): Workflow session ID
+  - Integrate into existing session (`.workflow/WFS-{session}/`)
+  - Enable automatic design system integration (Phase 5)
+  - If not provided: standalone mode (`.workflow/.design/`)
+
+- `--refine-tokens` (Optional, default: false): Enable full token refinement
+  - `false` (default): Fast path, skip consolidate (~30-60s faster)
+  - `true`: Production quality, execute full consolidate (philosophy-driven refinement)
+
+- `--prompt "<desc>"` (Optional): Style extraction guidance
+  - Influences extract command analysis focus
+  - Example: `"Focus on dark mode"`, `"Emphasize minimalist design"`
+
+## Execution Modes
+
+**Capture Modes**:
+- **Batch Mode** (default): Multi-URL screenshot capture for fast replication
+  - Uses `/workflow:ui-design:capture` for parallel screenshot capture
+  - Optimized for replicating multiple pages efficiently
+- **Deep Mode**: Single-URL layer exploration for detailed analysis
+  - Uses `/workflow:ui-design:explore-layers` for interactive depth traversal
+  - Captures page layers at different depths (1-5)
+  - Only processes first URL from url-map
+
+**Token Processing Modes**:
+- **Fast-Track** (default): Skip consolidate, use proposed tokens directly (~2s)
+  - Best for rapid prototyping and testing
+  - Tokens may lack philosophy-driven refinement
+- **Production** (--refine-tokens): Full consolidate with WCAG validation (~60s)
+  - Philosophy-driven token refinement
+  - Complete accessibility validation
+  - Production-ready design system
+
+**Session Integration**:
+- `--session` flag determines session integration or standalone execution
+- Integrated: Design system automatically added to session artifacts
+- Standalone: Output in `.workflow/.design/{run_id}/`
+
+## 6-Phase Execution
+
+### Phase 0: Initialization and Target Parsing
+
+```bash
+REPORT: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+REPORT: "🚀 UI Design Imitate-Auto"
+REPORT: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+
+# Constants
+DEPTH_NAMES = {
+    1: "Page level",
+    2: "Element level",
+    3: "Interaction level",
+    4: "Embedded level",
+    5: "Shadow DOM"
+}
+
+# Generate run ID
+run_id = "run-$(date +%Y%m%d-%H%M%S)"
+
+# Determine base path and session mode
+IF --session:
+    session_id = {provided_session}
+    base_path = ".workflow/WFS-{session_id}/design-{run_id}"
+    session_mode = "integrated"
+    REPORT: "Mode: Integrated (Session: {session_id})"
+ELSE:
+    session_id = null
+    base_path = ".workflow/.design/{run_id}"
+    session_mode = "standalone"
+    REPORT: "Mode: Standalone"
+
+# Create base directory
+Bash(mkdir -p "{base_path}")
+
+# Parse url-map
+url_map_string = {--url-map}
+VALIDATE: url_map_string is not empty, "--url-map parameter is required"
+
+# Parse target:url pairs
+url_map = {}  # {target_name: url}
+target_names = []
+
+FOR pair IN split(url_map_string, ","):
+    pair = pair.strip()
+
+    IF ":" NOT IN pair:
+        ERROR: "Invalid url-map format: '{pair}'"
+        ERROR: "Expected format: 'target:url'"
+        ERROR: "Example: 'home:https://example.com, pricing:https://example.com/pricing'"
+        EXIT 1
+
+    target, url = pair.split(":", 1)
+    target = target.strip().lower().replace(" ", "-")
+    url = url.strip()
+
+    url_map[target] = url
+    target_names.append(target)
+
+VALIDATE: len(target_names) > 0, "url-map must contain at least one target:url pair"
+
+primary_target = target_names[0]  # First target as primary style source
+refine_tokens_mode = --refine-tokens OR false
+
+# Parse capture mode
+capture_mode = --capture-mode OR "batch"
+depth = int(--depth OR 3)
+
+# Validate capture mode
+IF capture_mode NOT IN ["batch", "deep"]:
+    ERROR: "Invalid --capture-mode: {capture_mode}"
+    ERROR: "Valid options: batch, deep"
+    EXIT 1
+
+# Validate depth (only for deep mode)
+IF capture_mode == "deep":
+    IF depth NOT IN [1, 2, 3, 4, 5]:
+        ERROR: "Invalid --depth: {depth}"
+        ERROR: "Valid range: 1-5"
+        EXIT 1
+
+    # Warn if multiple URLs in deep mode
+    IF len(target_names) > 1:
+        WARN: "⚠️ Deep mode only uses first URL: '{primary_target}'"
+        WARN: "   Other URLs will be ignored: {', '.join(target_names[1:])}"
+        WARN: "   For multi-URL, use --capture-mode batch"
+
+# Write metadata
+metadata = {
+    "workflow": "imitate-auto",
+    "run_id": run_id,
+    "session_id": session_id,
+    "timestamp": current_timestamp(),
+    "parameters": {
+        "url_map": url_map,
+        "capture_mode": capture_mode,
+        "depth": depth IF capture_mode == "deep" ELSE null,
+        "refine_tokens": refine_tokens_mode,
+        "prompt": --prompt OR null
+    },
+    "targets": target_names,
+    "status": "in_progress"
+}
+
+Write("{base_path}/.run-metadata.json", JSON.stringify(metadata, null, 2))
+
+REPORT: ""
+REPORT: "Configuration:"
+REPORT: "  Capture mode: {capture_mode}"
+IF capture_mode == "deep":
+    REPORT: "    Depth level: {depth} ({DEPTH_NAMES[depth]})"
+    REPORT: "    Target: '{primary_target}' ({url_map[primary_target]})"
+ELSE:
+    REPORT: "    Targets: {len(target_names)} pages"
+    REPORT: "    Primary source: '{primary_target}' ({url_map[primary_target]})"
+    REPORT: "    All targets: {', '.join(target_names)}"
+REPORT: "  Token refinement: {refine_tokens_mode ? 'Enabled (production quality)' : 'Disabled (fast-track)'}"
+IF --prompt:
+    REPORT: "  Prompt guidance: \"{--prompt}\""
+REPORT: ""
+
+# Initialize TodoWrite
+TodoWrite({todos: [
+  {content: "Initialize and parse url-map", status: "completed", activeForm: "Initializing"},
+  {content: capture_mode == "batch" ? f"Batch screenshot capture ({len(target_names)} targets)" : f"Deep exploration (depth {depth})", status: "pending", activeForm: "Capturing screenshots"},
+  {content: "Extract style (visual tokens)", status: "pending", activeForm: "Extracting style"},
+  {content: "Extract layout (structure templates)", status: "pending", activeForm: "Extracting layout"},
+  {content: refine_tokens_mode ? "Refine design tokens via consolidate" : "Fast token adaptation (skip consolidate)", status: "pending", activeForm: "Processing tokens"},
+  {content: f"Assemble UI for {len(target_names)} targets", status: "pending", activeForm: "Assembling UI"},
+  {content: session_id ? "Integrate design system" : "Standalone completion", status: "pending", activeForm: "Completing"}
+]})
+```
+
+### Phase 1: Screenshot Capture (Dual Mode)
+
+```bash
+REPORT: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+REPORT: f"🚀 Phase 1: Screenshot Capture ({capture_mode} mode)"
+REPORT: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+
+IF capture_mode == "batch":
+    # Mode A: Batch Multi-URL Capture
+    REPORT: "Using batch capture for multiple URLs..."
+
+    # Build url-map string for capture command
+    url_map_command_string = ",".join([f"{name}:{url}" for name, url in url_map.items()])
+
+    # Call capture command
+    capture_command = f"/workflow:ui-design:capture --base-path \"{base_path}\" --url-map \"{url_map_command_string}\""
+
+    REPORT: f"  Command: {capture_command}"
+    REPORT: f"  Targets: {len(target_names)}"
+
+    TRY:
+        SlashCommand(capture_command)
+    CATCH error:
+        ERROR: "Batch capture failed: {error}"
+        ERROR: "Cannot proceed without screenshots"
+        EXIT 1
+
+    # Verify batch capture results
+    screenshot_metadata_path = "{base_path}/screenshots/capture-metadata.json"
+
+    IF NOT exists(screenshot_metadata_path):
+        ERROR: "capture command did not generate metadata file"
+        ERROR: "Expected: {screenshot_metadata_path}"
+        EXIT 1
+
+    screenshot_metadata = Read(screenshot_metadata_path)
+    captured_count = screenshot_metadata.total_captured
+    total_requested = screenshot_metadata.total_requested
+    missing_count = total_requested - captured_count
+
+    REPORT: ""
+    REPORT: "✅ Batch capture complete:"
+    REPORT: "   Captured: {captured_count}/{total_requested} screenshots ({(captured_count/total_requested*100):.1f}%)"
+
+    IF missing_count > 0:
+        missing_targets = [s.target for s in screenshot_metadata.screenshots if not s.captured]
+        WARN: "   ⚠️ Missing {missing_count} screenshots: {', '.join(missing_targets)}"
+        WARN: "   Proceeding with available screenshots for extract phase"
+
+    # If all screenshots failed, terminate
+    IF captured_count == 0:
+        ERROR: "No screenshots captured - cannot proceed"
+        ERROR: "Please check URLs and tool availability"
+        EXIT 1
+
+ELSE:  # capture_mode == "deep"
+    # Mode B: Deep Interactive Layer Exploration
+    REPORT: "Using deep exploration for single URL..."
+
+    primary_url = url_map[primary_target]
+
+    # Call explore-layers command
+    explore_command = f"/workflow:ui-design:explore-layers --url \"{primary_url}\" --depth {depth} --base-path \"{base_path}\""
+
+    REPORT: f"  Command: {explore_command}"
+    REPORT: f"  URL: {primary_url}"
+    REPORT: f"  Depth: {depth} ({DEPTH_NAMES[depth]})"
+
+    TRY:
+        SlashCommand(explore_command)
+    CATCH error:
+        ERROR: "Deep exploration failed: {error}"
+        ERROR: "Cannot proceed without screenshots"
+        EXIT 1
+
+    # Verify deep exploration results
+    layer_map_path = "{base_path}/screenshots/layer-map.json"
+
+    IF NOT exists(layer_map_path):
+        ERROR: "explore-layers did not generate layer-map.json"
+        ERROR: "Expected: {layer_map_path}"
+        EXIT 1
+
+    layer_map = Read(layer_map_path)
+    total_layers = len(layer_map.layers)
+    captured_count = layer_map.summary.total_captures
+
+    REPORT: ""
+    REPORT: "✅ Deep exploration complete:"
+    REPORT: "   Layers: {total_layers} (depth 1-{depth})"
+    REPORT: "   Captures: {captured_count} screenshots"
+    REPORT: "   Total size: {layer_map.summary.total_size_kb:.1f} KB"
+
+    # Count actual images for extract phase
+    total_requested = captured_count  # For consistency with batch mode
+
+TodoWrite(mark_completed: f"Batch screenshot capture ({len(target_names)} targets)" IF capture_mode == "batch" ELSE f"Deep exploration (depth {depth})",
+          mark_in_progress: "Extract style (visual tokens)")
+```
+
+### Phase 2: Style Extraction (Visual Tokens)
+
+```bash
+REPORT: ""
+REPORT: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+REPORT: "🚀 Phase 2: Extract Style (Visual Tokens)"
+REPORT: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+
+# Use all screenshots as input to extract single design system
+IF capture_mode == "batch":
+    images_glob = f"{base_path}/screenshots/*.{{png,jpg,jpeg,webp}}"
+ELSE:  # deep mode
+    images_glob = f"{base_path}/screenshots/**/*.{{png,jpg,jpeg,webp}}"  # Include all depth directories
+
+# Build extraction prompt
+IF --prompt:
+    user_guidance = {--prompt}
+    extraction_prompt = f"Extract visual style tokens (colors, typography, spacing) from the '{primary_target}' page. Use other screenshots for consistency. User guidance: {user_guidance}"
+ELSE:
+    extraction_prompt = f"Extract visual style tokens (colors, typography, spacing) from the '{primary_target}' page. Use other screenshots for consistency across all pages."
+
+# Call style-extract command (imitate mode, automatically uses single variant)
+extract_command = f"/workflow:ui-design:style-extract --base-path \"{base_path}\" --images \"{images_glob}\" --prompt \"{extraction_prompt}\" --mode imitate"
+
+REPORT: "Calling style-extract command..."
+REPORT: f"  Mode: imitate (high-fidelity single style, auto variants=1)"
+REPORT: f"  Primary source: '{primary_target}'"
+REPORT: f"  Images: {images_glob}"
+
+TRY:
+    SlashCommand(extract_command)
+CATCH error:
+    ERROR: "Style extraction failed: {error}"
+    ERROR: "Cannot proceed without visual tokens"
+    EXIT 1
+
+# style-extract outputs to: {base_path}/style-extraction/style-cards.json
+
+# Verify extraction results
+style_cards_path = "{base_path}/style-extraction/style-cards.json"
+
+IF NOT exists(style_cards_path):
+    ERROR: "style-extract command did not generate style-cards.json"
+    ERROR: "Expected: {style_cards_path}"
+    EXIT 1
+
+style_cards = Read(style_cards_path)
+
+IF len(style_cards.style_cards) != 1:
+    ERROR: "Expected single variant in imitate mode, got {len(style_cards.style_cards)}"
+    EXIT 1
+
+extracted_style = style_cards.style_cards[0]
+
+REPORT: ""
+REPORT: "✅ Phase 2 complete:"
+REPORT: "   Style: '{extracted_style.name}'"
+REPORT: "   Philosophy: {extracted_style.design_philosophy}"
+REPORT: "   Tokens: {count_tokens(extracted_style.proposed_tokens)} visual tokens"
+
+TodoWrite(mark_completed: "Extract style (visual tokens)",
+          mark_in_progress: "Extract layout (structure templates)")
+```
+
+### Phase 2.5: Layout Extraction (Structure Templates)
+
+```bash
+REPORT: ""
+REPORT: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+REPORT: "🚀 Phase 2.5: Extract Layout (Structure Templates)"
+REPORT: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+
+# Reuse same screenshots for layout extraction
+# Build URL map for layout-extract (uses first URL from each target)
+url_map_for_layout = ",".join([f"{target}:{url}" for target, url in url_map.items()])
+
+# Call layout-extract command (imitate mode for structure replication)
+layout_extract_command = f"/workflow:ui-design:layout-extract --base-path \"{base_path}\" --images \"{images_glob}\" --targets \"{','.join(target_names)}\" --mode imitate"
+
+REPORT: "Calling layout-extract command..."
+REPORT: f"  Mode: imitate (high-fidelity structure replication)"
+REPORT: f"  Targets: {', '.join(target_names)}"
+REPORT: f"  Images: {images_glob}"
+
+TRY:
+    SlashCommand(layout_extract_command)
+CATCH error:
+    ERROR: "Layout extraction failed: {error}"
+    ERROR: "Cannot proceed without layout templates"
+    EXIT 1
+
+# layout-extract outputs to: {base_path}/layout-extraction/layout-templates.json
+
+# Verify layout extraction results
+layout_templates_path = "{base_path}/layout-extraction/layout-templates.json"
+
+IF NOT exists(layout_templates_path):
+    ERROR: "layout-extract command did not generate layout-templates.json"
+    ERROR: "Expected: {layout_templates_path}"
+    EXIT 1
+
+layout_templates = Read(layout_templates_path)
+template_count = len(layout_templates.layout_templates)
+
+REPORT: ""
+REPORT: "✅ Phase 2.5 complete:"
+REPORT: "   Templates: {template_count} layout structures"
+REPORT: "   Targets: {', '.join(target_names)}"
+
+TodoWrite(mark_completed: "Extract layout (structure templates)",
+          mark_in_progress: refine_tokens_mode ? "Refine design tokens via consolidate" : "Fast token adaptation")
+```
+
+### Phase 3: Token Processing (Conditional Consolidate)
+
+```bash
+REPORT: ""
+REPORT: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+REPORT: "🚀 Phase 3: Token Processing"
+REPORT: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+
+IF refine_tokens_mode:
+    # Path A: Full consolidate (production quality)
+    REPORT: "🔧 Using full consolidate for production-ready tokens"
+    REPORT: "   Benefits:"
+    REPORT: "   • Philosophy-driven token refinement"
+    REPORT: "   • WCAG AA accessibility validation"
+    REPORT: "   • Complete design system documentation"
+    REPORT: "   • Token gap filling and consistency checks"
+    REPORT: ""
+
+    consolidate_command = f"/workflow:ui-design:consolidate --base-path \"{base_path}\" --variants 1"
+
+    REPORT: f"Calling consolidate command..."
+
+    TRY:
+        SlashCommand(consolidate_command)
+    CATCH error:
+        ERROR: "Token consolidation failed: {error}"
+        ERROR: "Cannot proceed without refined tokens"
+        EXIT 1
+
+    # consolidate outputs to: {base_path}/style-consolidation/style-1/design-tokens.json
+    tokens_path = "{base_path}/style-consolidation/style-1/design-tokens.json"
+
+    IF NOT exists(tokens_path):
+        ERROR: "consolidate command did not generate design-tokens.json"
+        ERROR: "Expected: {tokens_path}"
+        EXIT 1
+
+    REPORT: ""
+    REPORT: "✅ Full consolidate complete"
+    REPORT: "   Output: style-consolidation/style-1/"
+    REPORT: "   Quality: Production-ready"
+    token_quality = "production-ready (consolidated)"
+    time_spent_estimate = "~60s"
+
+ELSE:
+    # Path B: Fast Token Adaptation
+    REPORT: "⚡ Fast token adaptation (skipping consolidate for speed)"
+    REPORT: "   Note: Using proposed tokens from extraction phase"
+    REPORT: "   For production quality, re-run with --refine-tokens flag"
+    REPORT: ""
+
+    # Directly copy proposed_tokens to consolidation directory
+    style_cards = Read("{base_path}/style-extraction/style-cards.json")
+    proposed_tokens = style_cards.style_cards[0].proposed_tokens
+
+    # Create directory and write tokens
+    consolidation_dir = "{base_path}/style-consolidation/style-1"
+    Bash(mkdir -p "{consolidation_dir}")
+
+    tokens_path = f"{consolidation_dir}/design-tokens.json"
+    Write(tokens_path, JSON.stringify(proposed_tokens, null, 2))
+
+    # Create simplified style guide
+    variant = style_cards.style_cards[0]
+    simple_guide = f"""# Design System: {variant.name}
+
+## Design Philosophy
+{variant.design_philosophy}
+
+## Description
+{variant.description}
+
+## Design Tokens
+All tokens in `design-tokens.json` follow OKLCH color space.
+
+**Note**: Generated in fast-track imitate mode using proposed tokens from extraction.
+For production-ready quality with philosophy-driven refinement, re-run with `--refine-tokens` flag.
+
+## Color Preview
+- Primary: {variant.preview.primary if variant.preview else "N/A"}
+- Background: {variant.preview.background if variant.preview else "N/A"}
+
+## Typography Preview
+- Heading Font: {variant.preview.font_heading if variant.preview else "N/A"}
+
+## Token Categories
+{list_token_categories(proposed_tokens)}
+"""
+
+    Write(f"{consolidation_dir}/style-guide.md", simple_guide)
+
+    REPORT: "✅ Fast adaptation complete (~2s vs ~60s with consolidate)"
+    REPORT: "   Output: style-consolidation/style-1/"
+    REPORT: "   Quality: Proposed (not refined)"
+    REPORT: "   Time saved: ~30-60s"
+    token_quality = "proposed (fast-track)"
+    time_spent_estimate = "~2s"
+
+REPORT: ""
+REPORT: "Token processing summary:"
+REPORT: "   Path: {refine_tokens_mode ? 'Full consolidate' : 'Fast adaptation'}"
+REPORT: "   Quality: {token_quality}"
+REPORT: "   Time: {time_spent_estimate}"
+
+TodoWrite(mark_completed: refine_tokens_mode ? "Refine design tokens via consolidate" : "Fast token adaptation",
+          mark_in_progress: f"Assemble UI for {len(target_names)} targets")
+```
+
+### Phase 4: Batch UI Assembly
+
+```bash
+REPORT: ""
+REPORT: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+REPORT: "🚀 Phase 4: Batch UI Assembly"
+REPORT: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+
+# Build targets string
+targets_string = ",".join(target_names)
+
+# Call generate command (now pure assembler - combines layout templates + design tokens)
+generate_command = f"/workflow:ui-design:generate --base-path \"{base_path}\" --style-variants 1 --layout-variants 1"
+
+REPORT: "Calling generate command (pure assembler)..."
+REPORT: f"  Targets: {targets_string} (from layout templates)"
+REPORT: f"  Configuration: 1 style × 1 layout × {len(target_names)} pages"
+REPORT: f"  Inputs: layout-templates.json + design-tokens.json"
+
+TRY:
+    SlashCommand(generate_command)
+CATCH error:
+    ERROR: "UI assembly failed: {error}"
+    ERROR: "Layout templates or design tokens may be invalid"
+    EXIT 1
+
+# generate outputs to: {base_path}/prototypes/{target}-style-1-layout-1.html
+
+# Verify assembly results
+prototypes_dir = "{base_path}/prototypes"
+generated_html_files = Glob(f"{prototypes_dir}/*-style-1-layout-1.html")
+generated_count = len(generated_html_files)
+
+REPORT: ""
+REPORT: "✅ Phase 4 complete:"
+REPORT: "   Assembled: {generated_count} HTML prototypes"
+REPORT: "   Targets: {', '.join(target_names)}"
+REPORT: "   Output: {prototypes_dir}/"
+
+IF generated_count < len(target_names):
+    WARN: "   ⚠️ Expected {len(target_names)} prototypes, assembled {generated_count}"
+    WARN: "   Some targets may have failed - check generate output"
+
+TodoWrite(mark_completed: f"Assemble UI for {len(target_names)} targets",
+          mark_in_progress: session_id ? "Integrate design system" : "Standalone completion")
+```
+
+### Phase 5: Design System Integration
+
+```bash
+REPORT: ""
+REPORT: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+REPORT: "🚀 Phase 5: Design System Integration"
+REPORT: "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+
+IF session_id:
+    REPORT: "Integrating design system into session {session_id}..."
+
+    update_command = f"/workflow:ui-design:update --session {session_id}"
+
+    TRY:
+        SlashCommand(update_command)
+    CATCH error:
+        WARN: "Design system integration failed: {error}"
+        WARN: "Prototypes are still available at {base_path}/prototypes/"
+        # Don't terminate, prototypes already generated
+
+    REPORT: "✅ Design system integrated into session {session_id}"
+ELSE:
+    REPORT: "ℹ️ Standalone mode: Skipping integration"
+    REPORT: "   Prototypes available at: {base_path}/prototypes/"
+    REPORT: "   To integrate later:"
+    REPORT: "   1. Create a workflow session"
+    REPORT: "   2. Copy design-tokens.json to session artifacts"
+
+# Update metadata
+metadata = Read("{base_path}/.run-metadata.json")
+metadata.status = "completed"
+metadata.completion_time = current_timestamp()
+metadata.outputs = {
+    "screenshots": f"{base_path}/screenshots/",
+    "style_system": f"{base_path}/style-consolidation/style-1/",
+    "prototypes": f"{base_path}/prototypes/",
+    "token_quality": token_quality,
+    "captured_count": captured_count,
+    "generated_count": generated_count
+}
+Write("{base_path}/.run-metadata.json", JSON.stringify(metadata, null, 2))
+
+TodoWrite(mark_completed: session_id ? "Integrate design system" : "Standalone completion")
+
+# Mark all phases complete
+TodoWrite({todos: [
+  {content: "Initialize and parse url-map", status: "completed", activeForm: "Initializing"},
+  {content: capture_mode == "batch" ? f"Batch screenshot capture ({len(target_names)} targets)" : f"Deep exploration (depth {depth})", status: "completed", activeForm: "Capturing"},
+  {content: "Extract unified design system", status: "completed", activeForm: "Extracting"},
+  {content: refine_tokens_mode ? "Refine design tokens via consolidate" : "Fast token adaptation", status: "completed", activeForm: "Processing"},
+  {content: f"Generate UI for {len(target_names)} targets", status: "completed", activeForm: "Generating"},
+  {content: session_id ? "Integrate design system" : "Standalone completion", status: "completed", activeForm: "Completing"}
+]})
+```
+
+### Phase 6: Completion Report
+
+**Completion Message**:
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+✅ UI Design Imitate-Auto Complete!
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+━━━ 📊 Workflow Summary ━━━
+
+Mode: {capture_mode == "batch" ? "Batch Multi-Page Replication" : f"Deep Interactive Exploration (depth {depth})"}
+Session: {session_id or "standalone"}
+Run ID: {run_id}
+
+Phase 1 - Screenshot Capture: ✅ {IF capture_mode == "batch": f"{captured_count}/{total_requested} screenshots" ELSE: f"{captured_count} screenshots ({total_layers} layers)"}
+  {IF capture_mode == "batch" AND captured_count < total_requested: f"⚠️ {total_requested - captured_count} missing" ELSE: "All targets captured"}
+
+Phase 2 - Style Extraction: ✅ Single unified design system
+  Style: {extracted_style.name}
+  Philosophy: {extracted_style.design_philosophy[:80]}...
+
+Phase 3 - Token Processing: ✅ {token_quality}
+  {IF refine_tokens_mode:
+    "Full consolidate (~60s)"
+    "Quality: Production-ready with philosophy-driven refinement"
+  ELSE:
+    "Fast adaptation (~2s, saved ~30-60s)"
+    "Quality: Proposed tokens (for production, use --refine-tokens)"
+  }
+
+Phase 4 - UI Generation: ✅ {generated_count} pages generated
+  Targets: {', '.join(target_names)}
+  Configuration: 1 style × 1 layout × {generated_count} pages
+
+Phase 5 - Integration: {IF session_id: "✅ Integrated into session" ELSE: "⏭️ Standalone mode"}
+
+━━━ 📂 Output Structure ━━━
+
+{base_path}/
+├── screenshots/                    # {captured_count} screenshots
+{IF capture_mode == "batch":
+│   ├── {target1}.png
+│   ├── {target2}.png
+│   └── capture-metadata.json
+ELSE:
+│   ├── depth-1/
+│   │   └── full-page.png
+│   ├── depth-2/
+│   │   └── {elements}.png
+│   ├── depth-{depth}/
+│   │   └── {layers}.png
+│   └── layer-map.json
+}
+├── style-extraction/               # Design analysis
+│   └── style-cards.json
+├── style-consolidation/            # {token_quality}
+│   └── style-1/
+│       ├── design-tokens.json
+│       └── style-guide.md
+└── prototypes/                     # {generated_count} HTML/CSS files
+    ├── {target1}-style-1-layout-1.html + .css
+    ├── {target2}-style-1-layout-1.html + .css
+    ├── compare.html                # Interactive preview
+    └── index.html                  # Quick navigation
+
+━━━ ⚡ Performance ━━━
+
+Total workflow time: ~{estimate_total_time()} minutes
+  Screenshot capture: ~{capture_time}
+  Style extraction: ~{extract_time}
+  Token processing: ~{token_processing_time}
+  UI generation: ~{generate_time}
+
+━━━ 🌐 Next Steps ━━━
+
+1. Preview prototypes:
+   • Interactive matrix: Open {base_path}/prototypes/compare.html
+   • Quick navigation: Open {base_path}/prototypes/index.html
+
+{IF session_id:
+2. Create implementation tasks:
+   /workflow:plan --session {session_id}
+
+3. Generate tests (if needed):
+   /workflow:test-gen {session_id}
+ELSE:
+2. To integrate into a workflow session:
+   • Create session: /workflow:session:start
+   • Copy design-tokens.json to session artifacts
+
+3. Explore prototypes in {base_path}/prototypes/ directory
+}
+
+{IF NOT refine_tokens_mode:
+💡 Production Quality Tip:
+   Fast-track mode used proposed tokens for speed.
+   For production-ready quality with full token refinement:
+   /workflow:ui-design:imitate-auto --url-map "{url_map_command_string}" --refine-tokens {f"--session {session_id}" if session_id else ""}
+}
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+## TodoWrite Pattern
+
+```javascript
+// Initialize IMMEDIATELY at start of Phase 0 to track multi-phase execution
+TodoWrite({todos: [
+  {content: "Initialize and parse url-map", status: "in_progress", activeForm: "Initializing"},
+  {content: "Batch screenshot capture", status: "pending", activeForm: "Capturing screenshots"},
+  {content: "Extract unified design system", status: "pending", activeForm: "Extracting style"},
+  {content: refine_tokens ? "Refine tokens via consolidate" : "Fast token adaptation", status: "pending", activeForm: "Processing tokens"},
+  {content: "Generate UI for all targets", status: "pending", activeForm: "Generating UI"},
+  {content: "Integrate design system", status: "pending", activeForm: "Integrating"}
+]})
+
+// ⚠️ CRITICAL: After EACH SlashCommand completion (Phase 1-5), you MUST:
+// 1. SlashCommand blocks and returns when phase is complete
+// 2. Update current phase: status → "completed"
+// 3. Update next phase: status → "in_progress"
+// 4. IMMEDIATELY execute next phase SlashCommand (auto-continue)
+// This ensures continuous workflow tracking and prevents premature stopping
+```
+
+## Error Handling
+
+### Pre-execution Checks
+- **url-map format validation**: Clear error message with format example
+- **Empty url-map**: Error and exit
+- **Invalid target names**: Regex validation with suggestions
+
+### Phase-Specific Errors
+- **Screenshot capture failure (Phase 1)**:
+  - If total_captured == 0: Terminate workflow
+  - If partial failure: Warn but continue with available screenshots
+
+- **Style extraction failure (Phase 2)**:
+  - If extract fails: Terminate with clear error
+  - If style-cards.json missing: Terminate with debugging info
+
+- **Token processing failure (Phase 3)**:
+  - Consolidate mode: Terminate if consolidate fails
+  - Fast mode: Validate proposed_tokens exist before copying
+
+- **UI generation failure (Phase 4)**:
+  - If generate fails: Terminate with error
+  - If generated_count < target_count: Warn but proceed
+
+- **Integration failure (Phase 5)**:
+  - Non-blocking: Warn but don't terminate
+  - Prototypes already available
+
+### Recovery Strategies
+- **Partial screenshot failure**: Continue with available screenshots, list missing in warning
+- **Generate failure**: Report specific target failures, user can re-generate individually
+- **Integration failure**: Prototypes still usable, can integrate manually
+
+
+## Key Features
+
+- **🚀 Dual Capture**: Batch mode for speed, deep mode for detail
+- **⚡ Fast-Track Option**: Skip consolidate for 30-60s time savings
+- **🎨 High-Fidelity**: Single unified design system from primary target
+- **📦 Autonomous**: No user intervention required between phases
+- **🔄 Reproducible**: Deterministic flow with isolated run directories
+- **🎯 Flexible**: Standalone or session-integrated modes
+
+## Examples
+
+### 1. Basic Multi-Page Replication
+```bash
+/workflow:ui-design:imitate-auto --url-map "home:https://linear.app, features:https://linear.app/features"
+# Result: 2 prototypes with fast-track tokens
+```
+
+### 2. Production-Ready with Session
+```bash
+/workflow:ui-design:imitate-auto --session WFS-payment --url-map "pricing:https://stripe.com/pricing" --refine-tokens
+# Result: 1 prototype with production tokens, integrated into session
+```
+
+### 3. Deep Exploration Mode
+```bash
+/workflow:ui-design:imitate-auto --url-map "app:https://app.com" --capture-mode deep --depth 3
+# Result: Interactive layer capture + prototype
+```
+
+### 4. Guided Style Extraction
+```bash
+/workflow:ui-design:imitate-auto --url-map "home:https://example.com, about:https://example.com/about" --prompt "Focus on minimalist design"
+# Result: 2 prototypes with minimalist style focus
+```
+
+## Integration Points
+
+- **Input**: `--url-map` (multiple target:url pairs) + optional `--capture-mode`, `--depth`, `--session`, `--refine-tokens`, `--prompt`
+- **Output**: Complete design system in `{base_path}/` (screenshots, style-extraction, style-consolidation, prototypes)
+- **Sub-commands Called**:
+  1. Phase 1 (conditional):
+     - `--capture-mode batch`: `/workflow:ui-design:capture` (multi-URL batch)
+     - `--capture-mode deep`: `/workflow:ui-design:explore-layers` (single-URL depth exploration)
+  2. `/workflow:ui-design:extract` (Phase 2)
+  3. `/workflow:ui-design:consolidate` (Phase 3, conditional)
+  4. `/workflow:ui-design:generate` (Phase 4)
+  5. `/workflow:ui-design:update` (Phase 5, if --session)
+
+## Completion Output
+
+```
+✅ UI Design Imitate-Auto Workflow Complete!
+
+Mode: {capture_mode} | Session: {session_id or "standalone"}
+Run ID: {run_id}
+
+Phase 1 - Screenshot Capture: ✅ {captured_count} screenshots
+Phase 2 - Style Extraction: ✅ Single unified design system
+Phase 3 - Token Processing: ✅ {token_quality}
+Phase 4 - UI Generation: ✅ {generated_count} pages generated
+Phase 5 - Integration: {IF session_id: "✅ Integrated" ELSE: "⏭️ Standalone"}
+
+Design Quality:
+✅ High-Fidelity Replication: Accurate style from primary target
+✅ Token-Driven Styling: 100% var() usage
+✅ {IF refine_tokens: "Production-Ready: WCAG validated" ELSE: "Fast-Track: Proposed tokens"}
+
+📂 {base_path}/
+  ├── screenshots/                  # {captured_count} screenshots
+  ├── style-extraction/             # Design analysis
+  ├── style-consolidation/          # {token_quality}
+  └── prototypes/                   # {generated_count} HTML/CSS files
+
+🌐 Preview: {base_path}/prototypes/compare.html
+  - Interactive preview
+  - Side-by-side comparison
+  - {generated_count} replicated pages
+
+Next: [/workflow:execute] OR [Open compare.html → /workflow:plan]
+```

