feat: Redesign test-gen workflow with independent session and cross-session context

Major redesign of test-gen workflow based on simplified architecture:

Core Changes:
- Creates independent test session (WFS-test-[source]) instead of modifying existing session
- Implements 4-phase execution with concept-enhanced analysis integration
- Reuses IMPL-*.json format with meta.type="test-fix" (no new task type)
- Auto-detects cross-session context via workflow-session.json metadata

4-Phase Workflow:
1. Phase 1: Create test session with workflow_type and source_session_id metadata
2. Phase 2: Auto-detect and gather cross-session context (summaries, git changes, tests)
3. Phase 3: Analyze implementation with concept-enhanced (parallel Gemini + Codex)
4. Phase 4: Generate IMPL-001.json task with test strategy from ANALYSIS_RESULTS.md

Key Features:
- Session isolation: Test session separate from implementation session
- Parameter simplification: context-gather auto-detects via metadata (no --source-session param)
- Format reuse: IMPL-*.json with meta.type field (zero changes to execute/status tools)
- Analysis integration: concept-enhanced provides comprehensive test strategy and code targets
- Automatic cross-session: Collects source session artifacts automatically

Tool Modifications Required:
- session-start: Support test session metadata (workflow_type, source_session_id)
- context-gather: Auto-detect test session and gather from source session
- task-generate: Extract test strategy from ANALYSIS_RESULTS.md
- concept-enhanced: No changes (already supports analysis)
- execute: No changes (already dispatches by meta.agent)

Data Flow:
User → session-start (creates test session) → context-gather (auto cross-session)
→ concept-enhanced (analyzes + generates strategy) → task-generate (creates task)
→ Returns summary → User triggers /workflow:execute separately

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

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

@@ -228,7 +228,7 @@ Generate individual `.task/IMPL-*.json` files with:
       "modification_points": ["Apply requirements"],
       "logic_flow": ["Load spec", "Analyze", "Implement", "Validate"]
     },
-    "target_files": ["file:function:lines"]
+    "target_files": ["file:function:lines", "path/to/NewFile.ts"]
   }
 }
 ```

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

@@ -91,10 +91,11 @@ allowed-tools: TodoWrite(*), Read(*), Write(*), Bash(*), Glob(*)
 **Document Structure**:
 ```
 .workflow/WFS-[topic]/.brainstorming/
-├── topic-framework.md          # ★ STRUCTURED FRAMEWORK DOCUMENT
-└── workflow-session.json               # Framework metadata and role assignments
+└── topic-framework.md          # ★ STRUCTURED FRAMEWORK DOCUMENT
 ```
 
+**Note**: `workflow-session.json` is located at `.workflow/WFS-[topic]/workflow-session.json` (session root), not inside `.brainstorming/`.
+
 ## Framework Template Structures
 
 ### Dynamic Role-Based Framework

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

@@ -149,7 +149,7 @@ Task(subagent_type="conceptual-planning-agent",
 
      3. **load_session_metadata**
         - Action: Load session metadata and topic description
-        - Command: bash(cat .workflow/WFS-{topic}/.brainstorming/workflow-session.json 2>/dev/null || echo '{}')
+        - Command: bash(cat .workflow/WFS-{topic}/workflow-session.json 2>/dev/null || echo '{}')
         - Output: session_metadata
 
      ### Implementation Context
@@ -162,7 +162,7 @@ Task(subagent_type="conceptual-planning-agent",
      ### Session Context
      **Workflow Directory**: .workflow/WFS-{topic}/.brainstorming/
      **Output Directory**: .workflow/WFS-{topic}/.brainstorming/{role}/
-     **Session JSON**: .workflow/WFS-{topic}/.brainstorming/workflow-session.json
+     **Session JSON**: .workflow/WFS-{topic}/workflow-session.json
 
      ### Dependencies & Context
      **Topic**: {user-provided-topic}

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

@@ -88,7 +88,7 @@ ANALYSIS_MODE: {framework_mode ? "framework_based" : "standalone"}
 
 3. **load_session_metadata**
    - Action: Load session metadata and existing context
-   - Command: Read(.workflow/WFS-{session}/.brainstorming/session.json)
+   - Command: Read(.workflow/WFS-{session}/workflow-session.json)
    - Output: session_context
 
 ## Analysis Requirements
@@ -136,7 +136,7 @@ TodoWrite({
       activeForm: "Generating structured data-architect analysis"
     },
     {
-      content: "Update session.json with data-architect completion status",
+      content: "Update workflow-session.json with data-architect completion status",
       status: "pending",
       activeForm: "Updating session metadata"
     }

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

@@ -88,7 +88,7 @@ ANALYSIS_MODE: {framework_mode ? "framework_based" : "standalone"}
 
 3. **load_session_metadata**
    - Action: Load session metadata and existing context
-   - Command: Read(.workflow/WFS-{session}/.brainstorming/session.json)
+   - Command: Read(.workflow/WFS-{session}/workflow-session.json)
    - Output: session_context
 
 ## Analysis Requirements
@@ -136,7 +136,7 @@ TodoWrite({
       activeForm: "Generating structured product-manager analysis"
     },
     {
-      content: "Update session.json with product-manager completion status",
+      content: "Update workflow-session.json with product-manager completion status",
       status: "pending",
       activeForm: "Updating session metadata"
     }

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

@@ -88,7 +88,7 @@ ANALYSIS_MODE: {framework_mode ? "framework_based" : "standalone"}
 
 3. **load_session_metadata**
    - Action: Load session metadata and existing context
-   - Command: Read(.workflow/WFS-{session}/.brainstorming/session.json)
+   - Command: Read(.workflow/WFS-{session}/workflow-session.json)
    - Output: session_context
 
 ## Analysis Requirements
@@ -136,7 +136,7 @@ TodoWrite({
       activeForm: "Generating structured product-owner analysis"
     },
     {
-      content: "Update session.json with product-owner completion status",
+      content: "Update workflow-session.json with product-owner completion status",
       status: "pending",
       activeForm: "Updating session metadata"
     }

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

@@ -88,7 +88,7 @@ ANALYSIS_MODE: {framework_mode ? "framework_based" : "standalone"}
 
 3. **load_session_metadata**
    - Action: Load session metadata and existing context
-   - Command: Read(.workflow/WFS-{session}/.brainstorming/session.json)
+   - Command: Read(.workflow/WFS-{session}/workflow-session.json)
    - Output: session_context
 
 ## Analysis Requirements
@@ -136,7 +136,7 @@ TodoWrite({
       activeForm: "Generating structured scrum-master analysis"
     },
     {
-      content: "Update session.json with scrum-master completion status",
+      content: "Update workflow-session.json with scrum-master completion status",
       status: "pending",
       activeForm: "Updating session metadata"
     }

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

@@ -88,7 +88,7 @@ ANALYSIS_MODE: {framework_mode ? "framework_based" : "standalone"}
 
 3. **load_session_metadata**
    - Action: Load session metadata and existing context
-   - Command: Read(.workflow/WFS-{session}/.brainstorming/session.json)
+   - Command: Read(.workflow/WFS-{session}/workflow-session.json)
    - Output: session_context
 
 ## Analysis Requirements
@@ -136,7 +136,7 @@ TodoWrite({
       activeForm: "Generating structured subject-matter-expert analysis"
     },
     {
-      content: "Update session.json with subject-matter-expert completion status",
+      content: "Update workflow-session.json with subject-matter-expert completion status",
       status: "pending",
       activeForm: "Updating session metadata"
     }

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

@@ -88,7 +88,7 @@ ANALYSIS_MODE: {framework_mode ? "framework_based" : "standalone"}
 
 3. **load_session_metadata**
    - Action: Load session metadata and existing context
-   - Command: Read(.workflow/WFS-{session}/.brainstorming/session.json)
+   - Command: Read(.workflow/WFS-{session}/workflow-session.json)
    - Output: session_context
 
 ## Analysis Requirements
@@ -136,7 +136,7 @@ TodoWrite({
       activeForm: "Generating structured ui-designer analysis"
     },
     {
-      content: "Update session.json with ui-designer completion status",
+      content: "Update workflow-session.json with ui-designer completion status",
       status: "pending",
       activeForm: "Updating session metadata"
     }

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

@@ -88,7 +88,7 @@ ANALYSIS_MODE: {framework_mode ? "framework_based" : "standalone"}
 
 3. **load_session_metadata**
    - Action: Load session metadata and existing context
-   - Command: Read(.workflow/WFS-{session}/.brainstorming/session.json)
+   - Command: Read(.workflow/WFS-{session}/workflow-session.json)
    - Output: session_context
 
 ## Analysis Requirements
@@ -136,7 +136,7 @@ TodoWrite({
       activeForm: "Generating structured ux-expert analysis"
     },
     {
-      content: "Update session.json with ux-expert completion status",
+      content: "Update workflow-session.json with ux-expert completion status",
       status: "pending",
       activeForm: "Updating session metadata"
     }

.claude/commands/workflow/execute.md

@@ -356,8 +356,8 @@ Task(subagent_type="{meta.agent}",
 
      **WORKFLOW COMPLETION CHECK**:
      After updating task status, check if workflow is complete:
-     total_tasks=\$(ls .workflow/*/\.task/*.json | wc -l)
-     completed_tasks=\$(ls .workflow/*/\.summaries/*.md 2>/dev/null | wc -l)
+     total_tasks=\$(find .workflow/*/\.task/ -name "*.json" -type f 2>/dev/null | wc -l)
+     completed_tasks=\$(find .workflow/*/\.summaries/ -name "*.md" -type f 2>/dev/null | wc -l)
      if [ \$total_tasks -eq \$completed_tasks ]; then
        SlashCommand(command=\"/workflow:session:complete\")
      fi"),
@@ -433,7 +433,7 @@ Task(subagent_type="{meta.agent}",
       "task_description": "Implement following consolidated synthesis specification...",
       "modification_points": ["Apply synthesis specification requirements..."]
     },
-    "target_files": ["file:function:lines"]
+    "target_files": ["file:function:lines", "path/to/NewFile.ts"]
   }
 }
 ```