.claude/commands/workflow/ui-design/layout-extract.md

@@ -0,0 +1,372 @@
+---
+name: layout-extract
+description: Extract structural layout information from reference images, URLs, or text prompts
+argument-hint: [--base-path <path>] [--session <id>] [--images "<glob>"] [--urls "<list>"] [--prompt "<desc>"] [--targets "<list>"] [--mode <imitate|explore>] [--variants <count>] [--device-type <desktop|mobile|tablet|responsive>]
+allowed-tools: TodoWrite(*), Read(*), Write(*), Glob(*), Bash(*), Task(ui-design-agent), mcp__exa__web_search_exa(*)
+---
+
+# Layout Extraction Command
+
+## Overview
+Extract structural layout information from reference images, URLs, or text prompts using AI analysis. This command separates the "scaffolding" (HTML structure and CSS layout) from the "paint" (visual tokens handled by `style-extract`).
+
+**Strategy**: AI-Driven Structural Analysis
+- **Agent-Powered**: Uses `ui-design-agent` for deep structural analysis
+- **Dual-Mode**:
+  - `imitate`: High-fidelity replication of single layout structure
+  - `explore`: Multiple structurally distinct layout variations
+- **Single Output**: `layout-templates.json` with DOM structure, component hierarchy, and CSS layout rules
+- **Device-Aware**: Optimized for specific device types (desktop, mobile, tablet, responsive)
+- **Token-Based**: CSS uses `var()` placeholders for spacing and breakpoints
+
+## Phase 0: Setup & Input Validation
+
+### Step 1: Detect Input, Mode & Targets
+```bash
+# Detect input source
+# Priority: --urls + --images → hybrid | --urls → url | --images → image | --prompt → text
+
+# Determine extraction mode
+extraction_mode = --mode OR "imitate"  # "imitate" or "explore"
+
+# Set variants count based on mode
+IF extraction_mode == "imitate":
+    variants_count = 1  # Force single variant (ignore --variants)
+ELSE IF extraction_mode == "explore":
+    variants_count = --variants OR 3  # Default to 3
+    VALIDATE: 1 <= variants_count <= 5
+
+# Resolve targets
+# Priority: --targets → prompt analysis → default ["page"]
+targets = --targets OR extract_from_prompt(--prompt) OR ["page"]
+
+# Resolve device type
+device_type = --device-type OR "responsive"  # desktop|mobile|tablet|responsive
+
+# Determine base path
+bash(find .workflow -type d -name "design-*" | head -1)  # Auto-detect
+# OR use --base-path / --session parameters
+```
+
+### Step 2: Load Inputs & Create Directories
+```bash
+# For image mode
+bash(ls {images_pattern})  # Expand glob pattern
+Read({image_path})  # Load each image
+
+# For URL mode
+# Parse URL list format: "target:url,target:url"
+# Validate URLs are accessible
+
+# For text mode
+# Validate --prompt is non-empty
+
+# Create output directory
+bash(mkdir -p {base_path}/layout-extraction)
+```
+
+### Step 3: Memory Check (Skip if Already Done)
+```bash
+# Check if layouts already extracted
+bash(test -f {base_path}/layout-extraction/layout-templates.json && echo "exists")
+```
+
+**If exists**: Skip to completion message
+
+**Output**: `input_mode`, `base_path`, `extraction_mode`, `variants_count`, `targets[]`, `device_type`, loaded inputs
+
+## Phase 1: Layout Research (Explore Mode Only)
+
+### Step 1: Check Extraction Mode
+```bash
+# extraction_mode == "imitate" → skip this phase
+# extraction_mode == "explore" → execute this phase
+```
+
+**If imitate mode**: Skip to Phase 2
+
+### Step 2: Gather Layout Inspiration (Explore Mode)
+```bash
+bash(mkdir -p {base_path}/layout-extraction/_inspirations)
+
+# For each target: Research via MCP
+# mcp__exa__web_search_exa(query="{target} layout patterns {device_type}", numResults=5)
+
+# Write inspiration file
+Write({base_path}/layout-extraction/_inspirations/{target}-layout-ideas.txt, inspiration_content)
+```
+
+**Output**: Inspiration text files for each target (explore mode only)
+
+## Phase 2: Layout Analysis & Synthesis (Agent)
+
+**Executor**: `Task(ui-design-agent)`
+
+### Step 1: Launch Agent Task
+```javascript
+Task(ui-design-agent): `
+  [LAYOUT_EXTRACTION_TASK]
+  Analyze references and extract structural layout templates.
+  Focus ONLY on structure and layout. DO NOT concern with visual style (colors, fonts, etc.).
+
+  REFERENCES:
+  - Input: {reference_material}  // Images, URLs, or prompt
+  - Mode: {extraction_mode}  // 'imitate' or 'explore'
+  - Targets: {targets}  // List of page/component names
+  - Variants per Target: {variants_count}
+  - Device Type: {device_type}
+  ${exploration_mode ? "- Layout Inspiration: Read('" + base_path + "/layout-extraction/_inspirations/{target}-layout-ideas.txt')" : ""}
+
+  ## Analysis & Generation
+  For EACH target in {targets}:
+    For EACH variant (1 to {variants_count}):
+      1. **Analyze Structure**: Deconstruct reference to understand layout, hierarchy, responsiveness
+      2. **Define Philosophy**: Short description (e.g., "Asymmetrical grid with overlapping content areas")
+      3. **Generate DOM Structure**: JSON object representing semantic HTML5 structure
+         - Semantic tags: <header>, <nav>, <main>, <aside>, <section>, <footer>
+         - ARIA roles and accessibility attributes
+         - Device-specific structure:
+           * mobile: Single column, stacked sections, touch targets ≥44px
+           * desktop: Multi-column grids, hover states, larger hit areas
+           * tablet: Hybrid layouts, flexible columns
+           * responsive: Breakpoint-driven adaptive layouts (mobile-first)
+         - In 'explore' mode: Each variant structurally DISTINCT
+      4. **Define Component Hierarchy**: High-level array of main layout regions
+         Example: ["header", "main-content", "sidebar", "footer"]
+      5. **Generate CSS Layout Rules**:
+         - Focus ONLY on layout (Grid, Flexbox, position, alignment, gap, etc.)
+         - Use CSS Custom Properties for spacing/breakpoints: var(--spacing-4), var(--breakpoint-md)
+         - Device-specific styles (mobile-first @media for responsive)
+         - NO colors, NO fonts, NO shadows - layout structure only
+
+  ## Output Format
+  Return JSON object with layout_templates array.
+  Each template must include:
+  - target (string)
+  - variant_id (string, e.g., "layout-1")
+  - source_image_path (string, REQUIRED): Path to the primary reference image used for this layout analysis
+    * For image input: Use the actual image file path from {images_pattern}
+    * For URL input: Use the screenshot path if available, or empty string
+    * For text/prompt input: Use empty string
+    * Example: "{base_path}/screenshots/home.png"
+  - device_type (string)
+  - design_philosophy (string)
+  - dom_structure (JSON object)
+  - component_hierarchy (array of strings)
+  - css_layout_rules (string)
+
+  ## Notes
+  - Structure only, no visual styling
+  - Use var() for all spacing/sizing
+  - Layouts must be structurally distinct in explore mode
+  - Write complete layout-templates.json
+`
+```
+
+**Output**: Agent returns JSON with `layout_templates` array
+
+### Step 2: Write Output File
+```bash
+# Take JSON output from agent
+bash(echo '{agent_json_output}' > {base_path}/layout-extraction/layout-templates.json)
+
+# Verify output
+bash(test -f {base_path}/layout-extraction/layout-templates.json && echo "exists")
+bash(cat {base_path}/layout-extraction/layout-templates.json | grep -q "layout_templates" && echo "valid")
+```
+
+**Output**: `layout-templates.json` created and verified
+
+## Completion
+
+### Todo Update
+```javascript
+TodoWrite({todos: [
+  {content: "Setup and input validation", status: "completed", activeForm: "Validating inputs"},
+  {content: "Layout research (explore mode)", status: "completed", activeForm: "Researching layout patterns"},
+  {content: "Layout analysis and synthesis (agent)", status: "completed", activeForm: "Generating layout templates"},
+  {content: "Write layout-templates.json", status: "completed", activeForm: "Saving templates"}
+]});
+```
+
+### Output Message
+```
+✅ Layout extraction complete!
+
+Configuration:
+- Session: {session_id}
+- Extraction Mode: {extraction_mode} (imitate/explore)
+- Device Type: {device_type}
+- Targets: {targets}
+- Variants per Target: {variants_count}
+- Total Templates: {targets.length × variants_count}
+
+{IF extraction_mode == "explore":
+Layout Research:
+- {targets.length} inspiration files generated
+- Pattern search focused on {device_type} layouts
+}
+
+Generated Templates:
+{FOR each template: - Target: {template.target} | Variant: {template.variant_id} | Philosophy: {template.design_philosophy}}
+
+Output File:
+- {base_path}/layout-extraction/layout-templates.json
+
+Next: /workflow:ui-design:generate will combine these structural templates with style systems to produce final prototypes.
+```
+
+## Simple Bash Commands
+
+### Path Operations
+```bash
+# Find design directory
+bash(find .workflow -type d -name "design-*" | head -1)
+
+# Create output directories
+bash(mkdir -p {base_path}/layout-extraction)
+bash(mkdir -p {base_path}/layout-extraction/_inspirations)  # explore mode only
+```
+
+### Validation Commands
+```bash
+# Check if already extracted
+bash(test -f {base_path}/layout-extraction/layout-templates.json && echo "exists")
+
+# Validate JSON structure
+bash(cat layout-templates.json | grep -q "layout_templates" && echo "valid")
+
+# Count templates
+bash(cat layout-templates.json | grep -c "\"target\":")
+```
+
+### File Operations
+```bash
+# Load image references
+bash(ls {images_pattern})
+Read({image_path})
+
+# Write inspiration files (explore mode)
+Write({base_path}/layout-extraction/_inspirations/{target}-layout-ideas.txt, content)
+
+# Write layout templates
+bash(echo '{json}' > {base_path}/layout-extraction/layout-templates.json)
+```
+
+## Output Structure
+
+```
+{base_path}/
+└── layout-extraction/
+    ├── layout-templates.json         # Structural layout templates
+    ├── layout-space-analysis.json    # Layout directions (explore mode only)
+    └── _inspirations/                 # Explore mode only
+        └── {target}-layout-ideas.txt  # Layout inspiration research
+```
+
+## layout-templates.json Format
+
+```json
+{
+  "extraction_metadata": {
+    "session_id": "...",
+    "input_mode": "image|url|prompt|hybrid",
+    "extraction_mode": "imitate|explore",
+    "device_type": "desktop|mobile|tablet|responsive",
+    "timestamp": "...",
+    "variants_count": 3,
+    "targets": ["home", "dashboard"]
+  },
+  "layout_templates": [
+    {
+      "target": "home",
+      "variant_id": "layout-1",
+      "source_image_path": "{base_path}/screenshots/home.png",
+      "device_type": "responsive",
+      "design_philosophy": "Responsive 3-column holy grail layout with fixed header and footer",
+      "dom_structure": {
+        "tag": "body",
+        "children": [
+          {
+            "tag": "header",
+            "attributes": {"class": "layout-header"},
+            "children": [{"tag": "nav"}]
+          },
+          {
+            "tag": "div",
+            "attributes": {"class": "layout-main-wrapper"},
+            "children": [
+              {"tag": "main", "attributes": {"class": "layout-main-content"}},
+              {"tag": "aside", "attributes": {"class": "layout-sidebar-left"}},
+              {"tag": "aside", "attributes": {"class": "layout-sidebar-right"}}
+            ]
+          },
+          {"tag": "footer", "attributes": {"class": "layout-footer"}}
+        ]
+      },
+      "component_hierarchy": [
+        "header",
+        "main-content",
+        "sidebar-left",
+        "sidebar-right",
+        "footer"
+      ],
+      "css_layout_rules": ".layout-main-wrapper { display: grid; grid-template-columns: 1fr 3fr 1fr; gap: var(--spacing-6); } @media (max-width: var(--breakpoint-md)) { .layout-main-wrapper { grid-template-columns: 1fr; } }"
+    }
+  ]
+}
+```
+
+**Requirements**: Token-based CSS (var()), semantic HTML5, device-specific structure, accessibility attributes
+
+## Error Handling
+
+### Common Errors
+```
+ERROR: No inputs provided
+→ Provide --images, --urls, or --prompt
+
+ERROR: Invalid target name
+→ Use lowercase, alphanumeric, hyphens only
+
+ERROR: Agent task failed
+→ Check agent output, retry with simplified prompt
+
+ERROR: MCP search failed (explore mode)
+→ Check network, retry
+```
+
+### Recovery Strategies
+- **Partial success**: Keep successfully extracted templates
+- **Invalid JSON**: Retry with stricter format requirements
+- **Missing inspiration**: Works without (less informed exploration)
+
+## Key Features
+
+- **Separation of Concerns** - Decouples layout (structure) from style (visuals)
+- **Structural Exploration** - Explore mode enables A/B testing of different layouts
+- **Token-Based Layout** - CSS uses `var()` placeholders for instant design system adaptation
+- **Device-Specific** - Tailored structures for different screen sizes
+- **Foundation for Assembly** - Provides structural blueprint for refactored `generate` command
+- **Agent-Powered** - Deep structural analysis with AI
+
+## Integration
+
+**Workflow Position**: Between style extraction and prototype generation
+
+**New Workflow**:
+1. `/workflow:ui-design:style-extract` → `style-cards.json` (Visual tokens)
+2. `/workflow:ui-design:consolidate` → `design-tokens.json` (Final visual system)
+3. `/workflow:ui-design:layout-extract` → `layout-templates.json` (Structural templates)
+4. `/workflow:ui-design:generate` (Refactored as assembler):
+   - **Reads**: `design-tokens.json` + `layout-templates.json`
+   - **Action**: For each style × layout combination:
+     1. Build HTML from `dom_structure`
+     2. Create layout CSS from `css_layout_rules`
+     3. Link design tokens CSS
+     4. Inject placeholder content
+   - **Output**: Complete token-driven HTML/CSS prototypes
+
+**Input**: Reference images, URLs, or text prompts
+**Output**: `layout-templates.json` for `/workflow:ui-design:generate`
+**Next**: `/workflow:ui-design:generate --session {session_id}`

.claude/commands/workflow/ui-design/style-extract.md

@@ -0,0 +1,271 @@
+---
+name: style-extract
+description: Extract design style from reference images or text prompts using Claude's analysis
+argument-hint: "[--base-path <path>] [--session <id>] [--images "<glob>"] [--prompt "<desc>"] [--mode <imitate|explore>] [--variants <count>]"
+allowed-tools: TodoWrite(*), Read(*), Write(*), Glob(*)
+---
+
+# Style Extraction Command
+
+## Overview
+Extract design style from reference images or text prompts using Claude's built-in analysis. Generates `style-cards.json` with multiple design variants containing token proposals for consolidation.
+
+**Strategy**: AI-Driven Design Space Exploration
+- **Claude-Native**: 100% Claude analysis, no external tools
+- **Single Output**: `style-cards.json` with embedded token proposals
+- **Flexible Input**: Images, text prompts, or both (hybrid mode)
+- **Maximum Contrast**: AI generates maximally divergent design directions
+
+## Phase 0: Setup & Input Validation
+
+### Step 1: Detect Input Mode, Extraction Mode & Base Path
+```bash
+# Detect input source
+# Priority: --images + --prompt → hybrid | --images → image | --prompt → text
+
+# Determine extraction mode
+# Priority: --mode parameter → default "imitate"
+extraction_mode = --mode OR "imitate"  # "imitate" or "explore"
+
+# Set variants count based on mode
+IF extraction_mode == "imitate":
+    variants_count = 1  # Force single variant for imitate mode (ignore --variants)
+ELSE IF extraction_mode == "explore":
+    variants_count = --variants OR 3  # Default to 3 for explore mode
+    VALIDATE: 1 <= variants_count <= 5
+
+# Determine base path
+bash(find .workflow -type d -name "design-*" | head -1)  # Auto-detect
+# OR use --base-path / --session parameters
+```
+
+### Step 2: Load Inputs
+```bash
+# For image mode
+bash(ls {images_pattern})  # Expand glob pattern
+Read({image_path})  # Load each image
+
+# For text mode
+# Validate --prompt is non-empty
+
+# Create output directory
+bash(mkdir -p {base_path}/style-extraction/)
+```
+
+### Step 3: Memory Check (Skip if Already Done)
+```bash
+# Check if already extracted
+bash(test -f {base_path}/style-extraction/style-cards.json && echo "exists")
+```
+
+**If exists**: Skip to completion message
+
+**Output**: `input_mode`, `base_path`, `extraction_mode`, `variants_count`, `loaded_images[]` or `prompt_guidance`
+
+## Phase 1: Design Space Analysis (Explore Mode Only)
+
+### Step 1: Check Extraction Mode
+```bash
+# Check extraction mode
+# extraction_mode == "imitate" → skip this phase
+# extraction_mode == "explore" → execute this phase
+```
+
+**If imitate mode**: Skip to Phase 2
+
+### Step 2: Load Project Context (Explore Mode)
+```bash
+# Load brainstorming context if available
+bash(test -f {base_path}/.brainstorming/synthesis-specification.md && cat it)
+```
+
+### Step 3: Generate Divergent Directions (Claude Native)
+AI analyzes requirements and generates `variants_count` maximally contrasting design directions:
+
+**Input**: User prompt + project context + image count
+**Analysis**: 6D attribute space (color saturation, visual weight, formality, organic/geometric, innovation, density)
+**Output**: JSON with divergent_directions, each having:
+- philosophy_name (2-3 words)
+- design_attributes (specific scores)
+- search_keywords (3-5 keywords)
+- anti_keywords (2-3 keywords)
+- rationale (contrast explanation)
+
+### Step 4: Write Design Space Analysis
+```bash
+bash(echo '{design_space_analysis}' > {base_path}/style-extraction/design-space-analysis.json)
+
+# Verify output
+bash(test -f design-space-analysis.json && echo "saved")
+```
+
+**Output**: `design-space-analysis.json` for consolidation phase
+
+## Phase 2: Style Synthesis & File Write
+
+### Step 1: Claude Native Analysis
+AI generates `variants_count` design style proposals:
+
+**Input**:
+- Input mode (image/text/hybrid)
+- Visual references or text guidance
+- Design space analysis (explore mode only)
+- Variant-specific directions (explore mode only)
+
+**Analysis Rules**:
+- **Explore mode**: Each variant follows pre-defined philosophy and attributes, maintains maximum contrast
+- **Imitate mode**: High-fidelity replication of reference design
+- OKLCH color format
+- Complete token proposals (colors, typography, spacing, border_radius, shadows, breakpoints)
+- WCAG AA accessibility (4.5:1 text, 3:1 UI)
+
+**Output Format**: `style-cards.json` with:
+- extraction_metadata (session_id, input_mode, extraction_mode, timestamp, variants_count)
+- style_cards[] (id, name, description, design_philosophy, preview, proposed_tokens)
+
+### Step 2: Write Style Cards
+```bash
+bash(echo '{style_cards_json}' > {base_path}/style-extraction/style-cards.json)
+```
+
+**Output**: `style-cards.json` with `variants_count` complete variants
+
+## Completion
+
+### Todo Update
+```javascript
+TodoWrite({todos: [
+  {content: "Setup and input validation", status: "completed", activeForm: "Validating inputs"},
+  {content: "Design space analysis (explore mode)", status: "completed", activeForm: "Analyzing design space"},
+  {content: "Style synthesis and file write", status: "completed", activeForm: "Generating style cards"}
+]});
+```
+
+### Output Message
+```
+✅ Style extraction complete!
+
+Configuration:
+- Session: {session_id}
+- Extraction Mode: {extraction_mode} (imitate/explore)
+- Input Mode: {input_mode} (image/text/hybrid)
+- Variants: {variants_count}
+
+{IF extraction_mode == "explore":
+Design Space Analysis:
+- {variants_count} maximally contrasting design directions
+- Min contrast distance: {design_space_analysis.contrast_verification.min_pairwise_distance}
+}
+
+Generated Variants:
+{FOR each card: - {card.name} - {card.design_philosophy}}
+
+Output Files:
+- {base_path}/style-extraction/style-cards.json
+{IF extraction_mode == "explore": - {base_path}/style-extraction/design-space-analysis.json}
+
+Next: /workflow:ui-design:consolidate --session {session_id} --variants {variants_count}
+```
+
+## Simple Bash Commands
+
+### Path Operations
+```bash
+# Find design directory
+bash(find .workflow -type d -name "design-*" | head -1)
+
+# Expand image pattern
+bash(ls {images_pattern})
+
+# Create output directory
+bash(mkdir -p {base_path}/style-extraction/)
+```
+
+### Validation Commands
+```bash
+# Check if already extracted
+bash(test -f {base_path}/style-extraction/style-cards.json && echo "exists")
+
+# Count variants
+bash(cat style-cards.json | grep -c "\"id\": \"variant-")
+
+# Validate JSON
+bash(cat style-cards.json | grep -q "extraction_metadata" && echo "valid")
+```
+
+### File Operations
+```bash
+# Load brainstorming context
+bash(test -f .brainstorming/synthesis-specification.md && cat it)
+
+# Write output
+bash(echo '{json}' > {base_path}/style-extraction/style-cards.json)
+
+# Verify output
+bash(test -f design-space-analysis.json && echo "saved")
+```
+
+## Output Structure
+
+```
+{base_path}/style-extraction/
+├── style-cards.json              # Complete style variants with token proposals
+└── design-space-analysis.json    # Design directions (explore mode only)
+```
+
+## style-cards.json Format
+
+```json
+{
+  "extraction_metadata": {"session_id": "...", "input_mode": "image|text|hybrid", "extraction_mode": "imitate|explore", "timestamp": "...", "variants_count": N},
+  "style_cards": [
+    {
+      "id": "variant-1", "name": "Style Name", "description": "...",
+      "design_philosophy": "Core principles",
+      "preview": {"primary": "oklch(...)", "background": "oklch(...)", "font_heading": "...", "border_radius": "..."},
+      "proposed_tokens": {
+        "colors": {"brand": {...}, "surface": {...}, "semantic": {...}, "text": {...}, "border": {...}},
+        "typography": {"font_family": {...}, "font_size": {...}, "font_weight": {...}, "line_height": {...}, "letter_spacing": {...}},
+        "spacing": {"0": "0", ..., "24": "6rem"},
+        "border_radius": {"none": "0", ..., "full": "9999px"},
+        "shadows": {"sm": "...", ..., "xl": "..."},
+        "breakpoints": {"sm": "640px", ..., "2xl": "1536px"}
+      }
+    }
+    // Repeat for all variants
+  ]
+}
+```
+
+**Requirements**: All colors in OKLCH format, complete token proposals, semantic naming
+
+## Error Handling
+
+### Common Errors
+```
+ERROR: No images found
+→ Check glob pattern
+
+ERROR: Invalid prompt
+→ Provide non-empty string
+
+ERROR: Claude JSON parsing error
+→ Retry with stricter format
+```
+
+## Key Features
+
+- **AI-Driven Design Space Exploration** - 6D attribute space analysis for maximum contrast
+- **Variant-Specific Directions** - Each variant has unique philosophy, keywords, anti-patterns
+- **Maximum Contrast Guarantee** - Variants maximally distant in attribute space
+- **Claude-Native** - No external tools, fast deterministic synthesis
+- **Flexible Input** - Images, text, or hybrid mode
+- **Production-Ready** - OKLCH colors, WCAG AA, semantic naming
+
+## Integration
+
+**Input**: Reference images or text prompts
+**Output**: `style-cards.json` for consolidation
+**Next**: `/workflow:ui-design:consolidate --session {session_id} --variants {count}`
+
+**Note**: This command only extracts visual style (colors, typography, spacing). For layout structure extraction, use `/workflow:ui-design:layout-extract`.

.claude/commands/workflow/ui-design/update.md

@@ -0,0 +1,284 @@
+---
+name: update
+description: Update brainstorming artifacts with finalized design system references
+argument-hint: --session <session_id> [--selected-prototypes "<list>"]
+allowed-tools: Read(*), Write(*), Edit(*), TodoWrite(*), Glob(*), Bash(*)
+---
+
+# Design Update Command
+
+## Overview
+
+Synchronize finalized design system references to brainstorming artifacts, preparing them for `/workflow:plan` consumption. This command updates **references only** (via @ notation), not content duplication.
+
+## Core Philosophy
+
+- **Reference-Only Updates**: Use @ references, no content duplication
+- **Main Claude Execution**: Direct updates by main Claude (no Agent handoff)
+- **Synthesis Alignment**: Update synthesis-specification.md UI/UX Guidelines section
+- **Plan-Ready Output**: Ensure design artifacts discoverable by task-generate
+- **Minimal Reading**: Verify file existence, don't read design content
+
+## Execution Protocol
+
+### Phase 1: Session & Artifact Validation
+
+```bash
+# Validate session
+CHECK: .workflow/.active-* marker files; VALIDATE: session_id matches active session
+
+# Verify design artifacts in latest design run
+latest_design = find_latest_path_matching(".workflow/WFS-{session}/design-*")
+
+# Detect design system structure (unified vs separate)
+IF exists({latest_design}/style-consolidation/design-tokens.json):
+    design_system_mode = "unified"; design_tokens_path = "style-consolidation/design-tokens.json"; style_guide_path = "style-consolidation/style-guide.md"
+ELSE IF exists({latest_design}/style-consolidation/style-1/design-tokens.json):
+    design_system_mode = "separate"; design_tokens_path = "style-consolidation/style-1/design-tokens.json"; style_guide_path = "style-consolidation/style-1/style-guide.md"
+ELSE:
+    ERROR: "No design tokens found. Run /workflow:ui-design:consolidate first"
+
+VERIFY: {latest_design}/{design_tokens_path}, {latest_design}/{style_guide_path}, {latest_design}/prototypes/*.html
+
+REPORT: "📋 Design system mode: {design_system_mode} | Tokens: {design_tokens_path}"
+
+# Prototype selection
+selected_list = --selected-prototypes ? parse_comma_separated(--selected-prototypes) : Glob({latest_design}/prototypes/*.html)
+VALIDATE: Specified prototypes exist IF --selected-prototypes
+
+REPORT: "Found {count} design artifacts, {prototype_count} prototypes"
+```
+
+### Phase 1.1: Memory Check (Skip if Already Updated)
+
+```bash
+# Check if synthesis-specification.md contains current design run reference
+synthesis_spec_path = ".workflow/WFS-{session}/.brainstorming/synthesis-specification.md"
+current_design_run = basename(latest_design)  # e.g., "design-run-20250109-143022"
+
+IF exists(synthesis_spec_path):
+    synthesis_content = Read(synthesis_spec_path)
+    IF "## UI/UX Guidelines" in synthesis_content AND current_design_run in synthesis_content:
+        REPORT: "✅ Design system references already updated (found in memory)"
+        REPORT: "   Skipping: Phase 2-5 (Load Target Artifacts, Update Synthesis, Update UI Designer Guide, Completion)"
+        EXIT 0
+```
+
+### Phase 2: Load Target Artifacts Only
+
+**What to Load**: Only the files we need to **update**, not the design files we're referencing.
+
+```bash
+# Load target brainstorming artifacts (files to be updated)
+Read(.workflow/WFS-{session}/.brainstorming/synthesis-specification.md)
+IF exists(.workflow/WFS-{session}/.brainstorming/ui-designer/analysis.md): Read(analysis.md)
+
+# Optional: Read prototype notes for descriptions (minimal context)
+FOR each selected_prototype IN selected_list:
+    Read({latest_design}/prototypes/{selected_prototype}-notes.md)  # Extract: layout_strategy, page_name only
+
+# Note: Do NOT read design-tokens.json, style-guide.md, or prototype HTML. Only verify existence and generate @ references.
+```
+
+### Phase 3: Update Synthesis Specification
+
+Update `.brainstorming/synthesis-specification.md` with design system references.
+
+**Target Section**: `## UI/UX Guidelines`
+
+**Content Template**:
+```markdown
+## UI/UX Guidelines
+
+### Design System Reference
+**Finalized Design Tokens**: @../design-{run_id}/{design_tokens_path}
+**Style Guide**: @../design-{run_id}/{style_guide_path}
+**Design System Mode**: {design_system_mode}
+
+### Implementation Requirements
+**Token Adherence**: All UI implementations MUST use design token CSS custom properties
+**Accessibility**: WCAG AA compliance validated in design-tokens.json
+**Responsive**: Mobile-first design using token-based breakpoints
+**Component Patterns**: Follow patterns documented in style-guide.md
+
+### Reference Prototypes
+{FOR each selected_prototype:
+- **{page_name}**: @../design-{run_id}/prototypes/{prototype}.html | Layout: {layout_strategy from notes}
+}
+
+### Design System Assets
+```json
+{"design_tokens": "design-{run_id}/{design_tokens_path}", "style_guide": "design-{run_id}/{style_guide_path}", "design_system_mode": "{design_system_mode}", "prototypes": [{FOR each: "design-{run_id}/prototypes/{prototype}.html"}]}
+```
+```
+
+**Implementation**:
+```bash
+# Option 1: Edit existing section
+Edit(file_path=".workflow/WFS-{session}/.brainstorming/synthesis-specification.md",
+     old_string="## UI/UX Guidelines\n[existing content]",
+     new_string="## UI/UX Guidelines\n\n[new design reference content]")
+
+# Option 2: Append if section doesn't exist
+IF section not found:
+    Edit(file_path="...", old_string="[end of document]", new_string="\n\n## UI/UX Guidelines\n\n[new design reference content]")
+```
+
+### Phase 4: Update UI Designer Style Guide
+
+Create or update `.brainstorming/ui-designer/style-guide.md`:
+
+```markdown
+# UI Designer Style Guide
+
+## Design System Integration
+This style guide references the finalized design system from the design refinement phase.
+
+**Design Tokens**: @../../design-{run_id}/{design_tokens_path}
+**Style Guide**: @../../design-{run_id}/{style_guide_path}
+**Design System Mode**: {design_system_mode}
+
+## Implementation Guidelines
+1. **Use CSS Custom Properties**: All styles reference design tokens
+2. **Follow Semantic HTML**: Use HTML5 semantic elements
+3. **Maintain Accessibility**: WCAG AA compliance required
+4. **Responsive Design**: Mobile-first with token-based breakpoints
+
+## Reference Prototypes
+{FOR each selected_prototype:
+- **{page_name}**: @../../design-{run_id}/prototypes/{prototype}.html
+}
+
+## Token System
+For complete token definitions and usage examples, see:
+- Design Tokens: @../../design-{run_id}/{design_tokens_path}
+- Style Guide: @../../design-{run_id}/{style_guide_path}
+
+---
+*Auto-generated by /workflow:ui-design:update | Last updated: {timestamp}*
+```
+
+**Implementation**:
+```bash
+Write(file_path=".workflow/WFS-{session}/.brainstorming/ui-designer/style-guide.md",
+      content="[generated content with @ references]")
+```
+
+### Phase 5: Completion
+
+```javascript
+TodoWrite({todos: [
+  {content: "Validate session and design system artifacts", status: "completed", activeForm: "Validating artifacts"},
+  {content: "Load target brainstorming artifacts", status: "completed", activeForm: "Loading target files"},
+  {content: "Update synthesis-specification.md with design references", status: "completed", activeForm: "Updating synthesis spec"},
+  {content: "Create/update ui-designer/style-guide.md", status: "completed", activeForm: "Updating UI designer guide"}
+]});
+```
+
+**Completion Message**:
+```
+✅ Design system references updated for session: WFS-{session}
+
+Updated artifacts:
+✓ synthesis-specification.md - UI/UX Guidelines section with @ references
+✓ ui-designer/style-guide.md - Design system reference guide
+
+Design system assets ready for /workflow:plan:
+- design-tokens.json | style-guide.md | {prototype_count} reference prototypes
+
+Next: /workflow:plan [--agent] "<task description>"
+      The plan phase will automatically discover and utilize the design system.
+```
+
+## Output Structure
+
+**Updated Files**:
+```
+.workflow/WFS-{session}/.brainstorming/
+├── synthesis-specification.md       # Updated with UI/UX Guidelines section
+└── ui-designer/
+    └── style-guide.md               # New or updated design reference guide
+```
+
+**@ Reference Format** (synthesis-specification.md):
+```
+@../design-{run_id}/style-consolidation/design-tokens.json
+@../design-{run_id}/style-consolidation/style-guide.md
+@../design-{run_id}/prototypes/{prototype}.html
+```
+
+**@ Reference Format** (ui-designer/style-guide.md):
+```
+@../../design-{run_id}/style-consolidation/design-tokens.json
+@../../design-{run_id}/style-consolidation/style-guide.md
+@../../design-{run_id}/prototypes/{prototype}.html
+```
+
+## Integration with /workflow:plan
+
+After this update, `/workflow:plan` will discover design assets through:
+
+**Phase 3: Intelligent Analysis** (`/workflow:tools:concept-enhanced`)
+- Reads synthesis-specification.md → Discovers @ references → Includes design system context in ANALYSIS_RESULTS.md
+
+**Phase 4: Task Generation** (`/workflow:tools:task-generate`)
+- Reads ANALYSIS_RESULTS.md → Discovers design assets → Includes design system paths in task JSON files
+
+**Example Task JSON** (generated by task-generate):
+```json
+{
+  "task_id": "IMPL-001",
+  "context": {
+    "design_system": {
+      "tokens": "design-{run_id}/style-consolidation/design-tokens.json",
+      "style_guide": "design-{run_id}/style-consolidation/style-guide.md",
+      "prototypes": ["design-{run_id}/prototypes/dashboard-variant-1.html"]
+    }
+  }
+}
+```
+
+## Error Handling
+
+- **Missing design artifacts**: Error with message "Run /workflow:ui-design:consolidate and /workflow:ui-design:generate first"
+- **synthesis-specification.md not found**: Warning, create minimal version with just UI/UX Guidelines
+- **ui-designer/ directory missing**: Create directory and file
+- **Edit conflicts**: Preserve existing content, append or replace only UI/UX Guidelines section
+- **Invalid prototype names**: Skip invalid entries, continue with valid ones
+
+## Validation Checks
+
+After update, verify:
+- [ ] synthesis-specification.md contains UI/UX Guidelines section
+- [ ] UI/UX Guidelines include @ references (not content duplication)
+- [ ] ui-designer/style-guide.md created or updated
+- [ ] All @ referenced files exist and are accessible
+- [ ] @ reference paths are relative and correct
+
+## Key Features
+
+1. **Reference-Only Updates**: Uses @ notation for file references, no content duplication, lightweight and maintainable
+2. **Main Claude Direct Execution**: No Agent handoff (preserves context), simple reference generation, reliable path resolution
+3. **Plan-Ready Output**: `/workflow:plan` Phase 3 can discover design system, task generation includes design asset paths, clear integration points
+4. **Minimal Reading**: Only reads target files to update, verifies design file existence (no content reading), optional prototype notes for descriptions
+5. **Flexible Prototype Selection**: Auto-select all prototypes (default), manual selection via --selected-prototypes parameter, validates existence
+
+## Integration Points
+
+- **Input**: Design system artifacts from `/workflow:ui-design:consolidate` and `/workflow:ui-design:generate`
+- **Output**: Updated synthesis-specification.md, ui-designer/style-guide.md with @ references
+- **Next Phase**: `/workflow:plan` discovers and utilizes design system through @ references
+- **Auto Integration**: Automatically triggered by `/workflow:ui-design:auto` workflow
+
+## Why Main Claude Execution?
+
+This command is executed directly by main Claude (not delegated to an Agent) because:
+
+1. **Simple Reference Generation**: Only generating file paths, not complex synthesis
+2. **Context Preservation**: Main Claude has full session and conversation context
+3. **Minimal Transformation**: Primarily updating references, not analyzing content
+4. **Path Resolution**: Requires precise relative path calculation
+5. **Edit Operations**: Better error recovery for Edit conflicts
+6. **Synthesis Pattern**: Follows same direct-execution pattern as other reference updates
+
+This ensures reliable, lightweight integration without Agent handoff overhead.

.claude/prompt-templates/plan.md

@@ -1,10 +1,3 @@
----
-name: plan
-description: 软件架构规划和技术实现计划分析模板
-category: planning
-keywords: [规划, 架构, 实现计划, 技术设计, 修改方案]
----
-
 # 软件架构规划模板
 # AI Persona & Core Mission
 

.claude/scripts/convert_tokens_to_css.sh

@@ -0,0 +1,225 @@
+#!/bin/bash
+# Convert design-tokens.json to tokens.css with Google Fonts import and global font rules
+# Usage: cat design-tokens.json | ./convert_tokens_to_css.sh > tokens.css
+# Or: ./convert_tokens_to_css.sh < design-tokens.json > tokens.css
+
+# Read JSON from stdin
+json_input=$(cat)
+
+# Extract metadata for header comment
+style_name=$(echo "$json_input" | jq -r '.meta.name // "Unknown Style"' 2>/dev/null || echo "Design Tokens")
+
+# Generate header
+cat <<EOF
+/* ========================================
+   Design Tokens: ${style_name}
+   Auto-generated from design-tokens.json
+   ======================================== */
+
+EOF
+
+# ========================================
+# Google Fonts Import Generation
+# ========================================
+# Extract font families and generate Google Fonts import URL
+fonts=$(echo "$json_input" | jq -r '
+  .typography.font_family | to_entries[] | .value
+' 2>/dev/null | sed "s/'//g" | cut -d',' -f1 | sort -u)
+
+# Build Google Fonts URL
+google_fonts_url="https://fonts.googleapis.com/css2?"
+font_params=""
+
+while IFS= read -r font; do
+  # Skip system fonts and empty lines
+  if [[ -z "$font" ]] || [[ "$font" =~ ^(system-ui|sans-serif|serif|monospace|cursive|fantasy)$ ]]; then
+    continue
+  fi
+
+  # Special handling for common web fonts with weights
+  case "$font" in
+    "Comic Neue")
+      font_params+="family=Comic+Neue:wght@300;400;700&"
+      ;;
+    "Patrick Hand"|"Caveat"|"Dancing Script"|"Architects Daughter"|"Indie Flower"|"Shadows Into Light"|"Permanent Marker")
+      # URL-encode font name and add common weights
+      encoded_font=$(echo "$font" | sed 's/ /+/g')
+      font_params+="family=${encoded_font}:wght@400;700&"
+      ;;
+    "Segoe Print"|"Bradley Hand"|"Chilanka")
+      # These are system fonts, skip
+      ;;
+    *)
+      # Generic font: add with default weights
+      encoded_font=$(echo "$font" | sed 's/ /+/g')
+      font_params+="family=${encoded_font}:wght@400;500;600;700&"
+      ;;
+  esac
+done <<< "$fonts"
+
+# Generate @import if we have fonts
+if [[ -n "$font_params" ]]; then
+  # Remove trailing &
+  font_params="${font_params%&}"
+  echo "/* Import Web Fonts */"
+  echo "@import url('${google_fonts_url}${font_params}&display=swap');"
+  echo ""
+fi
+
+# ========================================
+# CSS Custom Properties Generation
+# ========================================
+echo ":root {"
+
+# Colors - Brand
+echo "  /* Colors - Brand */"
+echo "$json_input" | jq -r '
+  .colors.brand | to_entries[] |
+  "  --color-brand-\(.key): \(.value);"
+' 2>/dev/null
+
+echo ""
+
+# Colors - Surface
+echo "  /* Colors - Surface */"
+echo "$json_input" | jq -r '
+  .colors.surface | to_entries[] |
+  "  --color-surface-\(.key): \(.value);"
+' 2>/dev/null
+
+echo ""
+
+# Colors - Semantic
+echo "  /* Colors - Semantic */"
+echo "$json_input" | jq -r '
+  .colors.semantic | to_entries[] |
+  "  --color-semantic-\(.key): \(.value);"
+' 2>/dev/null
+
+echo ""
+
+# Colors - Text
+echo "  /* Colors - Text */"
+echo "$json_input" | jq -r '
+  .colors.text | to_entries[] |
+  "  --color-text-\(.key): \(.value);"
+' 2>/dev/null
+
+echo ""
+
+# Colors - Border
+echo "  /* Colors - Border */"
+echo "$json_input" | jq -r '
+  .colors.border | to_entries[] |
+  "  --color-border-\(.key): \(.value);"
+' 2>/dev/null
+
+echo ""
+
+# Typography - Font Family
+echo "  /* Typography - Font Family */"
+echo "$json_input" | jq -r '
+  .typography.font_family | to_entries[] |
+  "  --font-family-\(.key): \(.value);"
+' 2>/dev/null
+
+echo ""
+
+# Typography - Font Size
+echo "  /* Typography - Font Size */"
+echo "$json_input" | jq -r '
+  .typography.font_size | to_entries[] |
+  "  --font-size-\(.key): \(.value);"
+' 2>/dev/null
+
+echo ""
+
+# Typography - Font Weight
+echo "  /* Typography - Font Weight */"
+echo "$json_input" | jq -r '
+  .typography.font_weight | to_entries[] |
+  "  --font-weight-\(.key): \(.value);"
+' 2>/dev/null
+
+echo ""
+
+# Typography - Line Height
+echo "  /* Typography - Line Height */"
+echo "$json_input" | jq -r '
+  .typography.line_height | to_entries[] |
+  "  --line-height-\(.key): \(.value);"
+' 2>/dev/null
+
+echo ""
+
+# Typography - Letter Spacing
+echo "  /* Typography - Letter Spacing */"
+echo "$json_input" | jq -r '
+  .typography.letter_spacing | to_entries[] |
+  "  --letter-spacing-\(.key): \(.value);"
+' 2>/dev/null
+
+echo ""
+
+# Spacing
+echo "  /* Spacing */"
+echo "$json_input" | jq -r '
+  .spacing | to_entries[] |
+  "  --spacing-\(.key): \(.value);"
+' 2>/dev/null
+
+echo ""
+
+# Border Radius
+echo "  /* Border Radius */"
+echo "$json_input" | jq -r '
+  .border_radius | to_entries[] |
+  "  --border-radius-\(.key): \(.value);"
+' 2>/dev/null
+
+echo ""
+
+# Shadows
+echo "  /* Shadows */"
+echo "$json_input" | jq -r '
+  .shadows | to_entries[] |
+  "  --shadow-\(.key): \(.value);"
+' 2>/dev/null
+
+echo ""
+
+# Breakpoints
+echo "  /* Breakpoints */"
+echo "$json_input" | jq -r '
+  .breakpoints | to_entries[] |
+  "  --breakpoint-\(.key): \(.value);"
+' 2>/dev/null
+
+echo "}"
+echo ""
+
+# ========================================
+# Global Font Application
+# ========================================
+echo "/* ========================================"
+echo "   Global Font Application"
+echo "   ======================================== */"
+echo ""
+echo "body {"
+echo "  font-family: var(--font-family-body);"
+echo "  font-size: var(--font-size-base);"
+echo "  line-height: var(--line-height-normal);"
+echo "  color: var(--color-text-primary);"
+echo "  background-color: var(--color-surface-background);"
+echo "}"
+echo ""
+echo "h1, h2, h3, h4, h5, h6, legend {"
+echo "  font-family: var(--font-family-heading);"
+echo "}"
+echo ""
+echo "/* Reset default margins for better control */"
+echo "* {"
+echo "  margin: 0;"
+echo "  padding: 0;"
+echo "  box-sizing: border-box;"
+echo "}"