.claude/commands/workflow/review.md

@@ -55,7 +55,7 @@ if [ ! -d ".workflow/${sessionId}" ]; then
 fi
 
 # Check for completed tasks
-if [ ! -d ".workflow/${sessionId}/.summaries" ] || [ -z "$(ls .workflow/${sessionId}/.summaries/IMPL-*.md 2>/dev/null)" ]; then
+if [ ! -d ".workflow/${sessionId}/.summaries" ] || [ -z "$(find .workflow/${sessionId}/.summaries/ -name "IMPL-*.md" -type f 2>/dev/null)" ]; then
     echo "❌ No completed implementation found. Complete implementation first"
     exit 1
 fi

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

@@ -44,8 +44,8 @@ mv temp.json .workflow/WFS-session/workflow-session.json
 
 ### Step 5: Count Final Statistics
 ```bash
-ls .workflow/WFS-session/.task/*.json 2>/dev/null | wc -l
-ls .workflow/WFS-session/.summaries/*.md 2>/dev/null | wc -l
+find .workflow/WFS-session/.task/ -name "*.json" -type f 2>/dev/null | wc -l
+find .workflow/WFS-session/.summaries/ -name "*.md" -type f 2>/dev/null | wc -l
 ```
 
 ### Step 6: Remove Active Marker
@@ -56,12 +56,12 @@ rm .workflow/.active-WFS-session-name
 ## Simple Bash Commands
 
 ### Basic Operations
-- **Find active session**: `ls .workflow/.active-*`
+- **Find active session**: `find .workflow/ -name ".active-*" -type f`
 - **Get session name**: `basename marker | sed 's/^\.active-//'`
 - **Update status**: `jq '.status = "completed"' session.json > temp.json`
 - **Add timestamp**: `jq '.completed_at = "'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"'`
-- **Count tasks**: `ls .task/*.json | wc -l`
-- **Count completed**: `ls .summaries/*.md | wc -l`
+- **Count tasks**: `find .task/ -name "*.json" -type f | wc -l`
+- **Count completed**: `find .summaries/ -name "*.md" -type f 2>/dev/null | wc -l`
 - **Remove marker**: `rm .workflow/.active-session`
 
 ### Completion Result
@@ -92,11 +92,11 @@ Session Completion Summary:
 ### Error Handling
 ```bash
 # No active session
-ls .workflow/.active-* 2>/dev/null || echo "No active session found"
+find .workflow/ -name ".active-*" -type f 2>/dev/null || echo "No active session found"
 
 # Incomplete tasks
-task_count=$(ls .task/*.json | wc -l)
-summary_count=$(ls .summaries/*.md 2>/dev/null | wc -l)
+task_count=$(find .task/ -name "*.json" -type f | wc -l)
+summary_count=$(find .summaries/ -name "*.md" -type f 2>/dev/null | wc -l)
 test $task_count -eq $summary_count || echo "Warning: Not all tasks completed"
 ```
 

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

@@ -35,8 +35,8 @@ jq -r '.session_id, .status, .project' .workflow/WFS-session/workflow-session.js
 
 ### Step 4: Count Task Progress
 ```bash
-ls .workflow/WFS-session/.task/*.json 2>/dev/null | wc -l
-ls .workflow/WFS-session/.summaries/*.md 2>/dev/null | wc -l
+find .workflow/WFS-session/.task/ -name "*.json" -type f 2>/dev/null | wc -l
+find .workflow/WFS-session/.summaries/ -name "*.md" -type f 2>/dev/null | wc -l
 ```
 
 ### Step 5: Get Creation Time
@@ -47,11 +47,11 @@ jq -r '.created_at // "unknown"' .workflow/WFS-session/workflow-session.json
 ## Simple Bash Commands
 
 ### Basic Operations
-- **List sessions**: `ls .workflow/WFS-*`
-- **Find active**: `ls .workflow/.active-*`
+- **List sessions**: `find .workflow/ -maxdepth 1 -type d -name "WFS-*"`
+- **Find active**: `find .workflow/ -name ".active-*" -type f`
 - **Read session data**: `jq -r '.session_id, .status' session.json`
-- **Count tasks**: `ls .task/*.json | wc -l`
-- **Count completed**: `ls .summaries/*.md | wc -l`
+- **Count tasks**: `find .task/ -name "*.json" -type f | wc -l`
+- **Count completed**: `find .summaries/ -name "*.md" -type f 2>/dev/null | wc -l`
 - **Get timestamp**: `jq -r '.created_at' session.json`
 
 ## Simple Output Format

.claude/commands/workflow/status.md

@@ -25,7 +25,7 @@ Generates on-demand views from JSON task data. No synchronization needed - all v
 
 ### Step 1: Find Active Session
 ```bash
-ls .workflow/.active-* 2>/dev/null | head -1
+find .workflow/ -name ".active-*" -type f 2>/dev/null | head -1
 ```
 
 ### Step 2: Load Session Data
@@ -35,7 +35,7 @@ cat .workflow/WFS-session/workflow-session.json
 
 ### Step 3: Scan Task Files
 ```bash
-ls .workflow/WFS-session/.task/*.json 2>/dev/null
+find .workflow/WFS-session/.task/ -name "*.json" -type f 2>/dev/null
 ```
 