.claude/scripts/ui-generate-preview.sh

@@ -0,0 +1,391 @@
+#!/bin/bash
+#
+# UI Generate Preview v2.0 - Template-Based Preview Generation
+# Purpose: Generate compare.html and index.html using template substitution
+# Template: ~/.claude/workflows/_template-compare-matrix.html
+#
+# Usage: ui-generate-preview.sh <prototypes_dir> [--template <path>]
+#
+
+set -e
+
+# Color output
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+NC='\033[0m' # No Color
+
+# Default template path
+TEMPLATE_PATH="$HOME/.claude/workflows/_template-compare-matrix.html"
+
+# Parse arguments
+prototypes_dir="${1:-.}"
+shift || true
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --template)
+            TEMPLATE_PATH="$2"
+            shift 2
+            ;;
+        *)
+            echo -e "${RED}Unknown option: $1${NC}"
+            exit 1
+            ;;
+    esac
+done
+
+if [[ ! -d "$prototypes_dir" ]]; then
+    echo -e "${RED}Error: Directory not found: $prototypes_dir${NC}"
+    exit 1
+fi
+
+cd "$prototypes_dir" || exit 1
+
+echo -e "${GREEN}📊 Auto-detecting matrix dimensions...${NC}"
+
+# Auto-detect styles, layouts, targets from file patterns
+# Pattern: {target}-style-{s}-layout-{l}.html
+styles=$(find . -maxdepth 1 -name "*-style-*-layout-*.html" | \
+         sed 's/.*-style-\([0-9]\+\)-.*/\1/' | sort -un)
+layouts=$(find . -maxdepth 1 -name "*-style-*-layout-*.html" | \
+          sed 's/.*-layout-\([0-9]\+\)\.html/\1/' | sort -un)
+targets=$(find . -maxdepth 1 -name "*-style-*-layout-*.html" | \
+          sed 's/\.\///; s/-style-.*//' | sort -u)
+
+S=$(echo "$styles" | wc -l)
+L=$(echo "$layouts" | wc -l)
+T=$(echo "$targets" | wc -l)
+
+echo -e "   Detected: ${GREEN}${S}${NC} styles × ${GREEN}${L}${NC} layouts × ${GREEN}${T}${NC} targets"
+
+if [[ $S -eq 0 ]] || [[ $L -eq 0 ]] || [[ $T -eq 0 ]]; then
+    echo -e "${RED}Error: No prototype files found matching pattern {target}-style-{s}-layout-{l}.html${NC}"
+    exit 1
+fi
+
+# ============================================================================
+# Generate compare.html from template
+# ============================================================================
+
+echo -e "${YELLOW}🎨 Generating compare.html from template...${NC}"
+
+if [[ ! -f "$TEMPLATE_PATH" ]]; then
+    echo -e "${RED}Error: Template not found: $TEMPLATE_PATH${NC}"
+    exit 1
+fi
+
+# Build pages/targets JSON array
+PAGES_JSON="["
+first=true
+for target in $targets; do
+    if [[ "$first" == true ]]; then
+        first=false
+    else
+        PAGES_JSON+=", "
+    fi
+    PAGES_JSON+="\"$target\""
+done
+PAGES_JSON+="]"
+
+# Generate metadata
+RUN_ID="run-$(date +%Y%m%d-%H%M%S)"
+SESSION_ID="standalone"
+TIMESTAMP=$(date -u +%Y-%m-%dT%H:%M:%SZ 2>/dev/null || date -u +"%Y-%m-%d")
+
+# Replace placeholders in template
+cat "$TEMPLATE_PATH" | \
+    sed "s|{{run_id}}|${RUN_ID}|g" | \
+    sed "s|{{session_id}}|${SESSION_ID}|g" | \
+    sed "s|{{timestamp}}|${TIMESTAMP}|g" | \
+    sed "s|{{style_variants}}|${S}|g" | \
+    sed "s|{{layout_variants}}|${L}|g" | \
+    sed "s|{{pages_json}}|${PAGES_JSON}|g" \
+    > compare.html
+
+echo -e "${GREEN}   ✓ Generated compare.html from template${NC}"
+
+# ============================================================================
+# Generate index.html
+# ============================================================================
+
+echo -e "${YELLOW}📋 Generating index.html...${NC}"
+
+cat > index.html << 'EOF'
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>UI Prototypes Index</title>
+    <style>
+        * { margin: 0; padding: 0; box-sizing: border-box; }
+        body {
+            font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
+            max-width: 1200px;
+            margin: 0 auto;
+            padding: 40px 20px;
+            background: #f5f5f5;
+        }
+        h1 { margin-bottom: 10px; color: #333; }
+        .subtitle { color: #666; margin-bottom: 30px; }
+        .cta {
+            background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+            color: white;
+            padding: 20px;
+            border-radius: 8px;
+            margin-bottom: 30px;
+            box-shadow: 0 4px 6px rgba(0,0,0,0.1);
+        }
+        .cta h2 { margin-bottom: 10px; }
+        .cta a {
+            display: inline-block;
+            background: white;
+            color: #667eea;
+            padding: 10px 20px;
+            border-radius: 6px;
+            text-decoration: none;
+            font-weight: 600;
+            margin-top: 10px;
+        }
+        .cta a:hover { background: #f8f9fa; }
+        .style-section {
+            background: white;
+            padding: 20px;
+            border-radius: 8px;
+            margin-bottom: 20px;
+            box-shadow: 0 2px 4px rgba(0,0,0,0.1);
+        }
+        .style-section h2 {
+            color: #495057;
+            margin-bottom: 15px;
+            padding-bottom: 10px;
+            border-bottom: 2px solid #e9ecef;
+        }
+        .target-group {
+            margin-bottom: 20px;
+        }
+        .target-group h3 {
+            color: #6c757d;
+            font-size: 16px;
+            margin-bottom: 10px;
+        }
+        .link-grid {
+            display: grid;
+            grid-template-columns: repeat(auto-fill, minmax(200px, 1fr));
+            gap: 10px;
+        }
+        .prototype-link {
+            padding: 12px 16px;
+            background: #f8f9fa;
+            border: 1px solid #dee2e6;
+            border-radius: 6px;
+            text-decoration: none;
+            color: #495057;
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+            transition: all 0.2s;
+        }
+        .prototype-link:hover {
+            background: #e9ecef;
+            border-color: #667eea;
+            transform: translateX(2px);
+        }
+        .prototype-link .label { font-weight: 500; }
+        .prototype-link .icon { color: #667eea; }
+    </style>
+</head>
+<body>
+    <h1>🎨 UI Prototypes Index</h1>
+    <p class="subtitle">Generated __S__×__L__×__T__ = __TOTAL__ prototypes</p>
+
+    <div class="cta">
+        <h2>📊 Interactive Comparison</h2>
+        <p>View all styles and layouts side-by-side in an interactive matrix</p>
+        <a href="compare.html">Open Matrix View →</a>
+    </div>
+
+    <h2>📂 All Prototypes</h2>
+__CONTENT__
+</body>
+</html>
+EOF
+
+# Build content HTML
+CONTENT=""
+for style in $styles; do
+    CONTENT+="<div class='style-section'>"$'\n'
+    CONTENT+="<h2>Style ${style}</h2>"$'\n'
+
+    for target in $targets; do
+        target_capitalized="$(echo ${target:0:1} | tr '[:lower:]' '[:upper:]')${target:1}"
+        CONTENT+="<div class='target-group'>"$'\n'
+        CONTENT+="<h3>${target_capitalized}</h3>"$'\n'
+        CONTENT+="<div class='link-grid'>"$'\n'
+
+        for layout in $layouts; do
+            html_file="${target}-style-${style}-layout-${layout}.html"
+            if [[ -f "$html_file" ]]; then
+                CONTENT+="<a href='${html_file}' class='prototype-link' target='_blank'>"$'\n'
+                CONTENT+="<span class='label'>Layout ${layout}</span>"$'\n'
+                CONTENT+="<span class='icon'>↗</span>"$'\n'
+                CONTENT+="</a>"$'\n'
+            fi
+        done
+
+        CONTENT+="</div></div>"$'\n'
+    done
+
+    CONTENT+="</div>"$'\n'
+done
+
+# Calculate total
+TOTAL_PROTOTYPES=$((S * L * T))
+
+# Replace placeholders (using a temp file for complex replacement)
+{
+    echo "$CONTENT" > /tmp/content_tmp.txt
+    sed "s|__S__|${S}|g" index.html | \
+        sed "s|__L__|${L}|g" | \
+        sed "s|__T__|${T}|g" | \
+        sed "s|__TOTAL__|${TOTAL_PROTOTYPES}|g" | \
+        sed -e "/__CONTENT__/r /tmp/content_tmp.txt" -e "/__CONTENT__/d" > /tmp/index_tmp.html
+    mv /tmp/index_tmp.html index.html
+    rm -f /tmp/content_tmp.txt
+}
+
+echo -e "${GREEN}   ✓ Generated index.html${NC}"
+
+# ============================================================================
+# Generate PREVIEW.md
+# ============================================================================
+
+echo -e "${YELLOW}📝 Generating PREVIEW.md...${NC}"
+
+cat > PREVIEW.md << EOF
+# UI Prototypes Preview Guide
+
+Generated: $(date +"%Y-%m-%d %H:%M:%S")
+
+## 📊 Matrix Dimensions
+
+- **Styles**: ${S}
+- **Layouts**: ${L}
+- **Targets**: ${T}
+- **Total Prototypes**: $((S*L*T))
+
+## 🌐 How to View
+
+### Option 1: Interactive Matrix (Recommended)
+
+Open \`compare.html\` in your browser to see all prototypes in an interactive matrix view.
+
+**Features**:
+- Side-by-side comparison of all styles and layouts
+- Switch between targets using the dropdown
+- Adjust grid columns for better viewing
+- Direct links to full-page views
+- Selection system with export to JSON
+- Fullscreen mode for detailed inspection
+
+### Option 2: Simple Index
+
+Open \`index.html\` for a simple list of all prototypes with direct links.
+
+### Option 3: Direct File Access
+
+Each prototype can be opened directly:
+- Pattern: \`{target}-style-{s}-layout-{l}.html\`
+- Example: \`dashboard-style-1-layout-1.html\`
+
+## 📁 File Structure
+
+\`\`\`
+prototypes/
+├── compare.html           # Interactive matrix view
+├── index.html             # Simple navigation index
+├── PREVIEW.md             # This file
+EOF
+
+for style in $styles; do
+    for target in $targets; do
+        for layout in $layouts; do
+            echo "├── ${target}-style-${style}-layout-${layout}.html" >> PREVIEW.md
+            echo "├── ${target}-style-${style}-layout-${layout}.css" >> PREVIEW.md
+        done
+    done
+done
+
+cat >> PREVIEW.md << 'EOF2'
+```
+
+## 🎨 Style Variants
+
+EOF2
+
+for style in $styles; do
+    cat >> PREVIEW.md << EOF3
+### Style ${style}
+
+EOF3
+    style_guide="../style-consolidation/style-${style}/style-guide.md"
+    if [[ -f "$style_guide" ]]; then
+        head -n 10 "$style_guide" | tail -n +2 >> PREVIEW.md 2>/dev/null || echo "Design philosophy and tokens" >> PREVIEW.md
+    else
+        echo "Design system ${style}" >> PREVIEW.md
+    fi
+    echo "" >> PREVIEW.md
+done
+
+cat >> PREVIEW.md << 'EOF4'
+
+## 🎯 Targets
+
+EOF4
+
+for target in $targets; do
+    target_capitalized="$(echo ${target:0:1} | tr '[:lower:]' '[:upper:]')${target:1}"
+    echo "- **${target_capitalized}**: ${L} layouts × ${S} styles = $((L*S)) variations" >> PREVIEW.md
+done
+
+cat >> PREVIEW.md << 'EOF5'
+
+## 💡 Tips
+
+1. **Comparison**: Use compare.html to see how different styles affect the same layout
+2. **Navigation**: Use index.html for quick access to specific prototypes
+3. **Selection**: Mark favorites in compare.html using star icons
+4. **Export**: Download selection JSON for implementation planning
+5. **Inspection**: Open browser DevTools to inspect HTML structure and CSS
+6. **Sharing**: All files are standalone - can be shared or deployed directly
+
+## 📝 Next Steps
+
+1. Review prototypes in compare.html
+2. Select preferred style × layout combinations
+3. Export selections as JSON
+4. Provide feedback for refinement
+5. Use selected designs for implementation
+
+---
+
+Generated by /workflow:ui-design:generate-v2 (Style-Centric Architecture)
+EOF5
+
+echo -e "${GREEN}   ✓ Generated PREVIEW.md${NC}"
+
+# ============================================================================
+# Completion Summary
+# ============================================================================
+
+echo ""
+echo -e "${GREEN}✅ Preview generation complete!${NC}"
+echo -e "   Files created: compare.html, index.html, PREVIEW.md"
+echo -e "   Matrix: ${S} styles × ${L} layouts × ${T} targets = $((S*L*T)) prototypes"
+echo ""
+echo -e "${YELLOW}🌐 Next Steps:${NC}"
+echo -e "   1. Open compare.html for interactive matrix view"
+echo -e "   2. Open index.html for simple navigation"
+echo -e "   3. Read PREVIEW.md for detailed usage guide"
+echo ""

.claude/scripts/ui-instantiate-prototypes.sh

@@ -0,0 +1,811 @@
+#!/bin/bash
+
+# UI Prototype Instantiation Script with Preview Generation (v3.0 - Auto-detect)
+# Purpose: Generate S × L × P final prototypes from templates + interactive preview files
+# Usage:
+#   Simple: ui-instantiate-prototypes.sh <prototypes_dir>
+#   Full:   ui-instantiate-prototypes.sh <base_path> <pages> <style_variants> <layout_variants> [options]
+
+# Use safer error handling
+set -o pipefail
+
+# ============================================================================
+# Helper Functions
+# ============================================================================
+
+log_info() {
+    echo "$1"
+}
+
+log_success() {
+    echo "✅ $1"
+}
+
+log_error() {
+    echo "❌ $1"
+}
+
+log_warning() {
+    echo "⚠️  $1"
+}
+
+# Auto-detect pages from templates directory
+auto_detect_pages() {
+    local templates_dir="$1/_templates"
+
+    if [ ! -d "$templates_dir" ]; then
+        log_error "Templates directory not found: $templates_dir"
+        return 1
+    fi
+
+    # Find unique page names from template files (e.g., login-layout-1.html -> login)
+    local pages=$(find "$templates_dir" -name "*-layout-*.html" -type f | \
+                  sed 's|.*/||' | \
+                  sed 's|-layout-[0-9]*\.html||' | \
+                  sort -u | \
+                  tr '\n' ',' | \
+                  sed 's/,$//')
+
+    echo "$pages"
+}
+
+# Auto-detect style variants count
+auto_detect_style_variants() {
+    local base_path="$1"
+    local style_dir="$base_path/../style-consolidation"
+
+    if [ ! -d "$style_dir" ]; then
+        log_warning "Style consolidation directory not found: $style_dir"
+        echo "3"  # Default
+        return
+    fi
+
+    # Count style-* directories
+    local count=$(find "$style_dir" -maxdepth 1 -type d -name "style-*" | wc -l)
+
+    if [ "$count" -eq 0 ]; then
+        echo "3"  # Default
+    else
+        echo "$count"
+    fi
+}
+
+# Auto-detect layout variants count
+auto_detect_layout_variants() {
+    local templates_dir="$1/_templates"
+
+    if [ ! -d "$templates_dir" ]; then
+        echo "3"  # Default
+        return
+    fi
+
+    # Find the first page and count its layouts
+    local first_page=$(find "$templates_dir" -name "*-layout-1.html" -type f | head -1 | sed 's|.*/||' | sed 's|-layout-1\.html||')
+
+    if [ -z "$first_page" ]; then
+        echo "3"  # Default
+        return
+    fi
+
+    # Count layout files for this page
+    local count=$(find "$templates_dir" -name "${first_page}-layout-*.html" -type f | wc -l)
+
+    if [ "$count" -eq 0 ]; then
+        echo "3"  # Default
+    else
+        echo "$count"
+    fi
+}
+
+# ============================================================================
+# Parse Arguments
+# ============================================================================
+
+show_usage() {
+    cat <<'EOF'
+Usage:
+  Simple (auto-detect): ui-instantiate-prototypes.sh <prototypes_dir> [options]
+  Full:                 ui-instantiate-prototypes.sh <base_path> <pages> <style_variants> <layout_variants> [options]
+
+Simple Mode (Recommended):
+  prototypes_dir    Path to prototypes directory (auto-detects everything)
+
+Full Mode:
+  base_path         Base path to prototypes directory
+  pages             Comma-separated list of pages/components
+  style_variants    Number of style variants (1-5)
+  layout_variants   Number of layout variants (1-5)
+
+Options:
+  --run-id <id>         Run ID (default: auto-generated)
+  --session-id <id>     Session ID (default: standalone)
+  --mode <page|component>  Exploration mode (default: page)
+  --template <path>     Path to compare.html template (default: ~/.claude/workflows/_template-compare-matrix.html)
+  --no-preview          Skip preview file generation
+  --help                Show this help message
+
+Examples:
+  # Simple usage (auto-detect everything)
+  ui-instantiate-prototypes.sh .design/prototypes
+
+  # With options
+  ui-instantiate-prototypes.sh .design/prototypes --session-id WFS-auth
+
+  # Full manual mode
+  ui-instantiate-prototypes.sh .design/prototypes "login,dashboard" 3 3 --session-id WFS-auth
+EOF
+}
+
+# Default values
+BASE_PATH=""
+PAGES=""
+STYLE_VARIANTS=""
+LAYOUT_VARIANTS=""
+RUN_ID="run-$(date +%Y%m%d-%H%M%S)"
+SESSION_ID="standalone"
+MODE="page"
+TEMPLATE_PATH="$HOME/.claude/workflows/_template-compare-matrix.html"
+GENERATE_PREVIEW=true
+AUTO_DETECT=false
+
+# Parse arguments
+if [ $# -lt 1 ]; then
+    log_error "Missing required arguments"
+    show_usage
+    exit 1
+fi
+
+# Check if using simple mode (only 1 positional arg before options)
+if [ $# -eq 1 ] || [[ "$2" == --* ]]; then
+    # Simple mode - auto-detect
+    AUTO_DETECT=true
+    BASE_PATH="$1"
+    shift 1
+else
+    # Full mode - manual parameters
+    if [ $# -lt 4 ]; then
+        log_error "Full mode requires 4 positional arguments"
+        show_usage
+        exit 1
+    fi
+
+    BASE_PATH="$1"
+    PAGES="$2"
+    STYLE_VARIANTS="$3"
+    LAYOUT_VARIANTS="$4"
+    shift 4
+fi
+
+# Parse optional arguments
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --run-id)
+            RUN_ID="$2"
+            shift 2
+            ;;
+        --session-id)
+            SESSION_ID="$2"
+            shift 2
+            ;;
+        --mode)
+            MODE="$2"
+            shift 2
+            ;;
+        --template)
+            TEMPLATE_PATH="$2"
+            shift 2
+            ;;
+        --no-preview)
+            GENERATE_PREVIEW=false
+            shift
+            ;;
+        --help)
+            show_usage
+            exit 0
+            ;;
+        *)
+            log_error "Unknown option: $1"
+            show_usage
+            exit 1
+            ;;
+    esac
+done
+
+# ============================================================================
+# Auto-detection (if enabled)
+# ============================================================================
+
+if [ "$AUTO_DETECT" = true ]; then
+    log_info "🔍 Auto-detecting configuration from directory..."
+
+    # Detect pages
+    PAGES=$(auto_detect_pages "$BASE_PATH")
+    if [ -z "$PAGES" ]; then
+        log_error "Could not auto-detect pages from templates"
+        exit 1
+    fi
+    log_info "   Pages: $PAGES"
+
+    # Detect style variants
+    STYLE_VARIANTS=$(auto_detect_style_variants "$BASE_PATH")
+    log_info "   Style variants: $STYLE_VARIANTS"
+
+    # Detect layout variants
+    LAYOUT_VARIANTS=$(auto_detect_layout_variants "$BASE_PATH")
+    log_info "   Layout variants: $LAYOUT_VARIANTS"
+
+    echo ""
+fi
+
+# ============================================================================
+# Validation
+# ============================================================================
+
+# Validate base path
+if [ ! -d "$BASE_PATH" ]; then
+    log_error "Base path not found: $BASE_PATH"
+    exit 1
+fi
+
+# Validate style and layout variants
+if [ "$STYLE_VARIANTS" -lt 1 ] || [ "$STYLE_VARIANTS" -gt 5 ]; then
+    log_error "Style variants must be between 1 and 5 (got: $STYLE_VARIANTS)"
+    exit 1
+fi
+
+if [ "$LAYOUT_VARIANTS" -lt 1 ] || [ "$LAYOUT_VARIANTS" -gt 5 ]; then
+    log_error "Layout variants must be between 1 and 5 (got: $LAYOUT_VARIANTS)"
+    exit 1
+fi
+
+# Validate STYLE_VARIANTS against actual style directories
+if [ "$STYLE_VARIANTS" -gt 0 ]; then
+    style_dir="$BASE_PATH/../style-consolidation"
+
+    if [ ! -d "$style_dir" ]; then
+        log_error "Style consolidation directory not found: $style_dir"
+        log_info "Run /workflow:ui-design:consolidate first"
+        exit 1
+    fi
+
+    actual_styles=$(find "$style_dir" -maxdepth 1 -type d -name "style-*" 2>/dev/null | wc -l)
+
+    if [ "$actual_styles" -eq 0 ]; then
+        log_error "No style directories found in: $style_dir"
+        log_info "Run /workflow:ui-design:consolidate first to generate style design systems"
+        exit 1
+    fi
+
+    if [ "$STYLE_VARIANTS" -gt "$actual_styles" ]; then
+        log_warning "Requested $STYLE_VARIANTS style variants, but only found $actual_styles directories"
+        log_info "Available style directories:"
+        find "$style_dir" -maxdepth 1 -type d -name "style-*" 2>/dev/null | sed 's|.*/||' | sort
+        log_info "Auto-correcting to $actual_styles style variants"
+        STYLE_VARIANTS=$actual_styles
+    fi
+fi
+
+# Parse pages into array
+IFS=',' read -ra PAGE_ARRAY <<< "$PAGES"
+
+if [ ${#PAGE_ARRAY[@]} -eq 0 ]; then
+    log_error "No pages found"
+    exit 1
+fi
+
+# ============================================================================
+# Header Output
+# ============================================================================
+
+echo "========================================="
+echo "UI Prototype Instantiation & Preview"
+if [ "$AUTO_DETECT" = true ]; then
+    echo "(Auto-detected configuration)"
+fi
+echo "========================================="
+echo "Base Path: $BASE_PATH"
+echo "Mode: $MODE"
+echo "Pages/Components: $PAGES"
+echo "Style Variants: $STYLE_VARIANTS"
+echo "Layout Variants: $LAYOUT_VARIANTS"
+echo "Run ID: $RUN_ID"
+echo "Session ID: $SESSION_ID"
+echo "========================================="
+echo ""
+
+# Change to base path
+cd "$BASE_PATH" || exit 1
+
+# ============================================================================
+# Phase 1: Instantiate Prototypes
+# ============================================================================
+
+log_info "🚀 Phase 1: Instantiating prototypes from templates..."
+echo ""
+
+total_generated=0
+total_failed=0
+
+for page in "${PAGE_ARRAY[@]}"; do
+    # Trim whitespace
+    page=$(echo "$page" | xargs)
+
+    log_info "Processing page/component: $page"
+
+    for s in $(seq 1 "$STYLE_VARIANTS"); do
+        for l in $(seq 1 "$LAYOUT_VARIANTS"); do
+            # Define file paths
+            TEMPLATE_HTML="_templates/${page}-layout-${l}.html"
+            STRUCTURAL_CSS="_templates/${page}-layout-${l}.css"
+            TOKEN_CSS="../style-consolidation/style-${s}/tokens.css"
+            OUTPUT_HTML="${page}-style-${s}-layout-${l}.html"
+
+            # Copy template and replace placeholders
+            if [ -f "$TEMPLATE_HTML" ]; then
+                cp "$TEMPLATE_HTML" "$OUTPUT_HTML" || {
+                    log_error "Failed to copy template: $TEMPLATE_HTML"
+                    ((total_failed++))
+                    continue
+                }
+
+                # Replace CSS placeholders (Windows-compatible sed syntax)
+                sed -i "s|{{STRUCTURAL_CSS}}|${STRUCTURAL_CSS}|g" "$OUTPUT_HTML" || true
+                sed -i "s|{{TOKEN_CSS}}|${TOKEN_CSS}|g" "$OUTPUT_HTML" || true
+
+                log_success "Created: $OUTPUT_HTML"
+                ((total_generated++))
+
+                # Create implementation notes (simplified)
+                NOTES_FILE="${page}-style-${s}-layout-${l}-notes.md"
+
+                # Generate notes with simple heredoc
+                cat > "$NOTES_FILE" <<NOTESEOF
+# Implementation Notes: ${page}-style-${s}-layout-${l}
+
+## Generation Details
+- **Template**: ${TEMPLATE_HTML}
+- **Structural CSS**: ${STRUCTURAL_CSS}
+- **Style Tokens**: ${TOKEN_CSS}
+- **Layout Strategy**: Layout ${l}
+- **Style Variant**: Style ${s}
+- **Mode**: ${MODE}
+
+## Template Reuse
+This prototype was generated from a shared layout template to ensure consistency
+across all style variants. The HTML structure is identical for all ${page}-layout-${l}
+prototypes, with only the design tokens (colors, fonts, spacing) varying.
+
+## Design System Reference
+Refer to \`../style-consolidation/style-${s}/style-guide.md\` for:
+- Design philosophy
+- Token usage guidelines
+- Component patterns
+- Accessibility requirements
+
+## Customization
+To modify this prototype:
+1. Edit the layout template: \`${TEMPLATE_HTML}\` (affects all styles)
+2. Edit the structural CSS: \`${STRUCTURAL_CSS}\` (affects all styles)
+3. Edit design tokens: \`${TOKEN_CSS}\` (affects only this style variant)
+
+## Run Information
+- **Run ID**: ${RUN_ID}
+- **Session ID**: ${SESSION_ID}
+- **Generated**: $(date -u +%Y-%m-%dT%H:%M:%SZ 2>/dev/null || date -u +%Y-%m-%d)
+NOTESEOF
+
+            else
+                log_error "Template not found: $TEMPLATE_HTML"
+                ((total_failed++))
+            fi
+        done
+    done
+done
+
+echo ""
+log_success "Phase 1 complete: Generated ${total_generated} prototypes"
+if [ $total_failed -gt 0 ]; then
+    log_warning "Failed: ${total_failed} prototypes"
+fi
+echo ""
+
+# ============================================================================
+# Phase 2: Generate Preview Files (if enabled)
+# ============================================================================
+
+if [ "$GENERATE_PREVIEW" = false ]; then
+    log_info "⏭️  Skipping preview generation (--no-preview flag)"
+    exit 0
+fi
+
+log_info "🎨 Phase 2: Generating preview files..."
+echo ""
+
+# ============================================================================
+# 2a. Generate compare.html from template
+# ============================================================================
+
+if [ ! -f "$TEMPLATE_PATH" ]; then
+    log_warning "Template not found: $TEMPLATE_PATH"
+    log_info "   Skipping compare.html generation"
+else
+    log_info "📄 Generating compare.html from template..."
+
+    # Convert page array to JSON format
+    PAGES_JSON="["
+    for i in "${!PAGE_ARRAY[@]}"; do
+        page=$(echo "${PAGE_ARRAY[$i]}" | xargs)
+        PAGES_JSON+="\"$page\""
+        if [ $i -lt $((${#PAGE_ARRAY[@]} - 1)) ]; then
+            PAGES_JSON+=", "
+        fi
+    done
+    PAGES_JSON+="]"
+
+    TIMESTAMP=$(date -u +%Y-%m-%dT%H:%M:%SZ 2>/dev/null || date -u +%Y-%m-%d)
+
+    # Read template and replace placeholders
+    cat "$TEMPLATE_PATH" | \
+        sed "s|{{run_id}}|${RUN_ID}|g" | \
+        sed "s|{{session_id}}|${SESSION_ID}|g" | \
+        sed "s|{{timestamp}}|${TIMESTAMP}|g" | \
+        sed "s|{{style_variants}}|${STYLE_VARIANTS}|g" | \
+        sed "s|{{layout_variants}}|${LAYOUT_VARIANTS}|g" | \
+        sed "s|{{pages_json}}|${PAGES_JSON}|g" \
+        > compare.html
+
+    log_success "Generated: compare.html"
+fi
+
+# ============================================================================
+# 2b. Generate index.html
+# ============================================================================
+
+log_info "📄 Generating index.html..."
+
+# Calculate total prototypes
+TOTAL_PROTOTYPES=$((STYLE_VARIANTS * LAYOUT_VARIANTS * ${#PAGE_ARRAY[@]}))
+
+# Generate index.html with simple heredoc
+cat > index.html <<'INDEXEOF'
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <title>UI Prototypes - __MODE__ Mode - __RUN_ID__</title>
+  <style>
+    body {
+      font-family: system-ui, -apple-system, sans-serif;
+      max-width: 900px;
+      margin: 2rem auto;
+      padding: 0 2rem;
+      background: #f9fafb;
+    }
+    .header {
+      background: white;
+      padding: 2rem;
+      border-radius: 0.75rem;
+      box-shadow: 0 1px 3px rgba(0,0,0,0.1);
+      margin-bottom: 2rem;
+    }
+    h1 {
+      color: #2563eb;
+      margin-bottom: 0.5rem;
+      font-size: 2rem;
+    }
+    .meta {
+      color: #6b7280;
+      font-size: 0.875rem;
+      margin-top: 0.5rem;
+    }
+    .info {
+      background: #f3f4f6;
+      padding: 1.5rem;
+      border-radius: 0.5rem;
+      margin: 1.5rem 0;
+      border-left: 4px solid #2563eb;
+    }
+    .cta {
+      display: inline-block;
+      background: #2563eb;
+      color: white;
+      padding: 1rem 2rem;
+      border-radius: 0.5rem;
+      text-decoration: none;
+      font-weight: 600;
+      margin: 1rem 0;
+      transition: background 0.2s;
+    }
+    .cta:hover {
+      background: #1d4ed8;
+    }
+    .stats {
+      display: grid;
+      grid-template-columns: repeat(auto-fit, minmax(150px, 1fr));
+      gap: 1rem;
+      margin: 1.5rem 0;
+    }
+    .stat {
+      background: white;
+      border: 1px solid #e5e7eb;
+      padding: 1.5rem;
+      border-radius: 0.5rem;
+      text-align: center;
+      box-shadow: 0 1px 2px rgba(0,0,0,0.05);
+    }
+    .stat-value {
+      font-size: 2.5rem;
+      font-weight: bold;
+      color: #2563eb;
+      margin-bottom: 0.25rem;
+    }
+    .stat-label {
+      color: #6b7280;
+      font-size: 0.875rem;
+    }
+    .section {
+      background: white;
+      padding: 2rem;
+      border-radius: 0.75rem;
+      margin-bottom: 2rem;
+      box-shadow: 0 1px 3px rgba(0,0,0,0.1);
+    }
+    h2 {
+      color: #1f2937;
+      margin-bottom: 1rem;
+      font-size: 1.5rem;
+    }
+    ul {
+      line-height: 1.8;
+      color: #374151;
+    }
+    .pages-list {
+      list-style: none;
+      padding: 0;
+    }
+    .pages-list li {
+      background: #f9fafb;
+      padding: 0.75rem 1rem;
+      margin: 0.5rem 0;
+      border-radius: 0.375rem;
+      border-left: 3px solid #2563eb;
+    }
+    .badge {
+      display: inline-block;
+      background: #dbeafe;
+      color: #1e40af;
+      padding: 0.25rem 0.75rem;
+      border-radius: 0.25rem;
+      font-size: 0.75rem;
+      font-weight: 600;
+      margin-left: 0.5rem;
+    }
+  </style>
+</head>
+<body>
+  <div class="header">
+    <h1>🎨 UI Prototype __MODE__ Mode</h1>
+    <div class="meta">
+      <strong>Run ID:</strong> __RUN_ID__ |
+      <strong>Session:</strong> __SESSION_ID__ |
+      <strong>Generated:</strong> __TIMESTAMP__
+    </div>
+  </div>
+
+  <div class="info">
+    <p><strong>Matrix Configuration:</strong> __STYLE_VARIANTS__ styles × __LAYOUT_VARIANTS__ layouts × __PAGE_COUNT__ __MODE__s</p>
+    <p><strong>Total Prototypes:</strong> __TOTAL_PROTOTYPES__ interactive HTML files</p>
+  </div>
+
+  <a href="compare.html" class="cta">🔍 Open Interactive Matrix Comparison →</a>
+
+  <div class="stats">
+    <div class="stat">
+      <div class="stat-value">__STYLE_VARIANTS__</div>
+      <div class="stat-label">Style Variants</div>
+    </div>
+    <div class="stat">
+      <div class="stat-value">__LAYOUT_VARIANTS__</div>
+      <div class="stat-label">Layout Options</div>
+    </div>
+    <div class="stat">
+      <div class="stat-value">__PAGE_COUNT__</div>
+      <div class="stat-label">__MODE__s</div>
+    </div>
+    <div class="stat">
+      <div class="stat-value">__TOTAL_PROTOTYPES__</div>
+      <div class="stat-label">Total Prototypes</div>
+    </div>
+  </div>
+
+  <div class="section">
+    <h2>🌟 Features</h2>
+    <ul>
+      <li><strong>Interactive Matrix View:</strong> __STYLE_VARIANTS__×__LAYOUT_VARIANTS__ grid with synchronized scrolling</li>
+      <li><strong>Flexible Zoom:</strong> 25%, 50%, 75%, 100% viewport scaling</li>
+      <li><strong>Fullscreen Mode:</strong> Detailed view for individual prototypes</li>
+      <li><strong>Selection System:</strong> Mark favorites with export to JSON</li>
+      <li><strong>__MODE__ Switcher:</strong> Compare different __MODE__s side-by-side</li>
+      <li><strong>Persistent State:</strong> Selections saved in localStorage</li>
+    </ul>
+  </div>
+
+  <div class="section">
+    <h2>📄 Generated __MODE__s</h2>
+    <ul class="pages-list">
+__PAGES_LIST__
+    </ul>
+  </div>
+
+  <div class="section">
+    <h2>📚 Next Steps</h2>
+    <ol>
+      <li>Open <code>compare.html</code> to explore all variants in matrix view</li>
+      <li>Use zoom and sync scroll controls to compare details</li>
+      <li>Select your preferred style×layout combinations</li>
+      <li>Export selections as JSON for implementation planning</li>
+      <li>Review implementation notes in <code>*-notes.md</code> files</li>
+    </ol>
+  </div>
+</body>
+</html>
+INDEXEOF
+
+# Build pages list HTML
+PAGES_LIST_HTML=""
+for page in "${PAGE_ARRAY[@]}"; do
+    page=$(echo "$page" | xargs)
+    VARIANT_COUNT=$((STYLE_VARIANTS * LAYOUT_VARIANTS))
+    PAGES_LIST_HTML+="      <li>\n"
+    PAGES_LIST_HTML+="        <strong>${page}</strong>\n"
+    PAGES_LIST_HTML+="        <span class=\"badge\">${STYLE_VARIANTS}×${LAYOUT_VARIANTS} = ${VARIANT_COUNT} variants</span>\n"
+    PAGES_LIST_HTML+="      </li>\n"
+done
+
+# Replace all placeholders in index.html
+MODE_UPPER=$(echo "$MODE" | awk '{print toupper(substr($0,1,1)) tolower(substr($0,2))}')
+sed -i "s|__RUN_ID__|${RUN_ID}|g" index.html
+sed -i "s|__SESSION_ID__|${SESSION_ID}|g" index.html
+sed -i "s|__TIMESTAMP__|${TIMESTAMP}|g" index.html
+sed -i "s|__MODE__|${MODE_UPPER}|g" index.html
+sed -i "s|__STYLE_VARIANTS__|${STYLE_VARIANTS}|g" index.html
+sed -i "s|__LAYOUT_VARIANTS__|${LAYOUT_VARIANTS}|g" index.html
+sed -i "s|__PAGE_COUNT__|${#PAGE_ARRAY[@]}|g" index.html
+sed -i "s|__TOTAL_PROTOTYPES__|${TOTAL_PROTOTYPES}|g" index.html
+sed -i "s|__PAGES_LIST__|${PAGES_LIST_HTML}|g" index.html
+
+log_success "Generated: index.html"
+
+# ============================================================================
+# 2c. Generate PREVIEW.md
+# ============================================================================
+
+log_info "📄 Generating PREVIEW.md..."
+
+cat > PREVIEW.md <<PREVIEWEOF
+# UI Prototype Preview Guide
+
+## Quick Start
+1. Open \`index.html\` for overview and navigation
+2. Open \`compare.html\` for interactive matrix comparison
+3. Use browser developer tools to inspect responsive behavior
+
+## Configuration
+
+- **Exploration Mode:** ${MODE_UPPER}
+- **Run ID:** ${RUN_ID}
+- **Session ID:** ${SESSION_ID}
+- **Style Variants:** ${STYLE_VARIANTS}
+- **Layout Options:** ${LAYOUT_VARIANTS}
+- **${MODE_UPPER}s:** ${PAGES}
+- **Total Prototypes:** ${TOTAL_PROTOTYPES}
+- **Generated:** ${TIMESTAMP}
+
+## File Naming Convention
+
+\`\`\`
+{${MODE}}-style-{s}-layout-{l}.html
+\`\`\`
+
+**Example:** \`dashboard-style-1-layout-2.html\`
+- ${MODE_UPPER}: dashboard
+- Style: Design system 1
+- Layout: Layout variant 2
+
+## Interactive Features (compare.html)
+
+### Matrix View
+- **Grid Layout:** ${STYLE_VARIANTS}×${LAYOUT_VARIANTS} table with all prototypes visible
+- **Synchronized Scroll:** All iframes scroll together (toggle with button)
+- **Zoom Controls:** Adjust viewport scale (25%, 50%, 75%, 100%)
+- **${MODE_UPPER} Selector:** Switch between different ${MODE}s instantly
+
+### Prototype Actions
+- **⭐ Selection:** Click star icon to mark favorites
+- **⛶ Fullscreen:** View prototype in fullscreen overlay
+- **↗ New Tab:** Open prototype in dedicated browser tab
+
+### Selection Export
+1. Select preferred prototypes using star icons
+2. Click "Export Selection" button
+3. Downloads JSON file: \`selection-${RUN_ID}.json\`
+4. Use exported file for implementation planning
+
+## Design System References
+
+Each prototype references a specific style design system:
+PREVIEWEOF
+
+# Add style references
+for s in $(seq 1 "$STYLE_VARIANTS"); do
+    cat >> PREVIEW.md <<STYLEEOF
+
+### Style ${s}
+- **Tokens:** \`../style-consolidation/style-${s}/design-tokens.json\`
+- **CSS Variables:** \`../style-consolidation/style-${s}/tokens.css\`
+- **Style Guide:** \`../style-consolidation/style-${s}/style-guide.md\`
+STYLEEOF
+done
+
+cat >> PREVIEW.md <<'FOOTEREOF'
+
+## Responsive Testing
+
+All prototypes are mobile-first responsive. Test at these breakpoints:
+
+- **Mobile:** 375px - 767px
+- **Tablet:** 768px - 1023px
+- **Desktop:** 1024px+
+
+Use browser DevTools responsive mode for testing.
+
+## Accessibility Features
+
+- Semantic HTML5 structure
+- ARIA attributes for screen readers
+- Keyboard navigation support
+- Proper heading hierarchy
+- Focus indicators
+
+## Next Steps
+
+1. **Review:** Open `compare.html` and explore all variants
+2. **Select:** Mark preferred prototypes using star icons
+3. **Export:** Download selection JSON for implementation
+4. **Implement:** Use `/workflow:ui-design:update` to integrate selected designs
+5. **Plan:** Run `/workflow:plan` to generate implementation tasks
+
+---
+
+**Generated by:** `ui-instantiate-prototypes.sh`
+**Version:** 3.0 (auto-detect mode)
+FOOTEREOF
+
+log_success "Generated: PREVIEW.md"
+
+# ============================================================================
+# Completion Summary
+# ============================================================================
+
+echo ""
+echo "========================================="
+echo "✅ Generation Complete!"
+echo "========================================="
+echo ""
+echo "📊 Summary:"
+echo "   Prototypes: ${total_generated} generated"
+if [ $total_failed -gt 0 ]; then
+    echo "   Failed: ${total_failed}"
+fi
+echo "   Preview Files: compare.html, index.html, PREVIEW.md"
+echo "   Matrix: ${STYLE_VARIANTS}×${LAYOUT_VARIANTS} (${#PAGE_ARRAY[@]} ${MODE}s)"
+echo "   Total Files: ${TOTAL_PROTOTYPES} prototypes + preview files"
+echo ""
+echo "🌐 Next Steps:"
+echo "   1. Open: ${BASE_PATH}/index.html"
+echo "   2. Explore: ${BASE_PATH}/compare.html"
+echo "   3. Review: ${BASE_PATH}/PREVIEW.md"
+echo ""
+echo "Performance: Template-based approach with ${STYLE_VARIANTS}× speedup"
+echo "========================================="

.claude/scripts/update_module_claude.sh

@@ -1,13 +1,15 @@
 #!/bin/bash
 # Update CLAUDE.md for a specific module with automatic layer detection
-# Usage: update_module_claude.sh <module_path> [update_type]
+# Usage: update_module_claude.sh <module_path> [update_type] [tool]
 #   module_path: Path to the module directory
 #   update_type: full|related (default: full)
+#   tool: gemini|qwen|codex (default: gemini)
 #   Script automatically detects layer depth and selects appropriate template
 
 update_module_claude() {
     local module_path="$1"
     local update_type="${2:-full}"
+    local tool="${3:-gemini}"
     
     # Validate parameters
     if [ -z "$module_path" ]; then
@@ -40,30 +42,30 @@ update_module_claude() {
     if [ "$module_path" = "." ]; then
         # Root directory
         layer="Layer 1 (Root)"
-        template_path="$HOME/.claude/workflows/cli-templates/prompts/dms/claude-layer1-root.txt"
+        template_path="$HOME/.claude/workflows/cli-templates/prompts/memory/claude-layer1-root.txt"
         analysis_strategy="--all-files"
     elif [[ "$clean_path" =~ ^[^/]+$ ]]; then
         # Top-level directories (e.g., .claude, src, tests)
         layer="Layer 2 (Domain)"
-        template_path="$HOME/.claude/workflows/cli-templates/prompts/dms/claude-layer2-domain.txt"
+        template_path="$HOME/.claude/workflows/cli-templates/prompts/memory/claude-layer2-domain.txt"
         analysis_strategy="@{*/CLAUDE.md}"
     elif [[ "$clean_path" =~ ^[^/]+/[^/]+$ ]]; then
         # Second-level directories (e.g., .claude/scripts, src/components)
         layer="Layer 3 (Module)"
-        template_path="$HOME/.claude/workflows/cli-templates/prompts/dms/claude-layer3-module.txt"
+        template_path="$HOME/.claude/workflows/cli-templates/prompts/memory/claude-layer3-module.txt"
         analysis_strategy="@{*/CLAUDE.md}"
     else
         # Deeper directories (e.g., .claude/workflows/cli-templates/prompts)
         layer="Layer 4 (Sub-Module)"
-        template_path="$HOME/.claude/workflows/cli-templates/prompts/dms/claude-layer4-submodule.txt"
+        template_path="$HOME/.claude/workflows/cli-templates/prompts/memory/claude-layer4-submodule.txt"
         analysis_strategy="--all-files"
     fi
     
     # Prepare logging info
     local module_name=$(basename "$module_path")
-    
+
     echo "⚡ Updating: $module_path"
-    echo "   Layer: $layer | Type: $update_type | Files: $file_count"
+    echo "   Layer: $layer | Type: $update_type | Tool: $tool | Files: $file_count"
     echo "   Template: $(basename "$template_path") | Strategy: $analysis_strategy"
     
     # Generate prompt with template injection
@@ -106,31 +108,50 @@ update_module_claude() {
     # Execute update
     local start_time=$(date +%s)
     echo "   🔄 Starting update..."
-    
+
     if cd "$module_path" 2>/dev/null; then
-        # Execute gemini command with layer-specific analysis strategy
-        local gemini_result=0
-        if [ "$analysis_strategy" = "--all-files" ]; then
-            gemini --all-files --yolo -p "$base_prompt
+        local tool_result=0
+        local final_prompt="$base_prompt
 
         Module Information:
         - Name: $module_name
         - Path: $module_path
         - Layer: $layer
-        - Analysis Strategy: $analysis_strategy" 2>&1
-            gemini_result=$?
-        else
-            gemini --yolo -p "$analysis_strategy $base_prompt
+        - Tool: $tool
+        - Analysis Strategy: $analysis_strategy"
 
-        Module Information:
-        - Name: $module_name
-        - Path: $module_path
-        - Layer: $layer
-        - Analysis Strategy: $analysis_strategy" 2>&1
-            gemini_result=$?
-        fi
-        
-        if [ $gemini_result -eq 0 ]; then
+        # Execute with selected tool
+        case "$tool" in
+            qwen)
+                if [ "$analysis_strategy" = "--all-files" ]; then
+                    qwen --all-files --yolo -p "$final_prompt" 2>&1
+                    tool_result=$?
+                else
+                    qwen --yolo -p "$analysis_strategy $final_prompt" 2>&1
+                    tool_result=$?
+                fi
+                ;;
+            codex)
+                if [ "$analysis_strategy" = "--all-files" ]; then
+                    codex --full-auto exec "$final_prompt" --skip-git-repo-check -s danger-full-access 2>&1
+                    tool_result=$?
+                else
+                    codex --full-auto exec "$final_prompt CONTEXT: $analysis_strategy" --skip-git-repo-check -s danger-full-access 2>&1
+                    tool_result=$?
+                fi
+                ;;
+            gemini|*)
+                if [ "$analysis_strategy" = "--all-files" ]; then
+                    gemini --all-files --yolo -p "$final_prompt" 2>&1
+                    tool_result=$?
+                else
+                    gemini --yolo -p "$analysis_strategy $final_prompt" 2>&1
+                    tool_result=$?
+                fi
+                ;;
+        esac
+
+        if [ $tool_result -eq 0 ]; then
             local end_time=$(date +%s)
             local duration=$((end_time - start_time))
             echo "   ✅ Completed in ${duration}s"

.claude/workflows/_template-compare-matrix.html

@@ -0,0 +1,692 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <title>UI Design Matrix Comparison - {{run_id}}</title>
+  <style>
+    :root {
+      --color-primary: #2563eb;
+      --color-bg: #f9fafb;
+      --color-surface: #ffffff;
+      --color-border: #e5e7eb;
+      --color-text: #1f2937;
+      --color-text-secondary: #6b7280;
+    }
+
+    * {
+      margin: 0;
+      padding: 0;
+      box-sizing: border-box;
+    }
+
+    body {
+      font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;
+      background: var(--color-bg);
+      color: var(--color-text);
+      line-height: 1.6;
+    }
+
+    .container {
+      max-width: 1600px;
+      margin: 0 auto;
+      padding: 2rem;
+    }
+
+    header {
+      background: var(--color-surface);
+      padding: 1.5rem 2rem;
+      border-radius: 0.5rem;
+      margin-bottom: 2rem;
+      box-shadow: 0 1px 3px rgba(0,0,0,0.1);
+    }
+
+    h1 {
+      color: var(--color-primary);
+      font-size: 1.875rem;
+      margin-bottom: 0.5rem;
+    }
+
+    .meta {
+      color: var(--color-text-secondary);
+      font-size: 0.875rem;
+    }
+
+    .controls {
+      background: var(--color-surface);
+      padding: 1.5rem;
+      border-radius: 0.5rem;
+      margin-bottom: 2rem;
+      display: flex;
+      gap: 1.5rem;
+      align-items: center;
+      flex-wrap: wrap;
+    }
+
+    .control-group {
+      display: flex;
+      flex-direction: column;
+      gap: 0.5rem;
+    }
+
+    label {
+      font-size: 0.875rem;
+      font-weight: 500;
+      color: var(--color-text-secondary);
+    }
+
+    select, button {
+      padding: 0.5rem 1rem;
+      border: 1px solid var(--color-border);
+      border-radius: 0.375rem;
+      font-size: 0.875rem;
+      background: white;
+      cursor: pointer;
+    }
+
+    select:focus, button:focus {
+      outline: 2px solid var(--color-primary);
+      outline-offset: 2px;
+    }
+
+    button {
+      background: var(--color-primary);
+      color: white;
+      border: none;
+      font-weight: 500;
+      transition: background 0.2s;
+    }
+
+    button:hover {
+      background: #1d4ed8;
+    }
+
+    .matrix-container {
+      background: var(--color-surface);
+      border-radius: 0.5rem;
+      overflow: hidden;
+      box-shadow: 0 1px 3px rgba(0,0,0,0.1);
+    }
+
+    .matrix-table {
+      width: 100%;
+      border-collapse: collapse;
+    }
+
+    .matrix-table th,
+    .matrix-table td {
+      border: 1px solid var(--color-border);
+      padding: 0.75rem;
+      text-align: center;
+    }
+
+    .matrix-table th {
+      background: #f3f4f6;
+      font-weight: 600;
+      color: var(--color-text);
+    }
+
+    .matrix-table thead th {
+      background: var(--color-primary);
+      color: white;
+    }
+
+    .matrix-table tbody th {
+      background: #f9fafb;
+      font-weight: 600;
+    }
+
+    .prototype-cell {
+      position: relative;
+      padding: 0;
+      height: 400px;
+      vertical-align: top;
+    }
+
+    .prototype-wrapper {
+      height: 100%;
+      display: flex;
+      flex-direction: column;
+    }
+
+    .prototype-header {
+      padding: 0.5rem;
+      background: #f9fafb;
+      border-bottom: 1px solid var(--color-border);
+      display: flex;
+      justify-content: space-between;
+      align-items: center;
+      flex-shrink: 0;
+    }
+
+    .prototype-title {
+      font-size: 0.75rem;
+      font-weight: 500;
+      color: var(--color-text-secondary);
+    }
+
+    .prototype-actions {
+      display: flex;
+      gap: 0.25rem;
+    }
+
+    .icon-btn {
+      width: 24px;
+      height: 24px;
+      padding: 0;
+      display: flex;
+      align-items: center;
+      justify-content: center;
+      background: transparent;
+      border: none;
+      color: var(--color-text-secondary);
+      cursor: pointer;
+      border-radius: 0.25rem;
+    }
+
+    .icon-btn:hover {
+      background: #e5e7eb;
+      color: var(--color-text);
+    }
+
+    .icon-btn.selected {
+      background: var(--color-primary);
+      color: white;
+    }
+
+    .prototype-iframe-container {
+      flex: 1;
+      position: relative;
+      overflow: hidden;
+    }
+
+    .prototype-iframe {
+      width: 100%;
+      height: 100%;
+      border: none;
+      transform-origin: top left;
+    }
+
+    .zoom-info {
+      position: absolute;
+      bottom: 0.5rem;
+      right: 0.5rem;
+      background: rgba(0,0,0,0.7);
+      color: white;
+      padding: 0.25rem 0.5rem;
+      border-radius: 0.25rem;
+      font-size: 0.75rem;
+      pointer-events: none;
+    }
+
+    .tabs {
+      display: flex;
+      gap: 0.5rem;
+      margin-bottom: 1rem;
+      border-bottom: 2px solid var(--color-border);
+    }
+
+    .tab {
+      padding: 0.75rem 1.5rem;
+      background: transparent;
+      border: none;
+      border-bottom: 2px solid transparent;
+      cursor: pointer;
+      font-weight: 500;
+      color: var(--color-text-secondary);
+      margin-bottom: -2px;
+    }
+
+    .tab.active {
+      color: var(--color-primary);
+      border-bottom-color: var(--color-primary);
+    }
+
+    .tab-content {
+      display: none;
+    }
+
+    .tab-content.active {
+      display: block;
+    }
+
+    .fullscreen-overlay {
+      display: none;
+      position: fixed;
+      top: 0;
+      left: 0;
+      right: 0;
+      bottom: 0;
+      background: rgba(0,0,0,0.95);
+      z-index: 1000;
+      padding: 2rem;
+    }
+
+    .fullscreen-overlay.active {
+      display: flex;
+      flex-direction: column;
+    }
+
+    .fullscreen-header {
+      color: white;
+      margin-bottom: 1rem;
+      display: flex;
+      justify-content: space-between;
+      align-items: center;
+    }
+
+    .fullscreen-iframe {
+      flex: 1;
+      border: none;
+      background: white;
+      border-radius: 0.5rem;
+    }
+
+    .close-btn {
+      background: rgba(255,255,255,0.2);
+      color: white;
+      border: none;
+      padding: 0.5rem 1rem;
+      border-radius: 0.375rem;
+      cursor: pointer;
+    }
+
+    .close-btn:hover {
+      background: rgba(255,255,255,0.3);
+    }
+
+    .selection-summary {
+      background: #fef3c7;
+      border-left: 4px solid #f59e0b;
+      padding: 1rem;
+      margin-bottom: 2rem;
+      border-radius: 0.375rem;
+    }
+
+    .selection-summary h3 {
+      color: #92400e;
+      margin-bottom: 0.5rem;
+      font-size: 1rem;
+    }
+
+    .selection-list {
+      list-style: none;
+      color: #78350f;
+      font-size: 0.875rem;
+    }
+
+    .selection-list li {
+      padding: 0.25rem 0;
+    }
+
+    @media (max-width: 1200px) {
+      .prototype-cell {
+        height: 300px;
+      }
+    }
+  </style>
+</head>
+<body>
+  <div class="container">
+    <header>
+      <h1>🎨 UI Design Matrix Comparison</h1>
+      <div class="meta">
+        <strong>Run ID:</strong> {{run_id}} |
+        <strong>Session:</strong> {{session_id}} |
+        <strong>Generated:</strong> {{timestamp}}
+      </div>
+    </header>
+
+    <div class="controls">
+      <div class="control-group">
+        <label for="page-select">Page:</label>
+        <select id="page-select">
+          <!-- Populated by JavaScript -->
+        </select>
+      </div>
+
+      <div class="control-group">
+        <label for="zoom-level">Zoom:</label>
+        <select id="zoom-level">
+          <option value="0.25">25%</option>
+          <option value="0.5">50%</option>
+          <option value="0.75">75%</option>
+          <option value="1" selected>100%</option>
+        </select>
+      </div>
+
+      <div class="control-group">
+        <label>&nbsp;</label>
+        <button id="sync-scroll-toggle">🔗 Sync Scroll: ON</button>
+      </div>
+
+      <div class="control-group">
+        <label>&nbsp;</label>
+        <button id="export-selection">📥 Export Selection</button>
+      </div>
+    </div>
+
+    <div id="selection-summary" class="selection-summary" style="display:none">
+      <h3>Selected Prototypes (<span id="selection-count">0</span>)</h3>
+      <ul id="selection-list" class="selection-list"></ul>
+    </div>
+
+    <div class="tabs">
+      <button class="tab active" data-tab="matrix">Matrix View</button>
+      <button class="tab" data-tab="comparison">Side-by-Side</button>
+      <button class="tab" data-tab="runs">Compare Runs</button>
+    </div>
+
+    <div class="tab-content active" data-content="matrix">
+      <div class="matrix-container">
+        <table class="matrix-table">
+          <thead>
+            <tr>
+              <th>Style ↓ / Layout →</th>
+              <th>Layout 1</th>
+              <th>Layout 2</th>
+              <th>Layout 3</th>
+            </tr>
+          </thead>
+          <tbody id="matrix-body">
+            <!-- Populated by JavaScript -->
+          </tbody>
+        </table>
+      </div>
+    </div>
+
+    <div class="tab-content" data-content="comparison">
+      <p>Select two prototypes from the matrix to compare side-by-side.</p>
+      <div id="comparison-view"></div>
+    </div>
+
+    <div class="tab-content" data-content="runs">
+      <p>Compare the same prototype across different runs.</p>
+      <div id="runs-comparison"></div>
+    </div>
+  </div>
+
+  <div id="fullscreen-overlay" class="fullscreen-overlay">
+    <div class="fullscreen-header">
+      <h2 id="fullscreen-title"></h2>
+      <button class="close-btn" onclick="closeFullscreen()">✕ Close</button>
+    </div>
+    <iframe id="fullscreen-iframe" class="fullscreen-iframe"></iframe>
+  </div>
+
+  <script>
+    // Configuration - Replace with actual values during generation
+    const CONFIG = {
+      runId: "{{run_id}}",
+      sessionId: "{{session_id}}",
+      styleVariants: {{style_variants}},  // e.g., 3
+      layoutVariants: {{layout_variants}},  // e.g., 3
+      pages: {{pages_json}},  // e.g., ["dashboard", "auth"]
+      basePath: "."  // Relative path to prototypes
+    };
+
+    // State
+    let state = {
+      currentPage: CONFIG.pages[0],
+      zoomLevel: 1,
+      syncScroll: true,
+      selected: new Set(),
+      fullscreenSrc: null
+    };
+
+    // Initialize
+    document.addEventListener('DOMContentLoaded', () => {
+      populatePageSelect();
+      renderMatrix();
+      setupEventListeners();
+      loadSelectionFromStorage();
+    });
+
+    function populatePageSelect() {
+      const select = document.getElementById('page-select');
+      CONFIG.pages.forEach(page => {
+        const option = document.createElement('option');
+        option.value = page;
+        option.textContent = capitalize(page);
+        select.appendChild(option);
+      });
+    }
+
+    function renderMatrix() {
+      const tbody = document.getElementById('matrix-body');
+      tbody.innerHTML = '';
+
+      for (let s = 1; s <= CONFIG.styleVariants; s++) {
+        const row = document.createElement('tr');
+
+        // Style header cell
+        const headerCell = document.createElement('th');
+        headerCell.textContent = `Style ${s}`;
+        row.appendChild(headerCell);
+
+        // Prototype cells for each layout
+        for (let l = 1; l <= CONFIG.layoutVariants; l++) {
+          const cell = document.createElement('td');
+          cell.className = 'prototype-cell';
+
+          const filename = `${state.currentPage}-style-${s}-layout-${l}.html`;
+          const id = `${state.currentPage}-s${s}-l${l}`;
+
+          cell.innerHTML = `
+            <div class="prototype-wrapper">
+              <div class="prototype-header">
+                <span class="prototype-title">S${s}L${l}</span>
+                <div class="prototype-actions">
+                  <button class="icon-btn select-btn" data-id="${id}" title="Select">
+                    ${state.selected.has(id) ? '★' : '☆'}
+                  </button>
+                  <button class="icon-btn" onclick="openFullscreen('${filename}', 'Style ${s} Layout ${l}')" title="Fullscreen">
+                    ⛶
+                  </button>
+                  <button class="icon-btn" onclick="openInNewTab('${filename}')" title="Open in new tab">
+                    ↗
+                  </button>
+                </div>
+              </div>
+              <div class="prototype-iframe-container">
+                <iframe
+                  class="prototype-iframe"
+                  src="${filename}"
+                  data-cell="s${s}-l${l}"
+                  style="transform: scale(${state.zoomLevel});"
+                ></iframe>
+                <div class="zoom-info">${Math.round(state.zoomLevel * 100)}%</div>
+              </div>
+            </div>
+          `;
+
+          row.appendChild(cell);
+        }
+
+        tbody.appendChild(row);
+      }
+
+      // Re-attach selection event listeners
+      document.querySelectorAll('.select-btn').forEach(btn => {
+        btn.addEventListener('click', (e) => toggleSelection(e.target.dataset.id, e.target));
+      });
+
+      // Setup scroll sync
+      if (state.syncScroll) {
+        setupScrollSync();
+      }
+    }
+
+    function setupScrollSync() {
+      const iframes = document.querySelectorAll('.prototype-iframe');
+      let isScrolling = false;
+
+      iframes.forEach(iframe => {
+        iframe.addEventListener('load', () => {
+          const iframeWindow = iframe.contentWindow;
+
+          iframe.contentDocument.addEventListener('scroll', (e) => {
+            if (!state.syncScroll || isScrolling) return;
+
+            isScrolling = true;
+            const scrollTop = iframe.contentDocument.documentElement.scrollTop;
+            const scrollLeft = iframe.contentDocument.documentElement.scrollLeft;
+
+            iframes.forEach(otherIframe => {
+              if (otherIframe !== iframe && otherIframe.contentDocument) {
+                otherIframe.contentDocument.documentElement.scrollTop = scrollTop;
+                otherIframe.contentDocument.documentElement.scrollLeft = scrollLeft;
+              }
+            });
+
+            setTimeout(() => { isScrolling = false; }, 50);
+          });
+        });
+      });
+    }
+
+    function setupEventListeners() {
+      // Page selector
+      document.getElementById('page-select').addEventListener('change', (e) => {
+        state.currentPage = e.target.value;
+        renderMatrix();
+      });
+
+      // Zoom level
+      document.getElementById('zoom-level').addEventListener('change', (e) => {
+        state.zoomLevel = parseFloat(e.target.value);
+        renderMatrix();
+      });
+
+      // Sync scroll toggle
+      document.getElementById('sync-scroll-toggle').addEventListener('click', (e) => {
+        state.syncScroll = !state.syncScroll;
+        e.target.textContent = `🔗 Sync Scroll: ${state.syncScroll ? 'ON' : 'OFF'}`;
+        if (state.syncScroll) setupScrollSync();
+      });
+
+      // Export selection
+      document.getElementById('export-selection').addEventListener('click', exportSelection);
+
+      // Tab switching
+      document.querySelectorAll('.tab').forEach(tab => {
+        tab.addEventListener('click', (e) => {
+          const tabName = e.target.dataset.tab;
+          switchTab(tabName);
+        });
+      });
+    }
+
+    function toggleSelection(id, btn) {
+      if (state.selected.has(id)) {
+        state.selected.delete(id);
+        btn.textContent = '☆';
+        btn.classList.remove('selected');
+      } else {
+        state.selected.add(id);
+        btn.textContent = '★';
+        btn.classList.add('selected');
+      }
+
+      updateSelectionSummary();
+      saveSelectionToStorage();
+    }
+
+    function updateSelectionSummary() {
+      const summary = document.getElementById('selection-summary');
+      const count = document.getElementById('selection-count');
+      const list = document.getElementById('selection-list');
+
+      count.textContent = state.selected.size;
+
+      if (state.selected.size > 0) {
+        summary.style.display = 'block';
+        list.innerHTML = Array.from(state.selected)
+          .map(id => `<li>${id}</li>`)
+          .join('');
+      } else {
+        summary.style.display = 'none';
+      }
+    }
+
+    function saveSelectionToStorage() {
+      localStorage.setItem(`selection-${CONFIG.runId}`, JSON.stringify(Array.from(state.selected)));
+    }
+
+    function loadSelectionFromStorage() {
+      const stored = localStorage.getItem(`selection-${CONFIG.runId}`);
+      if (stored) {
+        state.selected = new Set(JSON.parse(stored));
+        updateSelectionSummary();
+      }
+    }
+
+    function exportSelection() {
+      const report = {
+        runId: CONFIG.runId,
+        sessionId: CONFIG.sessionId,
+        timestamp: new Date().toISOString(),
+        selections: Array.from(state.selected).map(id => ({
+          id,
+          file: `${id.replace(/-s(\d+)-l(\d+)/, '-style-$1-layout-$2')}.html`
+        }))
+      };
+
+      const blob = new Blob([JSON.stringify(report, null, 2)], { type: 'application/json' });
+      const url = URL.createObjectURL(blob);
+      const a = document.createElement('a');
+      a.href = url;
+      a.download = `selection-${CONFIG.runId}.json`;
+      a.click();
+      URL.revokeObjectURL(url);
+
+      alert(`Exported ${state.selected.size} selections to selection-${CONFIG.runId}.json`);
+    }
+
+    function openFullscreen(src, title) {
+      const overlay = document.getElementById('fullscreen-overlay');
+      const iframe = document.getElementById('fullscreen-iframe');
+      const titleEl = document.getElementById('fullscreen-title');
+
+      iframe.src = src;
+      titleEl.textContent = title;
+      overlay.classList.add('active');
+      state.fullscreenSrc = src;
+    }
+
+    function closeFullscreen() {
+      const overlay = document.getElementById('fullscreen-overlay');
+      const iframe = document.getElementById('fullscreen-iframe');
+
+      overlay.classList.remove('active');
+      iframe.src = '';
+      state.fullscreenSrc = null;
+    }
+
+    function openInNewTab(src) {
+      window.open(src, '_blank');
+    }
+
+    function switchTab(tabName) {
+      document.querySelectorAll('.tab').forEach(tab => {
+        tab.classList.toggle('active', tab.dataset.tab === tabName);
+      });
+
+      document.querySelectorAll('.tab-content').forEach(content => {
+        content.classList.toggle('active', content.dataset.content === tabName);
+      });
+    }
+
+    function capitalize(str) {
+      return str.charAt(0).toUpperCase() + str.slice(1);
+    }
+
+    // Close fullscreen on ESC key
+    document.addEventListener('keydown', (e) => {
+      if (e.key === 'Escape' && state.fullscreenSrc) {
+        closeFullscreen();
+      }
+    });
+  </script>
+</body>
+</html>