 ### Step 4: Generate Task Status
@@ -45,8 +45,8 @@ cat .workflow/WFS-session/.task/impl-1.json | jq -r '.status'
 
 ### Step 5: Count Task Progress
 ```bash
-ls .workflow/WFS-session/.task/*.json | wc -l
-ls .workflow/WFS-session/.summaries/*.md 2>/dev/null | wc -l
+find .workflow/WFS-session/.task/ -name "*.json" -type f | wc -l
+find .workflow/WFS-session/.summaries/ -name "*.md" -type f 2>/dev/null | wc -l
 ```
 
 ### Step 6: Display Overview
@@ -66,11 +66,11 @@ ls .workflow/WFS-session/.summaries/*.md 2>/dev/null | wc -l
 ## Simple Bash Commands
 
 ### Basic Operations
-- **Find active session**: `ls .workflow/.active-*`
+- **Find active session**: `find .workflow/ -name ".active-*" -type f`
 - **Read session info**: `cat .workflow/session/workflow-session.json`
-- **List tasks**: `ls .workflow/session/.task/*.json`
+- **List tasks**: `find .workflow/session/.task/ -name "*.json" -type f`
 - **Check task status**: `cat task.json | jq -r '.status'`
-- **Count completed**: `ls .summaries/*.md | wc -l`
+- **Count completed**: `find .summaries/ -name "*.md" -type f | wc -l`
 
 ### Task Status Check
 - **pending**: Not started yet
@@ -87,8 +87,8 @@ test -f .workflow/.active-* && echo "Session active"
 for f in .workflow/session/.task/*.json; do jq empty "$f" && echo "Valid: $f"; done
 
 # Check summaries match
-ls .task/*.json | wc -l
-ls .summaries/*.md | wc -l
+find .task/ -name "*.json" -type f | wc -l
+find .summaries/ -name "*.md" -type f 2>/dev/null | wc -l
 ```
 
 ## Simple Output Format

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

@@ -1,11 +1,11 @@
 ---
 name: test-gen
-description: Orchestrate test-fix workflow by analyzing implementation and generating TEST-FIX tasks
-usage: /workflow:test-gen [session-id]
-argument-hint: "[session-id]"
+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
   - /workflow:test-gen WFS-user-auth
+  - /workflow:test-gen WFS-api-refactor
 allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)
 ---
 
@@ -13,134 +13,177 @@ allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)
 
 ## Coordinator Role
 
-**This command is a pure orchestrator**: Analyze completed implementation session, generate test-fix workflow through standardized tool commands, and trigger automated test validation.
+**This command is a pure orchestrator**: Creates an independent test-fix workflow session for validating a completed implementation. It reuses the standard planning toolchain with automatic cross-session context gathering.
+
+**Core Principles**:
+- **Session Isolation**: Creates new `WFS-test-[source]` session to keep verification separate from implementation
+- **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
 
 **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
+1. Initialize TodoWrite → Create test session → Parse session ID
+2. Gather cross-session context (automatic) → Parse context path
+3. Analyze implementation with concept-enhanced → Parse ANALYSIS_RESULTS.md
+4. Generate test task from analysis → Return summary
 
 ## Core Rules
 
-1. **Start Immediately**: First action is TodoWrite initialization, second action is Phase 1 session discovery
+1. **Start Immediately**: First action is TodoWrite initialization, second action is Phase 1 test session creation
 2. **No Preliminary Analysis**: Do not read files or analyze before Phase 1
 3. **Parse Every Output**: Extract required data from each phase 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
+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. **Use Standard Tools**: Follow plan.md pattern using context-gather, concept-enhanced, task-generate
+7. **Automatic Detection**: context-gather auto-detects test session and gathers source session context
 
 ## 4-Phase Execution
 
-### Phase 1: Session Discovery & Context Gathering
-**Command**: `SlashCommand(command="/workflow:tools:context-gather --session [sessionId] \"TEST-FIX: Validate implementation for [sessionId]\"")`
+### Phase 1: Create Test Session
+**Command**: `SlashCommand(command="/workflow:session:start --new \"Test validation for [sourceSessionId]\"")`
 
-**Session ID Resolution**:
-- If argument provided → Use directly as `sessionId`
-- If no argument → Auto-detect from `.workflow/.active-*` marker
-- Format: `WFS-[session-name]`
+**Input**: `sourceSessionId` from user argument (e.g., `WFS-user-auth`)
 
-**Task Description Structure**:
-```
-GOAL: Execute and validate all tests for completed implementation
-SCOPE: Test execution, failure diagnosis, code fixing
-CONTEXT: Implementation session [sessionId] with completed IMPL tasks
-```
+**Expected Behavior**:
+- Creates new session with pattern `WFS-test-[source-slug]` (e.g., `WFS-test-user-auth`)
+- Writes metadata to `workflow-session.json`:
+  - `workflow_type: "test_session"`
+  - `source_session_id: "[sourceSessionId]"`
+- Returns new session ID for subsequent phases
 
 **Parse Output**:
-- Extract: context package path (store as `contextPath`)
-- Typical pattern: `.workflow/[sessionId]/.process/context-package-test.json`
+- Extract: new test session ID (store as `testSessionId`)
+- Pattern: `WFS-test-[slug]`
 
 **Validation**:
-- Session directory `.workflow/[sessionId]/` exists
-- Session has completed IMPL tasks (check .summaries/IMPL-*-summary.md)
-- Context package created successfully
+- Source session `.workflow/[sourceSessionId]/` exists
+- Source session has completed IMPL tasks (`.summaries/IMPL-*-summary.md`)
+- New test session directory created
+- Metadata includes `workflow_type` and `source_session_id`
 
 **TodoWrite**: Mark phase 1 completed, phase 2 in_progress
 
 ---
 
-### Phase 2: Implementation Analysis
-**Command**: `SlashCommand(command="/workflow:tools:concept-enhanced --session [sessionId] --context [contextPath]")`
+### Phase 2: Gather Cross-Session Context
+**Command**: `SlashCommand(command="/workflow:tools:context-gather --session [testSessionId]")`
 
-**Input**: `sessionId` from Phase 1, `contextPath` from Phase 1
+**Input**: `testSessionId` from Phase 1 (e.g., `WFS-test-user-auth`)
 
-**Expected Analysis**:
-- Review completed implementation summaries
-- Identify test files and coverage gaps
-- Assess test execution strategy
-- Determine failure diagnosis approach
+**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
 
 **Parse Output**:
-- Verify `.workflow/[sessionId]/.process/ANALYSIS_RESULTS.md` created
-- Extract test execution recommendations
-- Identify critical test areas
+- Extract: context package path (store as `contextPath`)
+- Pattern: `.workflow/[testSessionId]/.process/context-package.json`
 
 **Validation**:
-- File `.workflow/[sessionId]/.process/ANALYSIS_RESULTS.md` exists
-- Contains test strategy and execution plan
-- Lists focus test paths and acceptance criteria
+- Context package created in test session directory
+- Contains source session artifacts (summaries, changed files)
+- Includes test file inventory
 
 **TodoWrite**: Mark phase 2 completed, phase 3 in_progress
 
 ---
 
-### Phase 3: TEST-FIX Task Generation
-**Command**: `SlashCommand(command="/workflow:tools:task-generate --session [sessionId]")`
+### Phase 3: Implementation Analysis
+**Command**: `SlashCommand(command="/workflow:tools:concept-enhanced --session [testSessionId] --context [contextPath]")`
 
-**Input**: `sessionId` from Phase 1
+**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
 
 **Expected Behavior**:
-- Parse ANALYSIS_RESULTS.md for test requirements
-- Generate TEST-FIX-001.json with:
-  - `meta.type: "test-fix"`
-  - `meta.agent: "@test-fix-agent"`
-  - `context.requirements`: Test execution requirements
-  - `context.focus_paths`: Test files and source files
-  - `context.acceptance`: All tests pass criteria
-  - `flow_control.pre_analysis`: Load implementation summaries
-  - `flow_control.implementation_approach`: Test execution strategy
+- 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
 
 **Parse Output**:
-- Verify `.workflow/[sessionId]/.task/TEST-FIX-001.json` exists
-- Verify `.workflow/[sessionId]/IMPL_PLAN.md` updated
-- Verify `.workflow/[sessionId]/TODO_LIST.md` updated
+- 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
 
 **Validation**:
-- Task JSON has correct structure (id, meta.type="test-fix", meta.agent="@test-fix-agent")
-- IMPL_PLAN.md contains test-fix strategy
-- TODO_LIST.md shows TEST-FIX-001 task
+- 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)
 
 **TodoWrite**: Mark phase 3 completed, phase 4 in_progress
 
 ---
 
-### Phase 4: Execute Test-Fix Workflow
-**Command**: `SlashCommand(command="/workflow:execute --session [sessionId]")`
+### Phase 4: Generate Test Task
+**Command**: `SlashCommand(command="/workflow:tools:task-generate --session [testSessionId]")`
 
-**Input**: `sessionId` from Phase 1
+**Input**: `testSessionId` from Phase 1
 
 **Expected Behavior**:
-- Workflow executor detects TEST-FIX-001 task
-- Assigns to @test-fix-agent
-- Agent executes tests using flow_control.pre_analysis
-- If failures: diagnoses and fixes code
-- Re-runs tests until all pass
-- Generates completion summary
+- 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 Output**:
+- Verify `.workflow/[testSessionId]/.task/IMPL-001.json` exists
+- Verify `.workflow/[testSessionId]/IMPL_PLAN.md` created
+- Verify `.workflow/[testSessionId]/TODO_LIST.md` created
 
 **Validation**:
-- Workflow execution started successfully
-- TEST-FIX-001 task status updated to "active" or "completed"
+- 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
 
 **TodoWrite**: Mark phase 4 completed
 
 **Return to User**:
 ```
-Test-fix workflow initiated for session: [sessionId]
-- TEST-FIX-001 created and executing
-- @test-fix-agent validating implementation
-- Progress: /workflow:status [sessionId]
+Independent test-fix workflow created successfully!
+
+Source Session: [sourceSessionId]
+Test Session: [testSessionId]
+Task Created: IMPL-001 (test-fix)
+
+Next Steps:
+1. Review test plan: .workflow/[testSessionId]/IMPL_PLAN.md
+2. Execute validation: /workflow:execute
+3. Monitor progress: /workflow:status
+
+The @test-fix-agent will:
+- Execute all tests
+- Diagnose any failures
+- Fix code until tests pass
 ```
 
 ---
@@ -150,72 +193,112 @@ Test-fix workflow initiated for session: [sessionId]
 ```javascript
 // Initialize (before Phase 1)
 TodoWrite({todos: [
-  {"content": "Execute context gathering for test-fix", "status": "in_progress", "activeForm": "Executing context gathering for test-fix"},
-  {"content": "Execute implementation analysis", "status": "pending", "activeForm": "Executing implementation analysis"},
-  {"content": "Execute TEST-FIX task generation", "status": "pending", "activeForm": "Executing TEST-FIX task generation"},
-  {"content": "Execute test-fix workflow", "status": "pending", "activeForm": "Executing test-fix workflow"}
+  {"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": "Execute context gathering for test-fix", "status": "completed", "activeForm": "Executing context gathering for test-fix"},
-  {"content": "Execute implementation analysis", "status": "in_progress", "activeForm": "Executing implementation analysis"},
-  {"content": "Execute TEST-FIX task generation", "status": "pending", "activeForm": "Executing TEST-FIX task generation"},
-  {"content": "Execute test-fix workflow", "status": "pending", "activeForm": "Executing test-fix workflow"}
+  {"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"}
 ]})
 