.claude/workflows/cli-templates/prompts/documentation/api.txt

@@ -0,0 +1,337 @@
+# Unified API Documentation Template
+
+Generate comprehensive API documentation. This template supports both **Code API** (for libraries/modules) and **HTTP API** (for web services). Include only the sections relevant to your project type.
+
+---
+
+## Part A: Code API (For Libraries, Modules, SDKs)
+
+**Use this section when documenting**: Exported functions, classes, interfaces, and types from code modules.
+
+**Omit this section if**: This is a pure web service with only HTTP endpoints and no programmatic API.
+
+### 1. Exported Functions
+
+For each exported function, provide:
+```typescript
+/**
+ * Brief one-line description of what the function does
+ * @param paramName - Parameter type and description
+ * @returns Return type and description
+ * @throws ErrorType - When this error occurs
+ */
+export function functionName(paramName: ParamType): ReturnType;
+```
+
+**Example**:
+```typescript
+/**
+ * Authenticates a user with email and password
+ * @param credentials - User email and password
+ * @returns Authentication token and user info
+ * @throws AuthenticationError - When credentials are invalid
+ */
+export function authenticate(credentials: Credentials): Promise<AuthResult>;
+```
+
+### 2. Exported Classes
+
+For each exported class, provide:
+```typescript
+/**
+ * Brief one-line description of the class purpose
+ */
+export class ClassName {
+  constructor(param: Type);
+
+  // Public properties
+  propertyName: Type;
+
+  // Public methods
+  methodName(param: Type): ReturnType;
+}
+```
+
+**Example**:
+```typescript
+/**
+ * Manages user session lifecycle and token refresh
+ */
+export class SessionManager {
+  constructor(config: SessionConfig);
+
+  // Current session state
+  isActive: boolean;
+
+  // Refresh the session token
+  refresh(): Promise<void>;
+
+  // Terminate the session
+  destroy(): void;
+}
+```
+
+### 3. Exported Interfaces
+
+For each exported interface, provide:
+```typescript
+/**
+ * Brief description of what this interface represents
+ */
+export interface InterfaceName {
+  field1: Type;  // Field description
+  field2: Type;  // Field description
+  method?: (param: Type) => ReturnType;  // Optional method
+}
+```
+
+### 4. Type Definitions
+
+For each exported type, provide:
+```typescript
+/**
+ * Brief description of what this type represents
+ */
+export type TypeName = string | number | CustomType;
+```
+
+---
+
+## Part B: HTTP API (For Web Services, REST APIs, GraphQL)
+
+**Use this section when documenting**: HTTP endpoints, REST APIs, GraphQL APIs, webhooks.
+
+**Omit this section if**: This is a library/SDK with no HTTP interface.
+
+### 1. Overview
+
+[Brief description of the API's purpose and capabilities]
+
+**Base URL**:
+```
+Production: https://api.example.com/v1
+Staging: https://staging.api.example.com/v1
+Development: http://localhost:3000/api/v1
+```
+
+### 2. Authentication
+
+#### Authentication Method
+[e.g., JWT Bearer Token, OAuth2, API Keys]
+
+#### Obtaining Credentials
+```bash
+# Example: Login to get token
+curl -X POST https://api.example.com/v1/auth/login \
+  -H "Content-Type: application/json" \
+  -d '{"email": "user@example.com", "password": "password"}'
+```
+
+#### Using Credentials
+```http
+GET /api/resource HTTP/1.1
+Authorization: Bearer <token>
+```
+
+### 3. Common Response Codes
+
+| Code | Description | Common Causes |
+|------|-------------|---------------|
+| 200  | Success | Request completed successfully |
+| 201  | Created | Resource created successfully |
+| 400  | Bad Request | Invalid request body or parameters |
+| 401  | Unauthorized | Missing or invalid authentication |
+| 403  | Forbidden | Authenticated but not authorized |
+| 404  | Not Found | Resource does not exist |
+| 429  | Too Many Requests | Rate limit exceeded |
+| 500  | Internal Server Error | Server-side error |
+
+### 4. Endpoints
+
+#### Resource: [Resource Name, e.g., Users]
+
+##### GET /resource
+**Description**: [What this endpoint does]
+
+**Query Parameters**:
+| Parameter | Type | Required | Description | Default |
+|-----------|------|----------|-------------|---------|
+| `limit` | number | No | Number of results | 20 |
+| `offset` | number | No | Pagination offset | 0 |
+
+**Example Request**:
+```http
+GET /users?limit=10&offset=0 HTTP/1.1
+Authorization: Bearer <token>
+```
+
+**Response (200 OK)**:
+```json
+{
+  "data": [
+    {
+      "id": 1,
+      "name": "John Doe",
+      "email": "john@example.com"
+    }
+  ],
+  "pagination": {
+    "total": 100,
+    "limit": 10,
+    "offset": 0
+  }
+}
+```
+
+**Error Response (401 Unauthorized)**:
+```json
+{
+  "error": {
+    "code": "UNAUTHORIZED",
+    "message": "Invalid or expired token"
+  }
+}
+```
+
+---
+
+##### POST /resource
+**Description**: [What this endpoint does]
+
+**Request Body**:
+```json
+{
+  "field1": "value",
+  "field2": 123
+}
+```
+
+**Validation Rules**:
+- `field1`: Required, 2-100 characters
+- `field2`: Required, positive integer
+
+**Response (201 Created)**:
+```json
+{
+  "id": 124,
+  "field1": "value",
+  "field2": 123,
+  "created_at": "2024-01-20T12:00:00Z"
+}
+```
+
+---
+
+##### PUT /resource/:id
+**Description**: [What this endpoint does]
+
+**Path Parameters**:
+| Parameter | Type | Description |
+|-----------|------|-------------|
+| `id` | number | Resource ID |
+
+**Request Body** (all fields optional):
+```json
+{
+  "field1": "new value"
+}
+```
+
+**Response (200 OK)**:
+```json
+{
+  "id": 124,
+  "field1": "new value",
+  "updated_at": "2024-01-21T09:15:00Z"
+}
+```
+
+---
+
+##### DELETE /resource/:id
+**Description**: [What this endpoint does]
+
+**Path Parameters**:
+| Parameter | Type | Description |
+|-----------|------|-------------|
+| `id` | number | Resource ID |
+
+**Response (204 No Content)**:
+[Empty response body]
+
+---
+
+### 5. Rate Limiting
+
+- **Limit**: 1000 requests per hour per API key
+- **Headers**:
+  - `X-RateLimit-Limit`: Total requests allowed
+  - `X-RateLimit-Remaining`: Requests remaining
+  - `X-RateLimit-Reset`: Unix timestamp when limit resets
+
+**Example Response Headers**:
+```http
+X-RateLimit-Limit: 1000
+X-RateLimit-Remaining: 847
+X-RateLimit-Reset: 1640000000
+```
+
+### 6. Webhooks (Optional)
+
+[Description of webhook system if applicable]
+
+**Webhook Events**:
+- `resource.created` - Triggered when a new resource is created
+- `resource.updated` - Triggered when a resource is updated
+- `resource.deleted` - Triggered when a resource is deleted
+
+**Webhook Payload Example**:
+```json
+{
+  "event": "resource.created",
+  "timestamp": "2024-01-20T12:00:00Z",
+  "data": {
+    "id": 124,
+    "field1": "value"
+  }
+}
+```
+
+---
+
+## Rules
+
+1. **Include only relevant sections** - Skip Part A for pure web services, skip Part B for pure libraries
+2. **Signatures only in Part A** - No implementation code in Code API section
+3. **Complete examples in Part B** - All HTTP examples should be runnable
+4. **Consistent formatting** - Use language-specific code blocks (TypeScript, HTTP, JSON, bash)
+5. **Brief descriptions** - One line per item is sufficient for Code API
+6. **Detailed explanations for HTTP** - Include request/response examples, validation rules, error cases
+7. **Alphabetical order** - Sort items within each section for easy lookup
+8. **Public API only** - Do not document internal/private exports or endpoints
+
+---
+
+## Template Usage Guidelines
+
+### For Module-Level API.md (Code API)
+**Use**: Part A only
+**Location**: `modules/[module-name]/API.md`
+**Focus**: Exported functions, classes, interfaces
+
+### For Project-Level HTTP API Documentation
+**Use**: Part B only
+**Location**: `.workflow/docs/api/README.md`
+**Focus**: REST/GraphQL endpoints, authentication
+
+### For Full-Stack Projects (Both Code and HTTP APIs)
+**Use**: Both Part A and Part B
+**Organization**:
+- Part A for SDK/client library APIs
+- Part B for HTTP endpoints
+
+---
+
+**Last Updated**: [Auto-generated timestamp]
+**API Version**: [Version number]
+**Module/Service Path**: [Auto-fill with actual path]

.claude/workflows/cli-templates/prompts/documentation/folder-navigation.txt

@@ -0,0 +1,68 @@
+# Folder Navigation Documentation Template
+
+Generate a navigation README for directories that contain only subdirectories (no code files). This serves as an index to help readers navigate to specific modules.
+
+## Structure
+
+### 1. Overview
+
+Brief description of what this directory/category contains:
+
+> The `modules/` directory contains the core business logic modules of the application. Each subdirectory represents a self-contained functional module with its own responsibilities.
+
+### 2. Directory Structure
+
+Provide a tree view of the subdirectories with brief descriptions:
+
+```
+modules/
+├── auth/              - User authentication and authorization
+├── api/               - API route handlers and middleware
+├── database/          - Database connections and ORM models
+└── utils/             - Shared utility functions
+```
+
+### 3. Module Quick Reference
+
+Table format for quick scanning:
+
+| Module | Purpose | Key Features |
+|--------|---------|--------------|
+| [auth](./auth/) | Authentication | JWT tokens, session management |
+| [api](./api/) | API routing | REST endpoints, validation |
+| [database](./database/) | Data layer | PostgreSQL, migrations |
+| [utils](./utils/) | Utilities | Logging, helpers |
+
+### 4. How to Navigate
+
+Guidance on which module to explore based on needs:
+
+- **For authentication logic** → [auth module](./auth/)
+- **For API endpoints** → [api module](./api/)
+- **For database queries** → [database module](./database/)
+- **For helper functions** → [utils module](./utils/)
+
+### 5. Module Relationships (Optional)
+
+If modules have significant dependencies, show them:
+
+```
+api → auth (uses for authentication)
+api → database (uses for data access)
+auth → database (uses for user storage)
+```
+
+---
+
+## Rules
+
+1. **Keep it brief** - This is an index, not detailed documentation
+2. **One-line descriptions** - Each module gets a concise purpose statement
+3. **Scannable format** - Use tables and lists for quick navigation
+4. **Link to submodules** - Every module mentioned should link to its README
+5. **No code examples** - This is navigation only
+
+---
+
+**Directory Path**: [Auto-fill with actual directory path]
+**Last Updated**: [Auto-generated timestamp]

.claude/workflows/cli-templates/prompts/documentation/module-readme.txt

@@ -0,0 +1,98 @@
+# Module README Documentation Template
+
+Generate comprehensive module documentation focused on understanding and usage. Explain WHAT the module does, WHY it exists, and HOW to use it. Do NOT duplicate API signatures (those belong in API.md).
+
+## Structure
+
+### 1. Purpose
+
+**What**: Clearly state what this module is responsible for
+**Why**: Explain why this module exists and what problems it solves
+**Boundaries**: Define what is IN scope and OUT of scope
+
+Example:
+> The `auth` module handles user authentication and authorization. It exists to centralize security logic and provide a consistent authentication interface across the application. It does NOT handle user profile management or session storage.
+
+### 2. Core Concepts
+
+List and explain key concepts, patterns, or abstractions used by this module:
+
+- **Concept 1**: [Brief explanation of important concept]
+- **Concept 2**: [Another key concept users should understand]
+- **Pattern**: [Architectural pattern used, e.g., "Uses middleware pattern for request processing"]
+
+### 3. Usage Scenarios
+
+Provide 2-4 common use cases with code examples:
+
+#### Scenario 1: [Common use case title]
+```typescript
+// Brief example showing how to use the module for this scenario
+import { functionName } from './module';
+
+const result = functionName(input);
+```
+
+#### Scenario 2: [Another common use case]
+```typescript
+// Another practical example
+```
+
+### 4. Dependencies
+
+#### Internal Dependencies
+List other project modules this module depends on and explain why:
+- **[Module Name]** - [Why this dependency exists and what it provides]
+
+#### External Dependencies
+List third-party libraries and their purpose:
+- **[Library Name]** (`version`) - [What functionality it provides to this module]
+
+### 5. Configuration
+
+#### Environment Variables
+List any environment variables the module uses:
+- `ENV_VAR_NAME` - [Description, type, default value]
+
+#### Configuration Options
+If the module accepts configuration objects:
+```typescript
+// Example configuration
+const config = {
+  option1: value,  // Description of option1
+  option2: value,  // Description of option2
+};
+```
+
+### 6. Testing
+
+Explain how to test code that uses this module:
+```bash
+# Command to run tests for this module
+npm test -- path/to/module
+```
+
+**Test Coverage**: [Brief note on what's tested]
+
+### 7. Common Issues
+
+List 2-3 common problems and their solutions:
+
+#### Issue: [Common problem description]
+**Solution**: [How to resolve it]
+
+---
+
+## Rules
+
+1. **No API duplication** - Refer to API.md for signatures
+2. **Focus on understanding** - Explain concepts, not just code
+3. **Practical examples** - Show real usage, not trivial cases
+4. **Clear dependencies** - Help readers understand module relationships
+5. **Concise** - Each section should be scannable and to-the-point
+
+---
+
+**Module Path**: [Auto-fill with actual module path]
+**Last Updated**: [Auto-generated timestamp]
+**See also**: [Link to API.md for interface details]

.claude/workflows/cli-templates/prompts/documentation/project-architecture.txt

@@ -0,0 +1,167 @@
+# Project Architecture Documentation Template
+
+Generate comprehensive architecture documentation that synthesizes information from all module documents. Focus on system-level design, module relationships, and aggregated API overview. This document should be created AFTER all module documentation is complete.
+
+## Structure
+
+### 1. System Overview
+
+High-level description of the system architecture:
+
+**Architectural Style**: [e.g., Layered, Microservices, Event-Driven, Hexagonal]
+
+**Core Principles**:
+- [Principle 1, e.g., "Separation of concerns"]
+- [Principle 2, e.g., "Dependency inversion"]
+- [Principle 3, e.g., "Single responsibility"]
+
+**Technology Stack**:
+- **Languages**: [Primary programming languages]
+- **Frameworks**: [Key frameworks]
+- **Databases**: [Data storage solutions]
+- **Infrastructure**: [Deployment, hosting, CI/CD]
+
+### 2. System Structure
+
+Visual representation of the system structure using text diagrams:
+
+```
+┌─────────────────────────────────────┐
+│         Application Layer           │
+│  (API Routes, Controllers)          │
+└────────────┬────────────────────────┘
+             │
+┌────────────▼────────────────────────┐
+│       Business Logic Layer          │
+│  (Modules: auth, orders, payments)  │
+└────────────┬────────────────────────┘
+             │
+┌────────────▼────────────────────────┐
+│        Data Access Layer            │
+│  (Database, ORM, Repositories)      │
+└─────────────────────────────────────┘
+```
+
+### 3. Module Map
+
+Comprehensive list of all modules with their responsibilities:
+
+| Module | Layer | Responsibility | Dependencies |
+|--------|-------|----------------|--------------|
+| `auth` | Business | Authentication & authorization | database, utils |
+| `api` | Application | HTTP routing & validation | auth, orders |
+| `database` | Data | Data persistence | - |
+| `utils` | Infrastructure | Shared utilities | - |
+
+### 4. Module Interactions
+
+Describe key interaction patterns between modules:
+
+#### Data Flow Example: User Authentication
+```
+1. Client → api/login endpoint
+2. api → auth.authenticateUser()
+3. auth → database.findUser()
+4. database → PostgreSQL
+5. auth → JWT token generation
+6. api → Response with token
+```
+
+#### Dependency Graph
+```
+api ──────┐
+          ├──→ auth ───→ database
+orders ───┤              ↑
+          └──────────────┘
+```
+
+### 5. Design Patterns
+
+Document key architectural patterns used:
+
+#### Pattern 1: [Pattern Name, e.g., "Repository Pattern"]
+- **Where**: [Which modules use this pattern]
+- **Why**: [Reason for using this pattern]
+- **How**: [Brief explanation of implementation]
+
+#### Pattern 2: [Another pattern]
+[Similar structure]
+
+### 6. Aggregated API Overview
+
+High-level summary of all public APIs across modules. Group by category:
+
+#### Authentication APIs
+- `auth.authenticate(credentials)` - Validate user credentials
+- `auth.authorize(user, permission)` - Check user permissions
+- `auth.generateToken(userId)` - Create JWT token
+
+#### Data APIs
+- `database.findOne(query)` - Find single record
+- `database.findMany(query)` - Find multiple records
+- `database.insert(data)` - Insert new record
+
+#### Utility APIs
+- `utils.logger.log(message)` - Application logging
+- `utils.validator.validate(data, schema)` - Data validation
+
+*Note: For detailed API signatures, refer to individual module API.md files*
+
+### 7. Data Flow
+
+Describe how data moves through the system:
+
+**Request Lifecycle**:
+1. HTTP request enters through API layer
+2. Request validation and authentication (auth module)
+3. Business logic processing (domain modules)
+4. Data persistence (database module)
+5. Response formatting and return
+
+**Event Flow** (if applicable):
+- [Describe event-driven flows if present]
+
+### 8. Security Architecture
+
+Overview of security measures:
+
+- **Authentication**: [JWT, OAuth2, etc.]
+- **Authorization**: [RBAC, ACL, etc.]
+- **Data Protection**: [Encryption, hashing]
+- **API Security**: [Rate limiting, CORS, etc.]
+
+### 9. Scalability Considerations
+
+Architectural decisions that support scalability:
+
+- [Horizontal scaling approach]
+- [Caching strategy]
+- [Database optimization]
+- [Load balancing]
+
+---
+
+## Rules
+
+1. **Synthesize, don't duplicate** - Reference module docs, don't copy them
+2. **System-level perspective** - Focus on how modules work together
+3. **Visual aids** - Use diagrams for clarity (ASCII art is fine)
+4. **Aggregated APIs** - One-line summaries only, link to detailed docs
+5. **Design rationale** - Explain WHY decisions were made
+6. **Maintain consistency** - Ensure all module docs are considered
+
+---
+
+## Required Inputs
+
+This document requires the following to be available:
+- All module README.md files (for understanding module purposes)
+- All module API.md files (for aggregating API overview)
+- Project README.md (for context and navigation)
+
+---
+
+**Last Updated**: [Auto-generated timestamp]
+**See also**:
+- [Project README](./README.md) for project overview
+- [Module Documentation](./modules/) for detailed module docs