-// Continue pattern for Phase 2, 3, 4...
+// 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"}
+]})
 ```
 
 ## Data Flow
 
 ```
-Session ID (from argument or auto-detect)
+User: /workflow:test-gen WFS-user-auth
     ↓
-Phase 1: context-gather --session sessionId "test-fix description"
-    ↓ Output: contextPath (context-package-test.json)
+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: concept-enhanced --session sessionId --context contextPath
-    ↓ Input: sessionId + contextPath
-    ↓ Output: ANALYSIS_RESULTS.md (test execution strategy)
+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: task-generate --session sessionId
-    ↓ Input: sessionId + ANALYSIS_RESULTS.md
-    ↓ Output: TEST-FIX-001.json, IMPL_PLAN.md, TODO_LIST.md
+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: execute --session sessionId
-    ↓ Input: sessionId + TEST-FIX-001.json
-    ↓ Output: Test execution and fixing
+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 to user
+Return: Summary with next steps (user triggers /workflow:execute separately)
 ```
 
-## Context Gathering Customization
+## Session Metadata Design
 
-context-gather will analyze:
-- Completed IMPL task summaries
-- Git changes since session start
-- Test files in focus_paths
-- Implementation files to be tested
-- Test framework configuration
+**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"
+}
+```
 
-## Analysis Focus
+## Automatic Cross-Session Context Collection
 
-concept-enhanced will analyze:
-- Test coverage gaps
-- Test execution strategy (unit, integration, e2e)
-- Failure diagnosis approaches
-- Code fixing patterns
-- Test framework best practices
+When `context-gather` detects `workflow_type: "test_session"`:
+
+**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 TEST-FIX-001.json with:
+task-generate creates `IMPL-001.json` (reusing standard format) with:
 
 ```json
 {
-  "id": "TEST-FIX-001",
-  "title": "Execute and validate tests for [sessionId]",
+  "id": "IMPL-001",
+  "title": "Execute and validate tests for [sourceSessionId]",
   "status": "pending",
   "meta": {
     "type": "test-fix",
@@ -239,11 +322,11 @@ task-generate creates TEST-FIX-001.json with:
   "flow_control": {
     "pre_analysis": [
       {
-        "step": "load_implementation_summaries",
-        "action": "Load completed IMPL task summaries",
+        "step": "load_source_session_summaries",
+        "action": "Load implementation summaries from source session",
         "commands": [
-          "bash(find .workflow/[sessionId]/.summaries/ -name 'IMPL-*-summary.md' 2>/dev/null)",
-          "Read(.workflow/[sessionId]/.summaries/IMPL-001-summary.md)"
+          "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"
@@ -286,20 +369,22 @@ task-generate creates TEST-FIX-001.json with:
 ## Error Handling
 
 ### Phase 1 Failures
-- **No session found**: Return error "No active session detected. Provide session-id or run /workflow:plan first"
-- **Invalid session**: Return error "Session [sessionId] not found or incomplete"
-- **No implementation**: Return error "No completed IMPL tasks found. Complete implementation first"
+- **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 2 Failures
-- **Analysis failed**: Return error "Implementation analysis failed. Check context package"
-- **No test strategy**: Return error "Could not determine test execution strategy"
+- **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"
 
 ### Phase 3 Failures
-- **Task generation failed**: Retry once, then return error with details
-- **Invalid task structure**: Return error with JSON validation details
+- **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
-- **Execution failed**: Return error "Could not start test-fix workflow. Check session state"
+- **Task generation failed**: Retry once, then return error with details
+- **Invalid task structure**: Return error with JSON validation details
 
 ## Workflow Integration
 
@@ -307,18 +392,22 @@ task-generate creates TEST-FIX-001.json with:
 ```
 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
+   → Creates IMPL-001-summary.md in WFS-auth
 
 2. Test Generation Phase (test-gen)
    /workflow:test-gen WFS-auth
-   Phase 1: context-gather → Creates context-package-test.json
-   Phase 2: concept-enhanced → Creates ANALYSIS_RESULTS.md
-   Phase 3: task-generate → Creates TEST-FIX-001.json
-   Phase 4: execute → Triggers @test-fix-agent
+   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-Fix Phase (automated)
-   @test-fix-agent picks up TEST-FIX-001
+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
@@ -327,39 +416,72 @@ task-generate creates TEST-FIX-001.json with:
 ```
 
 ### Output Files Created
-- `.workflow/[sessionId]/.process/context-package-test.json` - Test context package
-- `.workflow/[sessionId]/.process/ANALYSIS_RESULTS.md` - Test execution strategy
-- `.workflow/[sessionId]/.task/TEST-FIX-001.json` - Task definition
-- `.workflow/[sessionId]/IMPL_PLAN.md` - Updated with test-fix plan
-- `.workflow/[sessionId]/TODO_LIST.md` - Updated with TEST-FIX task
-- `.workflow/[sessionId]/.summaries/TEST-FIX-001-summary.md` - Created by test-fix-agent after completion
+
+**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)
+- `TODO_LIST.md` - Task checklist
+- `.summaries/IMPL-001-summary.md` - Created by @test-fix-agent after completion
 
 ## Best Practices
 
-1. **Run after implementation complete**: Ensure all IMPL tasks are done before test-gen
-2. **Check git commits**: Make sure implementation changes are committed
-3. **Verify test files exist**: Code-developer should have created tests
-4. **Monitor execution**: Use `/workflow:status` to track test-fix progress
-5. **Review failures**: If tests fail repeatedly, check test-fix-agent summary for details
+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
-✅ Execute Phase 1 immediately with session ID
-✅ Parse context package path from Phase 1 output
-✅ Pass session ID and context path to Phase 2 command
-✅ Verify ANALYSIS_RESULTS.md after Phase 2
-✅ Pass session ID to Phase 3 command
-✅ Verify all Phase 3 outputs (task JSON, IMPL_PLAN, TODO_LIST)
-✅ Pass session ID to Phase 4 command
+✅ 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 only after Phase 4 completes
+✅ 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)
 
 ## Related Commands
 - `/workflow:plan` - Create implementation workflow (run before test-gen)
-- `/workflow:tools:context-gather` - Phase 1 tool for context collection
-- `/workflow:tools:concept-enhanced` - Phase 2 tool for analysis
-- `/workflow:tools:task-generate` - Phase 3 tool for task creation
-- `/workflow:execute` - Phase 4 workflow execution
+- `/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

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

@@ -141,6 +141,9 @@ Advanced solution design and feasibility analysis engine with parallel CLI execu
      RULES:
      - Focus on SOLUTION IMPROVEMENTS and KEY DESIGN DECISIONS, NOT task planning
      - Provide architectural rationale, evaluate alternatives, assess tradeoffs
+     - **CRITICAL**: Identify code targets - existing files as "file:function:lines", new files as "file"
+     - For modifications: specify exact files/functions/line ranges
+     - For new files: specify file path only (no function or lines)
      - Do NOT create task lists, implementation steps, or code examples
      - Do NOT generate any code snippets or implementation details
      - **MUST write output to .workflow/{session_id}/.process/gemini-solution-design.md**
@@ -172,6 +175,8 @@ Advanced solution design and feasibility analysis engine with parallel CLI execu
      RULES:
      - Focus on TECHNICAL FEASIBILITY and RISK ASSESSMENT, NOT implementation planning
      - Validate architectural decisions, identify potential issues, recommend optimizations
+     - **CRITICAL**: Verify code targets - existing files "file:function:lines", new files "file"
+     - Confirm exact locations for modifications, identify additional new files if needed
      - Do NOT create task breakdowns, step-by-step guides, or code examples
      - Do NOT generate any code snippets or implementation details
      - **MUST write output to .workflow/{session_id}/.process/codex-feasibility-validation.md**
@@ -301,6 +306,39 @@ Generated ANALYSIS_RESULTS.md focuses on **solution improvements, key design dec
 - **Module Dependencies**: {dependency_graph_and_order}
 - **Quality Assurance**: {qa_approach_and_validation}
 
+### Code Modification Targets
+**Purpose**: Specific code locations for modification AND new files to create
+
+**Format**:
+- Existing files: `file:function:lines` (with line numbers)
+- New files: `file` (no function or lines)
+
+**Identified Targets**:
+1. **Target**: `src/auth/AuthService.ts:login:45-52`
+   - **Type**: Modify existing
+   - **Modification**: Enhance error handling
+   - **Rationale**: Current logic lacks validation for edge cases
+
+2. **Target**: `src/auth/PasswordReset.ts`
+   - **Type**: Create new file
+   - **Purpose**: Password reset functionality
+   - **Rationale**: New feature requirement
+
+3. **Target**: `src/middleware/auth.ts:validateToken:30-45`
+   - **Type**: Modify existing
+   - **Modification**: Add token expiry check
+   - **Rationale**: Security requirement for JWT validation
+
+4. **Target**: `tests/auth/PasswordReset.test.ts`
+   - **Type**: Create new file
+   - **Purpose**: Test coverage for password reset
+   - **Rationale**: Test requirement for new feature
+
+**Note**:
+- For new files, only specify the file path (no function or lines)
+- For existing files without line numbers, use `file:function:*` format
+- Task generation will refine these during the `analyze_task_patterns` step
+
 ### Feasibility Assessment
 - **Technical Complexity**: {complexity_rating_and_analysis}
 - **Performance Impact**: {expected_performance_characteristics}

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

@@ -212,7 +212,7 @@ Task(
         "Validate against acceptance criteria"
       ]
     },
-    "target_files": ["file:function:lines"]
+    "target_files": ["file:function:lines", "path/to/NewFile.ts"]
   }
 }
 \`\`\`

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

@@ -142,12 +142,12 @@ Generate task JSON files and IMPL_PLAN.md from analysis results with automatic a
       },
       {
         "step": "analyze_task_patterns",
-        "action": "Analyze existing code patterns",
+        "action": "Analyze existing code patterns and identify modification targets",
         "commands": [
           "bash(cd \"[focus_paths]\")",
-          "bash(~/.claude/scripts/gemini-wrapper -p \"PURPOSE: Analyze patterns TASK: Review '[title]' CONTEXT: [synthesis_specification] [individual_artifacts] EXPECTED: Pattern analysis RULES: Prioritize synthesis-specification.md\")"
+          "bash(~/.claude/scripts/gemini-wrapper -p \"PURPOSE: Identify modification targets TASK: Analyze '[title]' and locate specific files/functions/lines to modify CONTEXT: [synthesis_specification] [individual_artifacts] EXPECTED: Code locations in format 'file:function:lines' RULES: Prioritize synthesis-specification.md, identify exact modification points\")"
         ],
-        "output_to": "task_context",
+        "output_to": "task_context_with_targets",
         "on_error": "fail"
       }
     ],
@@ -175,8 +175,40 @@ Generate task JSON files and IMPL_PLAN.md from analysis results with automatic a
 1. Parse analysis results and extract task definitions
 2. Detect brainstorming artifacts with priority scoring
 3. Generate task context (requirements, focus_paths, acceptance)
-4. Build flow_control with artifact loading steps
-5. Create individual task JSON files in `.task/`
+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/`
+
+#### Target Files Generation (Critical)
+**Purpose**: Identify specific code locations for modification AND new files to create
+
+**Source Data Priority**:
+1. **ANALYSIS_RESULTS.md** - Should contain identified code locations
+2. **Gemini/MCP Analysis** - From `analyze_task_patterns` step
+3. **Context Package** - File references from `focus_paths`
+
+**Format**: `["file:function:lines"]` or `["file"]` (for new files)
+- `file`: Relative path from project root (e.g., `src/auth/AuthService.ts`)
+- `function`: Function/method name to modify (e.g., `login`, `validateToken`) - **omit for new files**
+- `lines`: Approximate line range (e.g., `45-52`, `120-135`) - **omit for new files**
+
+**Examples**:
+```json
+"target_files": [
+  "src/auth/AuthService.ts:login:45-52",
+  "src/middleware/auth.ts:validateToken:30-45",
+  "src/auth/PasswordReset.ts",
+  "tests/auth/PasswordReset.test.ts",
+  "tests/auth.test.ts:testLogin:15-20"
+]
+```
+
+**Generation Strategy**:
+- **New files to create** → Use `["path/to/NewFile.ts"]` (no function or lines)
+- **Existing files with specific locations** → Use `["file:function:lines"]`
+- **Existing files with function only** → Search lines using MCP/grep `["file:function:*"]`
+- **Existing files (explore entire)** → Mark as `["file.ts:*:*"]`
+- **No specific targets** → Leave empty `[]` (agent explores focus_paths)
 