.claude/workflows/cli-templates/prompts/documentation/project-examples.txt

@@ -0,0 +1,205 @@
+# Project Examples Documentation Template
+
+Generate practical, end-to-end examples demonstrating core usage patterns of the project. Focus on realistic scenarios that span multiple modules. These examples should help users understand how to accomplish common tasks.
+
+## Structure
+
+### 1. Introduction
+
+Brief overview of what these examples cover:
+
+> This document provides complete, working examples for common use cases. Each example demonstrates how multiple modules work together to accomplish a specific task.
+
+**Prerequisites**:
+- [List required setup, e.g., "Project installed and configured"]
+- [Environment requirements, e.g., "PostgreSQL running on localhost"]
+
+### 2. Quick Start Example
+
+The simplest possible working example to get started:
+
+```typescript
+// The minimal example to verify setup
+import { App } from './src';
+
+const app = new App();
+await app.start();
+console.log('Application running!');
+```
+
+**What this does**: [Brief explanation]
+
+### 3. Core Use Cases
+
+Provide 3-5 complete examples for common scenarios:
+
+#### Example 1: [Scenario Name, e.g., "User Registration and Login"]
+
+**Objective**: [What this example accomplishes]
+
+**Modules involved**: `auth`, `database`, `api`
+
+**Complete code**:
+```typescript
+import { createUser, authenticateUser } from './modules/auth';
+import { startServer } from './modules/api';
+
+// Step 1: Initialize the application
+const app = await startServer({ port: 3000 });
+
+// Step 2: Register a new user
+const user = await createUser({
+  email: 'user@example.com',
+  password: 'securePassword123',
+  name: 'John Doe'
+});
+
+// Step 3: Authenticate the user
+const session = await authenticateUser({
+  email: 'user@example.com',
+  password: 'securePassword123'
+});
+
+// Step 4: Use the authentication token
+console.log('Login successful, token:', session.token);
+```
+
+**Expected output**:
+```
+Server started on port 3000
+User created: { id: 1, email: 'user@example.com', name: 'John Doe' }
+Login successful, token: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9...
+```
+
+**Explanation**:
+1. [Step-by-step breakdown of what each part does]
+2. [How modules interact]
+3. [Common variations or customizations]
+
+---
+
+#### Example 2: [Another Common Scenario]
+
+[Similar structure with complete code]
+
+---
+
+#### Example 3: [Another Use Case]
+
+[Similar structure with complete code]
+
+### 4. Advanced Examples
+
+More complex scenarios for power users:
+
+#### Advanced Example 1: [Complex Scenario]
+
+**Objective**: [What this example accomplishes]
+
+**Modules involved**: [List]
+
+```typescript
+// Complete working code with detailed comments
+```
+
+**Key points**:
+- [Important concept or gotcha]
+- [Performance consideration]
+- [Security note]
+
+### 5. Integration Examples
+
+Examples showing how to integrate with external systems:
+
+#### Integration with [External System]
+
+```typescript
+// Example of integrating with a third-party service
+```
+
+### 6. Testing Examples
+
+Show how to test code that uses this project:
+
+```typescript
+// Example test case using the project
+import { describe, it, expect } from 'your-test-framework';
+
+describe('User authentication', () => {
+  it('should authenticate valid credentials', async () => {
+    const result = await authenticateUser({
+      email: 'test@example.com',
+      password: 'password123'
+    });
+
+    expect(result.success).toBe(true);
+    expect(result.token).toBeDefined();
+  });
+});
+```
+
+### 7. Best Practices
+
+Demonstrate recommended patterns:
+
+#### Pattern 1: [Best Practice Title]
+```typescript
+// Good: Recommended approach
+const result = await handleWithErrorRecovery(operation);
+
+// Bad: Anti-pattern to avoid
+const result = operation(); // No error handling
+```
+
+**Why**: [Explanation of why this is the best approach]
+
+#### Pattern 2: [Another Best Practice]
+[Similar structure]
+
+### 8. Troubleshooting Common Issues
+
+Example-based solutions to common problems:
+
+#### Issue: [Common Problem]
+
+**Symptom**: [What the user experiences]
+
+**Solution**:
+```typescript
+// Before: Code that causes the issue
+const broken = doSomethingWrong();
+
+// After: Corrected code
+const fixed = doSomethingRight();
+```
+
+---
+
+## Rules
+
+1. **Complete, runnable code** - Every example should be copy-paste ready
+2. **Real-world scenarios** - Avoid trivial or contrived examples
+3. **Explain the flow** - Show how modules work together
+4. **Include output** - Show what users should expect to see
+5. **Error handling** - Demonstrate proper error handling patterns
+6. **Comment complex parts** - Help readers understand non-obvious code
+7. **Version compatibility** - Note if examples are version-specific
+
+---
+
+## Code Quality Standards
+
+All example code should:
+- Follow project coding standards
+- Include proper error handling
+- Use async/await correctly
+- Show TypeScript types where applicable
+- Be tested and verified to work
+
+---
+
+**Last Updated**: [Auto-generated timestamp]
+**See also**:
+- [Project README](./README.md) for getting started
+- [Architecture](./ARCHITECTURE.md) for understanding system design
+- [Module Documentation](./modules/) for API details

.claude/workflows/cli-templates/prompts/documentation/project-readme.txt

@@ -0,0 +1,58 @@
+# Project-Level Documentation Template
+
+Generate comprehensive project documentation following this structure:
+
+## 1. Overview
+- **Purpose**: [High-level mission and goals of the project]
+- **Target Audience**: [Primary users, developers, stakeholders]
+- **Key Features**: [List of major functionalities and capabilities]
+
+## 2. System Architecture
+- **Architectural Style**: [e.g., Monolith, Microservices, Layered, Event-Driven]
+- **Core Components**: [Diagram or list of major system parts and their interactions]
+- **Technology Stack**:
+  - Languages: [Programming languages used]
+  - Frameworks: [Key frameworks and libraries]
+  - Databases: [Data storage solutions]
+  - Infrastructure: [Deployment and hosting]
+- **Design Principles**: [Guiding principles like SOLID, DRY, separation of concerns]
+
+## 3. Getting Started
+- **Prerequisites**: [Required software, tools, versions]
+- **Installation**:
+  ```bash
+  # Installation commands
+  ```
+- **Configuration**: [Environment setup, config files]
+- **Running the Project**:
+  ```bash
+  # Startup commands
+  ```
+
+## 4. Development Workflow
+- **Branching Strategy**: [e.g., GitFlow, trunk-based]
+- **Coding Standards**: [Style guide, linting rules]
+- **Testing**:
+  ```bash
+  # Test commands
+  ```
+- **Build & Deployment**: [CI/CD pipeline overview]
+
+## 5. Project Structure
+```
+project-root/
+├── src/           # [Description]
+├── tests/         # [Description]
+├── docs/          # [Description]
+└── config/        # [Description]
+```
+
+## 6. Navigation
+- [Module Documentation](./modules/)
+- [API Reference](./api/)
+- [Architecture Details](./architecture/)
+- [Contributing Guidelines](./CONTRIBUTING.md)
+
+---
+**Last Updated**: [Auto-generated timestamp]
+**Documentation Version**: [Project version]

.claude/workflows/cli-templates/prompts/memory/hierarchy-analysis.txt

@@ -1,4 +1,4 @@
-Analyze project structure for DMS hierarchy optimization:
+Analyze project structure for memory hierarchy optimization:
 
 ## Required Analysis:
 1. Assess project complexity and file organization patterns

.claude/workflows/design-tokens-schema.md

@@ -0,0 +1,534 @@
+---
+name: design-tokens-schema
+description: Design tokens JSON schema specification for UI design workflow
+type: specification
+---
+
+# Design Tokens Schema Specification
+
+## Overview
+Standardized JSON schema for design tokens used in `/workflow:design/*` commands. Ensures consistency across style extraction, consolidation, and UI generation phases.
+
+## Core Principles
+
+1. **OKLCH Color Format**: All colors use OKLCH color space for perceptual uniformity
+2. **Semantic Naming**: User-centric token names (brand-primary, surface-elevated, not color-1, bg-2)
+3. **rem-Based Sizing**: All spacing and typography use rem units for scalability
+4. **Comprehensive Coverage**: Complete token set for production-ready design systems
+5. **Accessibility First**: WCAG AA compliance validated and documented
+
+## Full Schema
+
+```json
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "Design Tokens",
+  "description": "Design token definitions for UI design workflow",
+  "type": "object",
+  "required": ["colors", "typography", "spacing", "border_radius", "shadow"],
+  "properties": {
+    "meta": {
+      "type": "object",
+      "properties": {
+        "version": {"type": "string", "pattern": "^\\d+\\.\\d+\\.\\d+$"},
+        "generated_at": {"type": "string", "format": "date-time"},
+        "session_id": {"type": "string", "pattern": "^WFS-"},
+        "description": {"type": "string"}
+      }
+    },
+    "colors": {
+      "type": "object",
+      "required": ["brand", "surface", "semantic", "text"],
+      "properties": {
+        "brand": {
+          "type": "object",
+          "description": "Brand identity colors",
+          "required": ["primary", "secondary"],
+          "properties": {
+            "primary": {"$ref": "#/definitions/color"},
+            "secondary": {"$ref": "#/definitions/color"},
+            "accent": {"$ref": "#/definitions/color"}
+          }
+        },
+        "surface": {
+          "type": "object",
+          "description": "Surface and background colors",
+          "required": ["background", "elevated"],
+          "properties": {
+            "background": {"$ref": "#/definitions/color"},
+            "elevated": {"$ref": "#/definitions/color"},
+            "sunken": {"$ref": "#/definitions/color"},
+            "overlay": {"$ref": "#/definitions/color"}
+          }
+        },
+        "semantic": {
+          "type": "object",
+          "description": "Semantic state colors",
+          "required": ["success", "warning", "error", "info"],
+          "properties": {
+            "success": {"$ref": "#/definitions/color"},
+            "warning": {"$ref": "#/definitions/color"},
+            "error": {"$ref": "#/definitions/color"},
+            "info": {"$ref": "#/definitions/color"}
+          }
+        },
+        "text": {
+          "type": "object",
+          "description": "Text colors with WCAG AA validated contrast",
+          "required": ["primary", "secondary"],
+          "properties": {
+            "primary": {"$ref": "#/definitions/color"},
+            "secondary": {"$ref": "#/definitions/color"},
+            "tertiary": {"$ref": "#/definitions/color"},
+            "inverse": {"$ref": "#/definitions/color"},
+            "disabled": {"$ref": "#/definitions/color"}
+          }
+        },
+        "border": {
+          "type": "object",
+          "description": "Border and divider colors",
+          "properties": {
+            "subtle": {"$ref": "#/definitions/color"},
+            "default": {"$ref": "#/definitions/color"},
+            "strong": {"$ref": "#/definitions/color"}
+          }
+        }
+      }
+    },
+    "typography": {
+      "type": "object",
+      "required": ["font_family", "font_size", "line_height", "font_weight"],
+      "properties": {
+        "font_family": {
+          "type": "object",
+          "required": ["heading", "body"],
+          "properties": {
+            "heading": {"type": "string"},
+            "body": {"type": "string"},
+            "mono": {"type": "string"}
+          }
+        },
+        "font_size": {
+          "type": "object",
+          "required": ["xs", "sm", "base", "lg", "xl", "2xl", "3xl", "4xl"],
+          "properties": {
+            "xs": {"$ref": "#/definitions/size_rem"},
+            "sm": {"$ref": "#/definitions/size_rem"},
+            "base": {"$ref": "#/definitions/size_rem"},
+            "lg": {"$ref": "#/definitions/size_rem"},
+            "xl": {"$ref": "#/definitions/size_rem"},
+            "2xl": {"$ref": "#/definitions/size_rem"},
+            "3xl": {"$ref": "#/definitions/size_rem"},
+            "4xl": {"$ref": "#/definitions/size_rem"},
+            "5xl": {"$ref": "#/definitions/size_rem"}
+          }
+        },
+        "line_height": {
+          "type": "object",
+          "required": ["tight", "normal", "relaxed"],
+          "properties": {
+            "tight": {"type": "string", "pattern": "^\\d+(\\.\\d+)?$"},
+            "normal": {"type": "string", "pattern": "^\\d+(\\.\\d+)?$"},
+            "relaxed": {"type": "string", "pattern": "^\\d+(\\.\\d+)?$"}
+          }
+        },
+        "font_weight": {
+          "type": "object",
+          "properties": {
+            "light": {"type": "integer", "enum": [300]},
+            "normal": {"type": "integer", "enum": [400]},
+            "medium": {"type": "integer", "enum": [500]},
+            "semibold": {"type": "integer", "enum": [600]},
+            "bold": {"type": "integer", "enum": [700]}
+          }
+        }
+      }
+    },
+    "spacing": {
+      "type": "object",
+      "description": "Spacing scale (rem-based)",
+      "required": ["0", "1", "2", "3", "4", "6", "8"],
+      "patternProperties": {
+        "^\\d+$": {"$ref": "#/definitions/size_rem"}
+      }
+    },
+    "border_radius": {
+      "type": "object",
+      "required": ["none", "sm", "md", "lg", "full"],
+      "properties": {
+        "none": {"type": "string", "const": "0"},
+        "sm": {"$ref": "#/definitions/size_rem"},
+        "md": {"$ref": "#/definitions/size_rem"},
+        "lg": {"$ref": "#/definitions/size_rem"},
+        "xl": {"$ref": "#/definitions/size_rem"},
+        "2xl": {"$ref": "#/definitions/size_rem"},
+        "full": {"type": "string", "const": "9999px"}
+      }
+    },
+    "shadow": {
+      "type": "object",
+      "required": ["sm", "md", "lg"],
+      "properties": {
+        "none": {"type": "string", "const": "none"},
+        "sm": {"type": "string"},
+        "md": {"type": "string"},
+        "lg": {"type": "string"},
+        "xl": {"type": "string"},
+        "2xl": {"type": "string"}
+      }
+    },
+    "breakpoint": {
+      "type": "object",
+      "description": "Responsive breakpoints",
+      "properties": {
+        "sm": {"type": "string", "pattern": "^\\d+px$"},
+        "md": {"type": "string", "pattern": "^\\d+px$"},
+        "lg": {"type": "string", "pattern": "^\\d+px$"},
+        "xl": {"type": "string", "pattern": "^\\d+px$"},
+        "2xl": {"type": "string", "pattern": "^\\d+px$"}
+      }
+    },
+    "accessibility": {
+      "type": "object",
+      "description": "WCAG AA compliance data",
+      "properties": {
+        "contrast_ratios": {
+          "type": "object",
+          "patternProperties": {
+            ".*": {
+              "type": "object",
+              "properties": {
+                "background": {"type": "string"},
+                "foreground": {"type": "string"},
+                "ratio": {"type": "number"},
+                "wcag_aa_pass": {"type": "boolean"},
+                "wcag_aaa_pass": {"type": "boolean"}
+              }
+            }
+          }
+        }
+      }
+    }
+  },
+  "definitions": {
+    "color": {
+      "type": "string",
+      "pattern": "^oklch\\(\\s*\\d+(\\.\\d+)?\\s+\\d+(\\.\\d+)?\\s+\\d+(\\.\\d+)?\\s*(\\/\\s*\\d+(\\.\\d+)?)?\\s*\\)$",
+      "description": "OKLCH color format: oklch(L C H / A)"
+    },
+    "size_rem": {
+      "type": "string",
+      "pattern": "^\\d+(\\.\\d+)?rem$",
+      "description": "rem-based size value"
+    }
+  }
+}
+```
+
+## Example: Complete Design Tokens
+
+```json
+{
+  "meta": {
+    "version": "1.0.0",
+    "generated_at": "2025-10-05T15:30:00Z",
+    "session_id": "WFS-auth-dashboard",
+    "description": "Modern minimalist design system with high contrast"
+  },
+  "colors": {
+    "brand": {
+      "primary": "oklch(0.45 0.20 270 / 1)",
+      "secondary": "oklch(0.60 0.15 200 / 1)",
+      "accent": "oklch(0.65 0.18 30 / 1)"
+    },
+    "surface": {
+      "background": "oklch(0.98 0.01 270 / 1)",
+      "elevated": "oklch(1.00 0.00 0 / 1)",
+      "sunken": "oklch(0.95 0.02 270 / 1)",
+      "overlay": "oklch(0.00 0.00 0 / 0.5)"
+    },
+    "semantic": {
+      "success": "oklch(0.55 0.15 150 / 1)",
+      "warning": "oklch(0.70 0.18 60 / 1)",
+      "error": "oklch(0.50 0.20 20 / 1)",
+      "info": "oklch(0.60 0.15 240 / 1)"
+    },
+    "text": {
+      "primary": "oklch(0.20 0.02 270 / 1)",
+      "secondary": "oklch(0.45 0.02 270 / 1)",
+      "tertiary": "oklch(0.60 0.02 270 / 1)",
+      "inverse": "oklch(0.98 0.01 270 / 1)",
+      "disabled": "oklch(0.70 0.01 270 / 0.5)"
+    },
+    "border": {
+      "subtle": "oklch(0.90 0.01 270 / 1)",
+      "default": "oklch(0.80 0.02 270 / 1)",
+      "strong": "oklch(0.60 0.05 270 / 1)"
+    }
+  },
+  "typography": {
+    "font_family": {
+      "heading": "Inter, system-ui, -apple-system, sans-serif",
+      "body": "Inter, system-ui, -apple-system, sans-serif",
+      "mono": "Fira Code, Consolas, monospace"
+    },
+    "font_size": {
+      "xs": "0.75rem",
+      "sm": "0.875rem",
+      "base": "1rem",
+      "lg": "1.125rem",
+      "xl": "1.25rem",
+      "2xl": "1.5rem",
+      "3xl": "1.875rem",
+      "4xl": "2.25rem",
+      "5xl": "3rem"
+    },
+    "line_height": {
+      "tight": "1.25",
+      "normal": "1.5",
+      "relaxed": "1.75"
+    },
+    "font_weight": {
+      "light": 300,
+      "normal": 400,
+      "medium": 500,
+      "semibold": 600,
+      "bold": 700
+    }
+  },
+  "spacing": {
+    "0": "0",
+    "1": "0.25rem",
+    "2": "0.5rem",
+    "3": "0.75rem",
+    "4": "1rem",
+    "5": "1.25rem",
+    "6": "1.5rem",
+    "8": "2rem",
+    "10": "2.5rem",
+    "12": "3rem",
+    "16": "4rem",
+    "20": "5rem",
+    "24": "6rem"
+  },
+  "border_radius": {
+    "none": "0",
+    "sm": "0.25rem",
+    "md": "0.5rem",
+    "lg": "0.75rem",
+    "xl": "1rem",
+    "2xl": "1.5rem",
+    "full": "9999px"
+  },
+  "shadow": {
+    "none": "none",
+    "sm": "0 1px 2px oklch(0.00 0.00 0 / 0.05)",
+    "md": "0 4px 6px oklch(0.00 0.00 0 / 0.07), 0 2px 4px oklch(0.00 0.00 0 / 0.06)",
+    "lg": "0 10px 15px oklch(0.00 0.00 0 / 0.1), 0 4px 6px oklch(0.00 0.00 0 / 0.05)",
+    "xl": "0 20px 25px oklch(0.00 0.00 0 / 0.15), 0 10px 10px oklch(0.00 0.00 0 / 0.04)",
+    "2xl": "0 25px 50px oklch(0.00 0.00 0 / 0.25)"
+  },
+  "breakpoint": {
+    "sm": "640px",
+    "md": "768px",
+    "lg": "1024px",
+    "xl": "1280px",
+    "2xl": "1536px"
+  },
+  "accessibility": {
+    "contrast_ratios": {
+      "text_primary_on_background": {
+        "background": "oklch(0.98 0.01 270 / 1)",
+        "foreground": "oklch(0.20 0.02 270 / 1)",
+        "ratio": 14.2,
+        "wcag_aa_pass": true,
+        "wcag_aaa_pass": true
+      },
+      "brand_primary_on_background": {
+        "background": "oklch(0.98 0.01 270 / 1)",
+        "foreground": "oklch(0.45 0.20 270 / 1)",
+        "ratio": 6.8,
+        "wcag_aa_pass": true,
+        "wcag_aaa_pass": false
+      }
+    }
+  }
+}
+```
+
+## CSS Custom Properties Generation
+
+Design tokens should be converted to CSS custom properties for use in generated UI:
+
+```css
+:root {
+  /* Brand Colors */
+  --color-brand-primary: oklch(0.45 0.20 270 / 1);
+  --color-brand-secondary: oklch(0.60 0.15 200 / 1);
+  --color-brand-accent: oklch(0.65 0.18 30 / 1);
+
+  /* Surface Colors */
+  --color-surface-background: oklch(0.98 0.01 270 / 1);
+  --color-surface-elevated: oklch(1.00 0.00 0 / 1);
+  --color-surface-sunken: oklch(0.95 0.02 270 / 1);
+
+  /* Semantic Colors */
+  --color-semantic-success: oklch(0.55 0.15 150 / 1);
+  --color-semantic-warning: oklch(0.70 0.18 60 / 1);
+  --color-semantic-error: oklch(0.50 0.20 20 / 1);
+  --color-semantic-info: oklch(0.60 0.15 240 / 1);
+
+  /* Text Colors */
+  --color-text-primary: oklch(0.20 0.02 270 / 1);
+  --color-text-secondary: oklch(0.45 0.02 270 / 1);
+  --color-text-tertiary: oklch(0.60 0.02 270 / 1);
+
+  /* Typography */
+  --font-family-heading: Inter, system-ui, sans-serif;
+  --font-family-body: Inter, system-ui, sans-serif;
+  --font-family-mono: Fira Code, Consolas, monospace;
+
+  --font-size-xs: 0.75rem;
+  --font-size-sm: 0.875rem;
+  --font-size-base: 1rem;
+  --font-size-lg: 1.125rem;
+  --font-size-xl: 1.25rem;
+  --font-size-2xl: 1.5rem;
+  --font-size-3xl: 1.875rem;
+  --font-size-4xl: 2.25rem;
+
+  --line-height-tight: 1.25;
+  --line-height-normal: 1.5;
+  --line-height-relaxed: 1.75;
+
+  /* Spacing */
+  --spacing-0: 0;
+  --spacing-1: 0.25rem;
+  --spacing-2: 0.5rem;
+  --spacing-3: 0.75rem;
+  --spacing-4: 1rem;
+  --spacing-6: 1.5rem;
+  --spacing-8: 2rem;
+  --spacing-12: 3rem;
+  --spacing-16: 4rem;
+
+  /* Border Radius */
+  --border-radius-none: 0;
+  --border-radius-sm: 0.25rem;
+  --border-radius-md: 0.5rem;
+  --border-radius-lg: 0.75rem;
+  --border-radius-xl: 1rem;
+  --border-radius-full: 9999px;
+
+  /* Shadows */
+  --shadow-sm: 0 1px 2px oklch(0.00 0.00 0 / 0.05);
+  --shadow-md: 0 4px 6px oklch(0.00 0.00 0 / 0.07), 0 2px 4px oklch(0.00 0.00 0 / 0.06);
+  --shadow-lg: 0 10px 15px oklch(0.00 0.00 0 / 0.1), 0 4px 6px oklch(0.00 0.00 0 / 0.05);
+}
+```
+
+## Tailwind Configuration Generation
+
+```javascript
+// tailwind.config.js
+module.exports = {
+  theme: {
+    extend: {
+      colors: {
+        brand: {
+          primary: 'oklch(0.45 0.20 270 / <alpha-value>)',
+          secondary: 'oklch(0.60 0.15 200 / <alpha-value>)',
+          accent: 'oklch(0.65 0.18 30 / <alpha-value>)'
+        },
+        surface: {
+          background: 'oklch(0.98 0.01 270 / <alpha-value>)',
+          elevated: 'oklch(1.00 0.00 0 / <alpha-value>)',
+          sunken: 'oklch(0.95 0.02 270 / <alpha-value>)'
+        },
+        semantic: {
+          success: 'oklch(0.55 0.15 150 / <alpha-value>)',
+          warning: 'oklch(0.70 0.18 60 / <alpha-value>)',
+          error: 'oklch(0.50 0.20 20 / <alpha-value>)',
+          info: 'oklch(0.60 0.15 240 / <alpha-value>)'
+        }
+      },
+      fontFamily: {
+        heading: ['Inter', 'system-ui', 'sans-serif'],
+        body: ['Inter', 'system-ui', 'sans-serif'],
+        mono: ['Fira Code', 'Consolas', 'monospace']
+      },
+      fontSize: {
+        'xs': '0.75rem',
+        'sm': '0.875rem',
+        'base': '1rem',
+        'lg': '1.125rem',
+        'xl': '1.25rem',
+        '2xl': '1.5rem',
+        '3xl': '1.875rem',
+        '4xl': '2.25rem'
+      },
+      spacing: {
+        '1': '0.25rem',
+        '2': '0.5rem',
+        '3': '0.75rem',
+        '4': '1rem',
+        '6': '1.5rem',
+        '8': '2rem',
+        '12': '3rem',
+        '16': '4rem'
+      },
+      borderRadius: {
+        'sm': '0.25rem',
+        'md': '0.5rem',
+        'lg': '0.75rem',
+        'xl': '1rem',
+        '2xl': '1.5rem'
+      },
+      boxShadow: {
+        'sm': '0 1px 2px oklch(0.00 0.00 0 / 0.05)',
+        'md': '0 4px 6px oklch(0.00 0.00 0 / 0.07), 0 2px 4px oklch(0.00 0.00 0 / 0.06)',
+        'lg': '0 10px 15px oklch(0.00 0.00 0 / 0.1), 0 4px 6px oklch(0.00 0.00 0 / 0.05)'
+      }
+    }
+  }
+}
+```
+
+## Validation Requirements
+
+### Color Validation
+- All colors MUST use OKLCH format
+- Alpha channel optional (defaults to 1)
+- Lightness: 0-1 (0% to 100%)
+- Chroma: 0-0.4 (typical range, can exceed for vibrant colors)
+- Hue: 0-360 (degrees)
+
+### Accessibility Validation
+- Text on background: minimum 4.5:1 contrast (WCAG AA)
+- Large text (18pt+ or 14pt+ bold): minimum 3:1 contrast
+- UI components: minimum 3:1 contrast
+- Non-text focus indicators: minimum 3:1 contrast
+
+### Consistency Validation
+- Spacing scale maintains consistent ratio (e.g., 1.5x or 2x progression)
+- Typography scale follows modular scale principles
+- Border radius values progress logically
+- Shadow layers increase in offset and blur systematically
+
+## Usage in Commands
+
+### style-extract Output
+Generates initial `design-tokens.json` from visual analysis
+
+### style-consolidate Output
+Finalizes validated `design-tokens.json` with accessibility data
+
+### ui-generate Input
+Reads `design-tokens.json` to generate CSS custom properties
+
+### design-update Integration
+References `design-tokens.json` path in synthesis-specification.md
+
+## Version History
+
+- **1.0.0**: Initial schema with OKLCH colors, semantic naming, WCAG AA validation