 ### Phase 3: Artifact Detection & Integration
 

.claude/workflows/context-search-strategy.md

@@ -6,6 +6,12 @@ type: search-guideline
 
 # Context Search Strategy
 
+## ⚡ Execution Environment
+
+**CRITICAL**: All commands execute in **Bash environment** (Git Bash on Windows, Bash on Linux/macOS)
+
+**❌ Forbidden**: Windows-specific commands (`findstr`, `dir`, `where`, `type`, `copy`, `del`) - Use Bash equivalents (`grep`, `find`, `which`, `cat`, `cp`, `rm`)
+
 ## ⚡ Core Search Tools
 
 **rg (ripgrep)**: Fast content search with regex support
@@ -18,6 +24,7 @@ type: search-guideline
 - **Use find for files** - Locate files/directories by name
 - **Use grep sparingly** - Only when rg unavailable
 - **Use get_modules_by_depth.sh first** - MANDATORY for program architecture analysis before planning
+- **Always use Bash commands** - NEVER use Windows cmd/PowerShell commands
 
 ### Quick Command Reference
 ```bash

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

@@ -41,19 +41,21 @@ type: strategic-guideline
 
 ### Standard Format (REQUIRED)
 ```bash
-# Gemini Analysis
+# 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]
 "
 
-# Qwen Architecture & Code Generation
+# Qwen Architecture Analysis (仅分析)
 cd [directory] && ~/.claude/scripts/qwen-wrapper -p "
-PURPOSE: [clear architecture/code goal]
-TASK: [specific architecture/code task]
+PURPOSE: [clear architecture goal]
+TASK: [specific analysis task]
+MODE: analysis
 CONTEXT: [file references and memory context]
 EXPECTED: [expected deliverables]
 RULES: [template reference and constraints]
@@ -63,6 +65,7 @@ RULES: [template reference and constraints]
 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]
@@ -72,10 +75,26 @@ RULES: [template reference and constraints]
 ### Template Structure
 - [ ] **PURPOSE** - Clear goal and intent
 - [ ] **TASK** - Specific execution task
+- [ ] **MODE** - Execution mode and permission level
 - [ ] **CONTEXT** - File references and memory context from previous sessions
 - [ ] **EXPECTED** - Clear expected results
 - [ ] **RULES** - Template reference and constraints
 
+### MODE Field Definition
+
+The MODE field controls execution behavior and file permissions:
+
+**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）
+
+**For Qwen** (仅分析):
+- `analysis` (default) - 仅架构分析，不生成代码
+
+**For Codex**:
+- `auto` (default) - 自主开发，全文件操作
+- `write` - 测试生成和文件修改
+
 ### Directory Context
 Tools execute in current working directory:
 - **Gemini**: `cd path/to/project && ~/.claude/scripts/gemini-wrapper -p "prompt"`
@@ -150,80 +169,92 @@ When planning any coding task, **ALWAYS** integrate CLI tools:
 
 ### Common Scenarios
 ```bash
-# Project Analysis (in current directory)
+# Gemini - Code Analysis
 ~/.claude/scripts/gemini-wrapper -p "
 PURPOSE: Understand codebase architecture
 TASK: Analyze project structure and identify patterns
+MODE: analysis
 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
+RULES: $(cat '~/.claude/workflows/cli-templates/prompts/analysis/architecture.txt') | Focus on integration points
 "
 
-# Project Analysis (in different directory)
-cd ../other-project && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: Compare authentication patterns
-TASK: Analyze auth implementation in related project
-CONTEXT: @{src/auth/**/*} Current project context from session memory
-EXPECTED: Pattern comparison and recommendations
-RULES: $(cat "~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt") | Focus on architectural differences
+# Gemini - Generate Documentation
+~/.claude/scripts/gemini-wrapper -p "
+PURPOSE: Generate API documentation
+TASK: Create comprehensive API reference from code
+MODE: write
+CONTEXT: @{src/api/**/*}
+EXPECTED: API.md with all endpoints documented
+RULES: Follow project documentation standards
 "
 
-# Architecture Design (with Qwen)
+# Qwen - Architecture Analysis
 cd src/auth && ~/.claude/scripts/qwen-wrapper -p "
-PURPOSE: Design authentication system architecture
-TASK: Create modular JWT-based auth system design
+PURPOSE: Analyze authentication system architecture
+TASK: Review JWT-based auth system design
+MODE: analysis
 CONTEXT: @{src/auth/**/*} Existing patterns and requirements
-EXPECTED: Complete architecture with code scaffolding
-RULES: $(cat "~/.claude/workflows/cli-templates/prompts/analysis/architecture.txt") | Focus on modularity and security
+EXPECTED: Architecture analysis report with recommendations
+RULES: $(cat '~/.claude/workflows/cli-templates/prompts/analysis/architecture.txt') | Focus on security
 "
 
-# Feature Development (in target directory)
+# Codex - Feature Development
 codex -C path/to/project --full-auto exec "
 PURPOSE: Implement user authentication
 TASK: Create JWT-based authentication system
+MODE: auto
 CONTEXT: @{src/auth/**/*} Database schema from session memory
 EXPECTED: Complete auth module with tests
-RULES: $(cat "~/.claude/workflows/cli-templates/prompts/development/feature.txt") | Follow security best practices
+RULES: $(cat '~/.claude/workflows/cli-templates/prompts/development/feature.txt') | Follow security best practices
 " --skip-git-repo-check -s danger-full-access
 
-# Code Review Preparation
-~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: Prepare comprehensive code review
-TASK: Analyze code changes and identify potential issues
-CONTEXT: @{**/*.modified} Recent changes discussed in last session
-EXPECTED: Review checklist and improvement suggestions
-RULES: $(cat "~/.claude/workflows/cli-templates/prompts/analysis/quality.txt") | Focus on maintainability
-"
+# Codex - Test Generation
+codex -C src/auth --full-auto exec "
+PURPOSE: Increase test coverage
+TASK: Generate comprehensive tests for auth module
+MODE: write
+CONTEXT: @{**/*.ts} Exclude existing tests
+EXPECTED: Complete test suite with 80%+ coverage
+RULES: Use Jest, follow existing patterns
+" --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
 
 ## 🎯 Key Features
 
-### Gemini
+### Gemini (全权限)
 - **Command**: `~/.claude/scripts/gemini-wrapper`
 - **Strengths**: Large context window, pattern recognition
-- **Best For**: Analysis, architecture review, code exploration
+- **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
+### Qwen (仅分析)
 - **Command**: `~/.claude/scripts/qwen-wrapper`
-- **Strengths**: Architecture analysis, code generation, implementation patterns
-- **Best For**: System design, code scaffolding, architectural planning
+- **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: `@{**/*}`
@@ -250,15 +281,33 @@ For every development task:
 
 **Example**:
 ```bash
-# Focused analysis (preferred)
-cd src/auth && ~/.claude/scripts/gemini-wrapper -p "analyze auth patterns"
+# Gemini - Focused analysis
+cd src/auth && ~/.claude/scripts/gemini-wrapper -p "
+PURPOSE: Understand authentication patterns
+TASK: Analyze auth implementation
+MODE: analysis
+CONTEXT: @{**/*.ts}
+EXPECTED: Pattern documentation
+RULES: Focus on security best practices
+"
 
-# Focused architecture (Qwen)
-cd src/auth && ~/.claude/scripts/qwen-wrapper -p "design auth architecture"
+# Qwen - Architecture analysis
+cd src/auth && ~/.claude/scripts/qwen-wrapper -p "
+PURPOSE: Analyze auth architecture
+TASK: Review auth system design and patterns
+MODE: analysis
+CONTEXT: @{**/*}
+EXPECTED: Architecture analysis report
+RULES: Focus on modularity and security
+"
 
-# Focused implementation (Codex)
-codex -C src/auth --full-auto exec "analyze auth implementation" --skip-git-repo-check
-
-# Multi-scope (stay in root)
-~/.claude/scripts/gemini-wrapper -p "CONTEXT: @{src/auth/**/*,src/api/**/*}"
+# Codex - Implementation
+codex -C src/auth --full-auto exec "
+PURPOSE: Improve auth implementation
+TASK: Review and enhance auth code
+MODE: auto
+CONTEXT: @{**/*.ts}
+EXPECTED: Code improvements and fixes
+RULES: Maintain backward compatibility
+" --skip-git-repo-check -s danger-full-access
 ```

.claude/workflows/task-core.md

@@ -49,7 +49,8 @@ All task files use this simplified 5-field schema (aligned with workflow-archite
     },
     "target_files": [
       "src/auth/login.ts:handleLogin:75-120",
-      "src/middleware/auth.ts:validateToken"
+      "src/middleware/auth.ts:validateToken",
+      "src/auth/PasswordReset.ts"
     ]
   }
 }
@@ -81,7 +82,7 @@ All task files use this simplified 5-field schema (aligned with workflow-archite
 **Components**:
 - **pre_analysis**: Array of sequential process steps
 - **implementation_approach**: Task execution strategy
-- **target_files**: Specific files to modify in "file:function:lines" format
+- **target_files**: Files to modify/create - existing files in `file:function:lines` format, new files as `file` only
 
 **Step Structure**:
 ```json

.claude/workflows/workflow-architecture.md

@@ -175,7 +175,8 @@ All task files use this unified 5-field schema with optional artifacts enhanceme
     },
     "target_files": [
       "src/auth/login.ts:handleLogin:75-120",
-      "src/middleware/auth.ts:validateToken"
+      "src/middleware/auth.ts:validateToken",
+      "src/auth/PasswordReset.ts"
     ]
   }
 }
@@ -219,7 +220,7 @@ The **flow_control** field manages task execution with two main components:
 - **task_description**: Comprehensive implementation description
 - **modification_points**: Specific code modification targets
 - **logic_flow**: Business logic execution sequence
-- **target_files**: Target file list in `file:function:lines` format
+- **target_files**: Target file list - existing files in `file:function:lines` format, new files as `file` only
 
 #### Tool Reference
 **Command Types Available**:

.codex/AGENTS.md

@@ -0,0 +1,215 @@
+# Codex Agent Execution Protocol
+
+## Overview
+
+**Role**: Codex - autonomous development, implementation, and testing
+
+## Prompt Structure
+
+**Receive prompts in this format**:
+
+```
+PURPOSE: [development goal]
+TASK: [specific implementation task]
+MODE: [auto|write]
+CONTEXT: [file patterns]
+EXPECTED: [deliverables]
+RULES: [constraints and templates]
+```
+
+## Execution Requirements
+
+### ALWAYS
+
+- **Parse all six fields** - Understand PURPOSE, TASK, MODE, CONTEXT, EXPECTED, RULES
+- **Follow MODE strictly** - Respect execution boundaries
+- **Study CONTEXT files** - Find 3+ similar patterns before implementing
+- **Apply RULES** - Follow templates and constraints exactly
+- **Test continuously** - Run tests after every change
+- **Commit incrementally** - Small, working commits
+- **Match project style** - Follow existing patterns exactly
+- **Validate EXPECTED** - Ensure all deliverables are met
+
+### NEVER
+
+- **Make assumptions** - Verify with existing code
+- **Ignore existing patterns** - Study before implementing
+- **Skip tests** - Tests are mandatory
+- **Use clever tricks** - Choose boring, obvious solutions
+- **Over-engineer** - Simple solutions over complex architectures
+- **Break existing code** - Ensure backward compatibility
+- **Exceed 3 attempts** - Stop and reassess if blocked 3 times
+
+## MODE Behavior
+
+### MODE: auto (default)
+
+**Permissions**:
+- Full file operations (create/modify/delete)
+- Run tests and builds
+- Commit code incrementally
+
+**Execute**:
+1. Parse PURPOSE and TASK
+2. Analyze CONTEXT files - find 3+ similar patterns
+3. Plan implementation approach
+4. Generate code following RULES and project patterns
+5. Write tests alongside code
+6. Run tests continuously
+7. Commit working code incrementally
+8. Validate all EXPECTED deliverables
+9. Report results
+
+**Use For**: Feature implementation, bug fixes, refactoring
+
+### MODE: write
+
+**Permissions**:
+- Focused file operations
+- Create/modify specific files
+- Run tests for validation
+
+**Execute**:
+1. Analyze CONTEXT files
+2. Make targeted changes
+3. Validate tests pass
+4. Report file changes
+
+**Use For**: Test generation, documentation updates, targeted fixes
+
+## RULES Processing
+
+- **Parse the RULES field** to identify template content and additional constraints
+- **Recognize `|` as separator** between template and additional constraints
+- **ALWAYS apply all template guidelines** provided in the prompt
+- **ALWAYS apply all additional constraints** specified after `|`
+- **Treat all rules as mandatory** - both template and constraints must be followed
+- **Failure to follow any rule** constitutes task failure
+
+## Error Handling
+
+### Three-Attempt Rule
+
+**On 3rd failed attempt**:
+1. **Stop execution**
+2. **Report status**: What was attempted, what failed, root cause
+3. **Request guidance**: Ask for clarification, suggest alternatives
+
+### Recovery Strategies
+
+**Syntax/Type Errors**:
+1. Review and fix errors
+2. Re-run tests
+3. Validate build succeeds
+
+**Runtime Errors**:
+1. Analyze stack trace
+2. Add error handling
+3. Add tests for error cases
+
+**Test Failures**:
+1. Debug in isolation
+2. Review test setup
+3. Fix implementation or test
+
+**Build Failures**:
+1. Check error messages
+2. Fix incrementally
+3. Validate each fix
+
+## Progress Reporting
+
+### During Execution
+
+```
+[1/5] Analyzing existing code patterns...
+[2/5] Planning implementation approach...
+[3/5] Generating code...
+[4/5] Writing tests...
+[5/5] Running validation...
+```
+
+### On Success
+
+```
+✅ Task completed
+
+Changes:
+- Created: [files with line counts]
+- Modified: [files with changes]
+
+Validation:
+✅ Tests: [count] passing
+✅ Coverage: [percentage]
+✅ Build: Success
+
+Next Steps: [recommendations]
+```
+
+### On Partial Completion
+
+```
+⚠️ Task partially completed
+
+Completed: [what worked]
+Blocked: [what failed and why]
+Required: [what's needed]
+Recommendation: [next steps]
+```
+
+## Quality Standards
+
+### Code Quality
+- Follow project's existing patterns
+- Match import style and naming conventions
+- Single responsibility per function/class
+- DRY (Don't Repeat Yourself)
+- YAGNI (You Aren't Gonna Need It)
+
+### Testing
+- Test all public functions
+- Test edge cases and error conditions
+- Mock external dependencies
+- Target 80%+ coverage
+
+### Error Handling
+- Proper try-catch blocks
+- Clear error messages
+- Graceful degradation
+- Don't expose sensitive info
+
+## Philosophy
+
+- **Incremental progress over big bangs** - Small, testable changes
+- **Learning from existing code** - Study 3+ patterns before implementing
+- **Pragmatic over dogmatic** - Adapt to project reality
+- **Clear intent over clever code** - Boring, obvious solutions
+- **Simple over complex** - Avoid over-engineering
+- **Follow existing style** - Match project patterns exactly
+
+## Execution Checklist
+
+### Before Implementation
+- [ ] Understand PURPOSE and TASK clearly
+- [ ] Review all CONTEXT files
+- [ ] Find 3+ similar patterns in codebase
+- [ ] Check RULES templates and constraints
+- [ ] Plan implementation approach
+
+### During Implementation
+- [ ] Follow existing patterns exactly
+- [ ] Write tests alongside code
+- [ ] Run tests after every change
+- [ ] Commit working code incrementally
+- [ ] Handle errors properly
+
+### After Implementation
+- [ ] Run full test suite - all pass
+- [ ] Check coverage - meets target
+- [ ] Run build - succeeds
+- [ ] Review EXPECTED - all deliverables met
+
+---
+
+**Version**: 2.0.0
+**Last Updated**: 2025-10-02