.claude/workflows/intelligent-tools-strategy.md

@@ -6,11 +6,22 @@ type: strategic-guideline
 
 # Intelligent Tools Selection Strategy
 
+## 📋 Table of Contents
+1. [Core Framework](#-core-framework)
+2. [Tool Specifications](#-tool-specifications)
+3. [Command Templates](#-command-templates)
+4. [Tool Selection Guide](#-tool-selection-guide)
+5. [Usage Patterns](#-usage-patterns)
+6. [Best Practices](#-best-practices)
+
+---
+
 ## ⚡ Core Framework
 
-**Gemini**: Analysis, understanding, exploration & documentation
-**Qwen**: Architecture analysis, code generation & implementation
-**Codex**: Development, implementation & automation
+### Tool Overview
+- **Gemini**: Analysis, understanding, exploration & documentation (primary)
+- **Qwen**: Analysis, understanding, exploration & documentation (fallback, same capabilities as Gemini)
+- **Codex**: Development, implementation & automation
 
 ### Decision Principles
 - **Use tools early and often** - Tools are faster, more thorough, and reliable than manual approaches
@@ -18,61 +29,92 @@ type: strategic-guideline
 - **Default to tools** - Use specialized tools for most coding tasks, no matter how small
 - **Lower barriers** - Engage tools immediately when encountering any complexity
 - **Context optimization** - Based on user intent, determine whether to use `-C [directory]` parameter for focused analysis to reduce irrelevant context import
+- **⚠️ Write operation protection** - For local codebase write/modify operations, require EXPLICIT user confirmation unless user provides clear instructions containing MODE=write or MODE=auto
 
 ### Quick Decision Rules
-1. **Exploring/Understanding?** → Start with Gemini
-2. **Architecture/Code generation?** → Start with Qwen
+1. **Exploring/Understanding?** → Start with Gemini (fallback to Qwen if needed)
+2. **Architecture/Analysis?** → Start with Gemini (fallback to Qwen if needed)
 3. **Building/Fixing?** → Start with Codex
 4. **Not sure?** → Use multiple tools in parallel
 5. **Small task?** → Still use tools - they're faster than manual work
 
-### Core Execution Rules
-- **Default Timeout**: Bash commands default execution time = 20 minutes (1200000ms)
-- **Apply to All Tools**: All bash() wrapped commands including Gemini, Qwen wrapper and Codex executions use this timeout
-- **Command Examples**: `bash(cd target/directory && ~/.claude/scripts/gemini-wrapper -p "prompt")`, `bash(cd target/directory && ~/.claude/scripts/qwen-wrapper -p "prompt")`, `bash(codex -C directory --full-auto exec "task")`
-- **Override When Needed**: Specify custom timeout for longer operations
+---
 
-### Permission Framework
-- **Gemini/Qwen Write Access**: Use `--approval-mode yolo` when tools need to create/modify files
-- **Codex Write Access**: Always use `-s danger-full-access` and `--skip-git-repo-check` for development and file operations
-- **Auto-approval Protocol**: Enable automatic tool approvals for autonomous workflow execution
+## 🎯 Tool Specifications
 
-## 🎯 Universal Command Template
+### Gemini
+- **Command**: `~/.claude/scripts/gemini-wrapper`
+- **Strengths**: Large context window, pattern recognition
+- **Best For**: Analysis, documentation generation, code exploration
+- **Permissions**: Default read-only analysis, MODE=write requires explicit specification (auto-enables --approval-mode yolo)
+- **Default MODE**: `analysis` (read-only)
+- **⚠️ Write Trigger**: Only when user explicitly requests "generate documentation", "modify code", or specifies MODE=write
 
-### Standard Format (REQUIRED)
-```bash
-# Gemini Analysis (全权限)
-cd [directory] && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: [clear analysis goal]
-TASK: [specific analysis task]
-MODE: [analysis|write]
-CONTEXT: [file references and memory context]
-EXPECTED: [expected output]
-RULES: [template reference and constraints]
-"
+#### MODE Options
+- `analysis` (default) - Read-only analysis and documentation generation
+- `write` - ⚠️ Create/modify codebase files (requires explicit specification, auto-enables --approval-mode yolo)
 
-# Qwen Architecture Analysis (仅分析)
-cd [directory] && ~/.claude/scripts/qwen-wrapper -p "
-PURPOSE: [clear architecture goal]
-TASK: [specific analysis task]
-MODE: analysis
-CONTEXT: [file references and memory context]
-EXPECTED: [expected deliverables]
-RULES: [template reference and constraints]
-"
+### Qwen
+- **Command**: `~/.claude/scripts/qwen-wrapper`
+- **Strengths**: Large context window, pattern recognition (same as Gemini)
+- **Best For**: Analysis, documentation generation, code exploration (fallback option when Gemini unavailable)
+- **Permissions**: Default read-only analysis, MODE=write requires explicit specification (auto-enables --approval-mode yolo)
+- **Default MODE**: `analysis` (read-only)
+- **⚠️ Write Trigger**: Only when user explicitly requests "generate documentation", "modify code", or specifies MODE=write
+- **Priority**: Secondary to Gemini - use as fallback for same tasks
 
-# Codex Development
-codex -C [directory] --full-auto exec "
-PURPOSE: [clear development goal]
-TASK: [specific development task]
-MODE: [auto|write]
-CONTEXT: [file references and memory context]
-EXPECTED: [expected deliverables]
-RULES: [template reference and constraints]
-" --skip-git-repo-check -s danger-full-access
-```
+#### MODE Options
+- `analysis` (default) - Read-only analysis and documentation generation (same as Gemini)
+- `write` - ⚠️ Create/modify codebase files (requires explicit specification, auto-enables --approval-mode yolo)
 
-### Template Structure
+### Codex
+- **Command**: `codex --full-auto exec`
+- **Strengths**: Autonomous development, mathematical reasoning
+- **Best For**: Implementation, testing, automation
+- **Permissions**: Requires explicit MODE=auto or MODE=write specification
+- **Default MODE**: No default, must be explicitly specified
+- **⚠️ Write Trigger**: Only when user explicitly requests "implement", "modify", "generate code" AND specifies MODE
+
+#### MODE Options
+- `auto` - ⚠️ Autonomous development with full file operations (requires explicit specification, enables -s danger-full-access)
+- `write` - ⚠️ Test generation and file modification (requires explicit specification)
+- **Default**: No default mode, MODE must be explicitly specified
+
+#### Session Management
+- `codex resume` - Resume previous interactive session (picker by default)
+- `codex exec "task" resume --last` - Continue most recent session with new task (maintains context)
+- `codex -i <image_file>` - Attach image(s) to initial prompt (useful for UI/design references)
+- **Multi-task Pattern**: First task uses `exec`, subsequent tasks use `exec "..." resume --last` for context continuity
+  - **Parameter Position**: `resume --last` must be placed AFTER the prompt string at command END
+  - **Example**:
+    ```bash
+    # First task - establish session
+    codex -C project --full-auto exec "Implement auth module" --skip-git-repo-check -s danger-full-access
+
+    # Subsequent tasks - continue same session
+    codex --full-auto exec "Add JWT validation" resume --last --skip-git-repo-check -s danger-full-access
+    codex --full-auto exec "Write auth tests" resume --last --skip-git-repo-check -s danger-full-access
+    ```
+
+#### Auto-Resume Decision Rules
+**When to use `resume --last`**:
+- Current task is related to/extends previous Codex task in conversation memory
+- Current task requires context from previous implementation
+- Current task is part of multi-step workflow (e.g., implement → enhance → test)
+- Session memory indicates recent Codex execution on same module/feature
+
+**When NOT to use `resume --last`**:
+- First Codex task in conversation
+- New independent task unrelated to previous work
+- Switching to different module/feature area
+- No recent Codex task in conversation memory
+
+---
+
+## 🎯 Command Templates
+
+### Universal Template Structure
+Every command MUST follow this structure:
 - [ ] **PURPOSE** - Clear goal and intent
 - [ ] **TASK** - Specific execution task
 - [ ] **MODE** - Execution mode and permission level
@@ -80,22 +122,82 @@ RULES: [template reference and constraints]
 - [ ] **EXPECTED** - Clear expected results
 - [ ] **RULES** - Template reference and constraints
 
-### MODE Field Definition
+### Standard Command Formats
 
-The MODE field controls execution behavior and file permissions:
+#### Gemini Commands
+```bash
+# Gemini Analysis (read-only, default)
+cd [directory] && ~/.claude/scripts/gemini-wrapper -p "
+PURPOSE: [clear analysis goal]
+TASK: [specific analysis task]
+MODE: analysis
+CONTEXT: [file references and memory context]
+EXPECTED: [expected output]
+RULES: [template reference and constraints]
+"
 
-**For Gemini** (全权限，可读写):
-- `analysis` (default) - 分析 + 可生成文档
-- `write` - 创建/修改文件（自动启用 --approval-mode yolo）
+# Gemini Write Mode (requires explicit MODE=write)
+# NOTE: --approval-mode yolo must be placed AFTER wrapper command, BEFORE -p
+cd [directory] && ~/.claude/scripts/gemini-wrapper --approval-mode yolo -p "
+PURPOSE: [clear goal]
+TASK: [specific task]
+MODE: write
+CONTEXT: [file references and memory context]
+EXPECTED: [expected output]
+RULES: [template reference and constraints]
+"
+```
 
-**For Qwen** (仅分析):
-- `analysis` (default) - 仅架构分析，不生成代码
+#### Qwen Commands
+```bash
+# Qwen Analysis (read-only, default) - Same as Gemini, use as fallback
+cd [directory] && ~/.claude/scripts/qwen-wrapper -p "
+PURPOSE: [clear analysis goal]
+TASK: [specific analysis task]
+MODE: analysis
+CONTEXT: [file references and memory context]
+EXPECTED: [expected output]
+RULES: [template reference and constraints]
+"
 
-**For Codex**:
-- `auto` (default) - 自主开发，全文件操作
-- `write` - 测试生成和文件修改
+# Qwen Write Mode (requires explicit MODE=write)
+# NOTE: --approval-mode yolo must be placed AFTER wrapper command, BEFORE -p
+cd [directory] && ~/.claude/scripts/qwen-wrapper --approval-mode yolo -p "
+PURPOSE: [clear goal]
+TASK: [specific task]
+MODE: write
+CONTEXT: [file references and memory context]
+EXPECTED: [expected output]
+RULES: [template reference and constraints]
+"
+```
 
-### Directory Context
+#### Codex Commands
+```bash
+# Codex Development (requires explicit MODE=auto)
+# NOTE: --skip-git-repo-check and -s danger-full-access must be placed at command END
+codex -C [directory] --full-auto exec "
+PURPOSE: [clear development goal]
+TASK: [specific development task]
+MODE: auto
+CONTEXT: [file references and memory context]
+EXPECTED: [expected deliverables]
+RULES: [template reference and constraints]
+" --skip-git-repo-check -s danger-full-access
+
+# Codex Test/Write Mode (requires explicit MODE=write)
+# NOTE: --skip-git-repo-check and -s danger-full-access must be placed at command END
+codex -C [directory] --full-auto exec "
+PURPOSE: [clear goal]
+TASK: [specific task]
+MODE: write
+CONTEXT: [file references and memory context]
+EXPECTED: [expected deliverables]
+RULES: [template reference and constraints]
+" --skip-git-repo-check -s danger-full-access
+```
+
+### Directory Context Configuration
 Tools execute in current working directory:
 - **Gemini**: `cd path/to/project && ~/.claude/scripts/gemini-wrapper -p "prompt"`
 - **Qwen**: `cd path/to/project && ~/.claude/scripts/qwen-wrapper -p "prompt"`
@@ -103,7 +205,7 @@ Tools execute in current working directory:
 - **Path types**: Supports both relative (`../project`) and absolute (`/full/path`) paths
 - **Token analysis**: For gemini-wrapper and qwen-wrapper, token counting happens in current directory
 
-### Rules Field Format
+### RULES Field Format
 ```bash
 RULES: $(cat "~/.claude/workflows/cli-templates/prompts/[category]/[template].txt") | [constraints]
 ```
@@ -114,24 +216,60 @@ RULES: $(cat "~/.claude/workflows/cli-templates/prompts/[category]/[template].tx
 - No template: `Focus on security patterns, include dependency analysis`
 - File patterns: `@{src/**/*.ts,CLAUDE.md} - Stay within scope`
 
-## 📊 Tool Selection Matrix
+### File Pattern Reference
+- All files: `@{**/*}`
+- Source files: `@{src/**/*}`
+- TypeScript: `@{*.ts,*.tsx}`
+- With docs: `@{CLAUDE.md,**/*CLAUDE.md}`
+- Tests: `@{src/**/*.test.*}`
+
+**Complex Pattern Discovery**:
+For complex file pattern requirements, use semantic discovery tools BEFORE CLI execution:
+- **rg (ripgrep)**: Content-based file discovery with regex patterns
+- **Code Index MCP**: Semantic file search based on task requirements
+- **Workflow**: Discover → Extract precise paths → Build CONTEXT field
+
+**Example**:
+```bash
+# Step 1: Discover files semantically
+rg "export.*Component" --files-with-matches --type ts  # Find component files
+mcp__code-index__search_code_advanced(pattern="interface.*Props", file_pattern="*.tsx")  # Find interface files
+
+# Step 2: Build precise CONTEXT from discovery results
+CONTEXT: @{src/components/Auth.tsx,src/types/auth.d.ts,src/hooks/useAuth.ts}
+
+# Step 3: Execute CLI with precise file references
+cd src && ~/.claude/scripts/gemini-wrapper -p "
+PURPOSE: Analyze authentication components
+TASK: Review auth component patterns and props interfaces
+MODE: analysis
+CONTEXT: @{components/Auth.tsx,types/auth.d.ts,hooks/useAuth.ts}
+EXPECTED: Pattern analysis and improvement suggestions
+RULES: Focus on type safety and component composition
+"
+```
+
+---
+
+## 📊 Tool Selection Guide
+
+### Selection Matrix
 
 | Task Type | Tool | Use Case | Template |
 |-----------|------|----------|-----------|
-| **Analysis** | Gemini | Code exploration, architecture review, patterns | `analysis/pattern.txt` |
-| **Architecture** | Qwen | System design, code generation, architectural analysis | `analysis/architecture.txt` |
-| **Code Generation** | Qwen | Implementation patterns, code scaffolding, component creation | `development/feature.txt` |
+| **Analysis** | Gemini (Qwen fallback) | Code exploration, architecture review, patterns | `analysis/pattern.txt` |
+| **Architecture** | Gemini (Qwen fallback) | System design, architectural analysis | `analysis/architecture.txt` |
+| **Documentation** | Gemini (Qwen fallback) | Code docs, API specs, guides | `analysis/quality.txt` |
 | **Development** | Codex | Feature implementation, bug fixes, testing | `development/feature.txt` |
-| **Planning** | Multiple | Task breakdown, migration planning | `planning/task-breakdown.txt` |
-| **Documentation** | Multiple | Code docs, API specs, guides | `analysis/quality.txt` |
+| **Planning** | Gemini/Qwen | Task breakdown, migration planning | `planning/task-breakdown.txt` |
 | **Security** | Codex | Vulnerability assessment, fixes | `analysis/security.txt` |
-| **Refactoring** | Multiple | Gemini for analysis, Qwen/Codex for execution | `development/refactor.txt` |
+| **Refactoring** | Multiple | Gemini/Qwen for analysis, Codex for execution | `development/refactor.txt` |
 
-## 📁 Template System
+### Template System
 
 **Base Structure**: `~/.claude/workflows/cli-templates/`
 
-### Available Templates
+#### Available Templates
 ```
 prompts/
 ├── analysis/
@@ -157,19 +295,22 @@ tech-stacks/
 └── react-dev.md         - React architecture
 ```
 
+---
+
 ## 🚀 Usage Patterns
 
 ### Workflow Integration (REQUIRED)
 When planning any coding task, **ALWAYS** integrate CLI tools:
 
-1. **Understanding Phase**: Use Gemini for analysis
-2. **Architecture Phase**: Use Qwen for design and code generation
-3. **Implementation Phase**: Use Qwen/Codex for development
+1. **Understanding Phase**: Use Gemini for analysis (Qwen as fallback)
+2. **Architecture Phase**: Use Gemini for design and analysis (Qwen as fallback)
+3. **Implementation Phase**: Use Codex for development
 4. **Quality Phase**: Use Codex for testing and validation
 
 ### Common Scenarios
+
+#### Code Analysis
 ```bash
-# Gemini - Code Analysis
 ~/.claude/scripts/gemini-wrapper -p "
 PURPOSE: Understand codebase architecture
 TASK: Analyze project structure and identify patterns
@@ -178,8 +319,10 @@ CONTEXT: @{src/**/*.ts,CLAUDE.md} Previous analysis of auth system
 EXPECTED: Architecture overview and integration points
 RULES: $(cat '~/.claude/workflows/cli-templates/prompts/analysis/architecture.txt') | Focus on integration points
 "
+```
 
-# Gemini - Generate Documentation
+#### Documentation Generation
+```bash
 ~/.claude/scripts/gemini-wrapper -p "
 PURPOSE: Generate API documentation
 TASK: Create comprehensive API reference from code
@@ -188,9 +331,12 @@ CONTEXT: @{src/api/**/*}
 EXPECTED: API.md with all endpoints documented
 RULES: Follow project documentation standards
 "
+```
 
-# Qwen - Architecture Analysis
-cd src/auth && ~/.claude/scripts/qwen-wrapper -p "
+#### Architecture Analysis (Qwen as Gemini fallback)
+```bash
+# Prefer Gemini for architecture analysis
+cd src/auth && ~/.claude/scripts/gemini-wrapper -p "
 PURPOSE: Analyze authentication system architecture
 TASK: Review JWT-based auth system design
 MODE: analysis
@@ -199,7 +345,20 @@ EXPECTED: Architecture analysis report with recommendations
 RULES: $(cat '~/.claude/workflows/cli-templates/prompts/analysis/architecture.txt') | Focus on security
 "
 
-# Codex - Feature Development
+# Use Qwen only if Gemini unavailable
+cd src/auth && ~/.claude/scripts/qwen-wrapper -p "
+PURPOSE: Analyze authentication system architecture
+TASK: Review JWT-based auth system design
+MODE: analysis
+CONTEXT: @{src/auth/**/*} Existing patterns and requirements
+EXPECTED: Architecture analysis report with recommendations
+RULES: $(cat '~/.claude/workflows/cli-templates/prompts/analysis/architecture.txt') | Focus on security
+"
+```
+
+#### Feature Development (Multi-task with Resume)
+```bash
+# First task - establish session
 codex -C path/to/project --full-auto exec "
 PURPOSE: Implement user authentication
 TASK: Create JWT-based authentication system
@@ -209,66 +368,46 @@ EXPECTED: Complete auth module with tests
 RULES: $(cat '~/.claude/workflows/cli-templates/prompts/development/feature.txt') | Follow security best practices
 " --skip-git-repo-check -s danger-full-access
 
-# Codex - Test Generation
-codex -C src/auth --full-auto exec "
+# Continue in same session - Add JWT validation
+codex --full-auto exec "
+PURPOSE: Enhance authentication security
+TASK: Add JWT token validation and refresh logic
+MODE: auto
+CONTEXT: Previous auth implementation from current session
+EXPECTED: JWT validation middleware and token refresh endpoints
+RULES: Follow JWT best practices, maintain session context
+" resume --last --skip-git-repo-check -s danger-full-access
+
+# Continue in same session - Add tests
+codex --full-auto exec "
 PURPOSE: Increase test coverage
 TASK: Generate comprehensive tests for auth module
 MODE: write
-CONTEXT: @{**/*.ts} Exclude existing tests
+CONTEXT: Auth implementation from current session
 EXPECTED: Complete test suite with 80%+ coverage
 RULES: Use Jest, follow existing patterns
-" --skip-git-repo-check -s danger-full-access
+" resume --last --skip-git-repo-check -s danger-full-access
 ```
 
-## 📋 Planning Checklist
+#### Interactive Session Resume
+```bash
+# Resume previous session with picker
+codex resume
 
-For every development task:
-- [ ] **Purpose defined** - Clear goal and intent
-- [ ] **Mode selected** - Execution mode and permission level determined
-- [ ] **Context gathered** - File references and session memory documented
-- [ ] **Gemini analysis** completed for understanding
-- [ ] **Template selected** - Appropriate template chosen
-- [ ] **Constraints specified** - File patterns, scope, requirements
-- [ ] **Implementation approach** - Tool selection and workflow
-- [ ] **Quality measures** - Testing and validation plan
-- [ ] **Tool configuration** - Review `.gemini/CLAUDE.md` or `.codex/Agent.md` if needed
+# Or resume most recent session directly
+codex resume --last
+```
 
-## 🎯 Key Features
-
-### Gemini (全权限)
-- **Command**: `~/.claude/scripts/gemini-wrapper`
-- **Strengths**: Large context window, pattern recognition
-- **Best For**: Analysis, documentation generation, code exploration
-- **Permissions**: 可读写，MODE=write 时自动启用 --approval-mode yolo
-- **Default MODE**: `analysis`
-
-### Qwen (仅分析)
-- **Command**: `~/.claude/scripts/qwen-wrapper`
-- **Strengths**: Architecture analysis, pattern recognition
-- **Best For**: System design analysis, architectural review
-- **Permissions**: 仅分析，不生成代码
-- **Default MODE**: `analysis`
-
-### Codex
-- **Command**: `codex --full-auto exec`
-- **Strengths**: Autonomous development, mathematical reasoning
-- **Best For**: Implementation, testing, automation
-- **Required**: `-s danger-full-access` and `--skip-git-repo-check` for development
-- **Default MODE**: `auto`
-
-### File Patterns
-- All files: `@{**/*}`
-- Source files: `@{src/**/*}`
-- TypeScript: `@{*.ts,*.tsx}`
-- With docs: `@{CLAUDE.md,**/*CLAUDE.md}`
-- Tests: `@{src/**/*.test.*}`
+---
 
 ## 🔧 Best Practices
 
+### General Guidelines
 - **Start with templates** - Use predefined templates for consistency
 - **Be specific** - Clear PURPOSE, TASK, and EXPECTED fields
 - **Include constraints** - File patterns, scope, requirements in RULES
-- **Test patterns first** - Validate file patterns with `ls`
+- **Discover patterns first** - Use rg/MCP for complex file discovery before CLI execution
+- **Build precise CONTEXT** - Convert discovery results to explicit file references
 - **Document context** - Always reference CLAUDE.md for context
 
 ### Context Optimization Strategy
@@ -291,7 +430,7 @@ EXPECTED: Pattern documentation
 RULES: Focus on security best practices
 "
 
-# Qwen - Architecture analysis
+# Qwen - Analysis (fallback option, same as Gemini)
 cd src/auth && ~/.claude/scripts/qwen-wrapper -p "
 PURPOSE: Analyze auth architecture
 TASK: Review auth system design and patterns
@@ -310,4 +449,42 @@ CONTEXT: @{**/*.ts}
 EXPECTED: Code improvements and fixes
 RULES: Maintain backward compatibility
 " --skip-git-repo-check -s danger-full-access
-```
+```
+
+### Planning Checklist
+
+For every development task:
+- [ ] **Purpose defined** - Clear goal and intent
+- [ ] **Mode selected** - Execution mode and permission level determined
+- [ ] **Context gathered** - File references and session memory documented
+- [ ] **Gemini analysis** completed for understanding
+- [ ] **Template selected** - Appropriate template chosen
+- [ ] **Constraints specified** - File patterns, scope, requirements
+- [ ] **Implementation approach** - Tool selection and workflow
+- [ ] **Quality measures** - Testing and validation plan
+- [ ] **Tool configuration** - Review `.gemini/CLAUDE.md` or `.codex/Agent.md` if needed
+
+---
+
+## ⚙️ Execution Configuration
+
+### Core Execution Rules
+- **Dynamic Timeout (20-120min)**: Allocate execution time based on task complexity
+  - Simple tasks (analysis, search): 20-40min (1200000-2400000ms)
+  - Medium tasks (refactoring, documentation): 40-60min (2400000-3600000ms)
+  - Complex tasks (implementation, migration): 60-120min (3600000-7200000ms)
+- **Codex Multiplier**: Codex commands use 1.5x of allocated time
+- **Apply to All Tools**: All bash() wrapped commands including Gemini, Qwen wrapper and Codex executions
+- **Command Examples**: `bash(~/.claude/scripts/gemini-wrapper -p "prompt")`, `bash(codex -C directory --full-auto exec "task")`
+- **Auto-detect**: Analyze PURPOSE and TASK fields to determine appropriate timeout
+
+### Permission Framework
+- **⚠️ WRITE PROTECTION**: Local codebase write/modify requires EXPLICIT user confirmation
+  - **Analysis Mode (default)**: Read-only, safe for auto-execution
+  - **Write Mode**: Requires user explicitly states MODE=write or MODE=auto in prompt
+  - **Exception**: User provides clear instructions like "modify", "create", "implement"
+- **Gemini/Qwen Write Access**: Use `--approval-mode yolo` ONLY when MODE=write explicitly specified
+  - **Parameter Position**: Place AFTER the wrapper command: `gemini-wrapper --approval-mode yolo -p "..."`
+- **Codex Write Access**: Use `-s danger-full-access` and `--skip-git-repo-check` ONLY when MODE=auto explicitly specified
+  - **Parameter Position**: Place AFTER the prompt string at command END: `codex ... exec "..." --skip-git-repo-check -s danger-full-access`
+- **Default Behavior**: All tools default to analysis/read-only mode without explicit write permission

.claude/workflows/task-core.md

@@ -42,11 +42,17 @@ All task files use this simplified 5-field schema (aligned with workflow-archite
         "on_error": "skip_optional"
       }
     ],
-    "implementation_approach": {
-      "task_description": "Implement comprehensive JWT authentication system...",
-      "modification_points": ["Add JWT token generation...", "..."],
-      "logic_flow": ["User login request → validate credentials...", "..."]
-    },
+    "implementation_approach": [
+      {
+        "step": 1,
+        "title": "Implement JWT authentication system",
+        "description": "Implement comprehensive JWT authentication system with token generation, validation, and refresh logic",
+        "modification_points": ["Add JWT token generation", "Implement token validation middleware", "Create refresh token logic"],
+        "logic_flow": ["User login request → validate credentials", "Generate JWT access and refresh tokens", "Store refresh token securely", "Return tokens to client"],
+        "depends_on": [],
+        "output": "jwt_implementation"
+      }
+    ],
     "target_files": [
       "src/auth/login.ts:handleLogin:75-120",
       "src/middleware/auth.ts:validateToken",

.claude/workflows/tool-control.yaml

@@ -0,0 +1,10 @@
+# Tool Control Configuration
+# Controls whether CLI tools (Gemini, Qwen, Codex) are enabled in the workspace
+
+tools:
+  gemini:
+    enabled: true
+  qwen:
+    enabled: true
+  codex:
+    enabled: true