.gemini/GEMINI.md

@@ -0,0 +1,143 @@
+# Gemini Execution Protocol
+
+## Overview
+
+**Role**: Gemini - code analysis and documentation generation
+
+## Prompt Structure
+
+**Receive prompts in this format**:
+
+```
+PURPOSE: [goal statement]
+TASK: [specific task]
+MODE: [analysis|write]
+CONTEXT: [file patterns]
+EXPECTED: [deliverables]
+RULES: [constraints and templates]
+```
+
+## Execution Requirements
+
+### ALWAYS
+
+- **Parse all six fields** - Understand PURPOSE, TASK, MODE, CONTEXT, EXPECTED, RULES
+- **Follow MODE strictly** - Respect permission boundaries
+- **Analyze CONTEXT files** - Read all matching patterns thoroughly
+- **Apply RULES** - Follow templates and constraints exactly
+- **Provide evidence** - Quote code with file:line references
+- **Match EXPECTED** - Deliver exactly what's requested
+
+### NEVER
+
+- **Assume behavior** - Verify with actual code
+- **Ignore CONTEXT** - Stay within specified file patterns
+- **Skip RULES** - Templates are mandatory when provided
+- **Make unsubstantiated claims** - Always back with code references
+- **Deviate from MODE** - Respect read/write boundaries
+
+## MODE Behavior
+
+### MODE: analysis (default)
+
+**Permissions**:
+- Read all CONTEXT files
+- Create/modify documentation files
+
+**Execute**:
+1. Read and analyze CONTEXT files
+2. Identify patterns and issues
+3. Generate insights and recommendations
+4. Create documentation if needed
+5. Output structured analysis
+
+**Constraint**: Do NOT modify source code files
+
+### MODE: write
+
+**Permissions**:
+- Full file operations
+- Create/modify any files
+
+**Execute**:
+1. Read CONTEXT files
+2. Perform requested file operations
+3. Create/modify files as specified
+4. Validate changes
+5. Report file changes
+
+## Output Format
+
+### Standard Analysis Structure
+
+```markdown
+# Analysis: [TASK Title]
+
+## Summary
+[2-3 sentence overview]
+
+## Key Findings
+1. [Finding] - path/to/file:123
+2. [Finding] - path/to/file:456
+
+## Detailed Analysis
+[Evidence-based analysis with code quotes]
+
+## Recommendations
+1. [Actionable recommendation]
+2. [Actionable recommendation]
+```
+
+### Code References
+
+Always use format: `path/to/file:line_number`
+
+Example: "Authentication logic at `src/auth/jwt.ts:45` uses deprecated algorithm"
+
+## RULES Processing
+
+- **Parse the RULES field** to identify template content and additional constraints
+- **Recognize `|` as separator** between template and additional constraints
+- **ALWAYS apply all template guidelines** provided in the prompt
+- **ALWAYS apply all additional constraints** specified after `|`
+- **Treat all rules as mandatory** - both template and constraints must be followed
+- **Failure to follow any rule** constitutes task failure
+
+## Error Handling
+
+**File Not Found**:
+- Report missing files
+- Continue with available files
+- Note in output
+
+**Invalid CONTEXT Pattern**:
+- Report invalid pattern
+- Request correction
+- Do not guess
+
+## Quality Standards
+
+### Thoroughness
+- Analyze ALL files in CONTEXT
+- Check cross-file patterns
+- Identify edge cases
+- Quantify when possible
+
+### Evidence-Based
+- Quote relevant code
+- Provide file:line references
+- Link related patterns
+
+### Actionable
+- Clear recommendations
+- Prioritized by impact
+- Specific, not vague
+
+## Philosophy
+
+- **Incremental over big bangs** - Suggest small, testable changes
+- **Learn from existing code** - Reference project patterns
+- **Pragmatic over dogmatic** - Adapt to project reality
+- **Clear over clever** - Prefer obvious solutions
+- **Simple over complex** - Avoid over-engineering
+

Install-Claude.ps1

@@ -156,22 +156,34 @@ function Test-Prerequisites {
         Write-ColorOutput "Current version: $($PSVersionTable.PSVersion)" $ColorError
         return $false
     }
-    
+
     # Test source files exist
     $sourceDir = $PSScriptRoot
     $claudeDir = Join-Path $sourceDir ".claude"
     $claudeMd = Join-Path $sourceDir "CLAUDE.md"
-    
+    $codexDir = Join-Path $sourceDir ".codex"
+    $geminiDir = Join-Path $sourceDir ".gemini"
+
     if (-not (Test-Path $claudeDir)) {
         Write-ColorOutput "ERROR: .claude directory not found in $sourceDir" $ColorError
         return $false
     }
-    
+
     if (-not (Test-Path $claudeMd)) {
         Write-ColorOutput "ERROR: CLAUDE.md file not found in $sourceDir" $ColorError
         return $false
     }
-    
+
+    if (-not (Test-Path $codexDir)) {
+        Write-ColorOutput "ERROR: .codex directory not found in $sourceDir" $ColorError
+        return $false
+    }
+
+    if (-not (Test-Path $geminiDir)) {
+        Write-ColorOutput "ERROR: .gemini directory not found in $sourceDir" $ColorError
+        return $false
+    }
+
     Write-ColorOutput "Prerequisites check passed" $ColorSuccess
     return $true
 }
@@ -617,6 +629,8 @@ function Install-Global {
     $userProfile = [Environment]::GetFolderPath("UserProfile")
     $globalClaudeDir = Join-Path $userProfile ".claude"
     $globalClaudeMd = Join-Path $globalClaudeDir "CLAUDE.md"
+    $globalCodexDir = Join-Path $userProfile ".codex"
+    $globalGeminiDir = Join-Path $userProfile ".gemini"
 
     Write-ColorOutput "Global installation path: $userProfile" $ColorInfo
 
@@ -624,12 +638,23 @@ function Install-Global {
     $sourceDir = $PSScriptRoot
     $sourceClaudeDir = Join-Path $sourceDir ".claude"
     $sourceClaudeMd = Join-Path $sourceDir "CLAUDE.md"
+    $sourceCodexDir = Join-Path $sourceDir ".codex"
+    $sourceGeminiDir = Join-Path $sourceDir ".gemini"
 
     # Create backup folder if needed (default behavior unless NoBackup is specified)
     $backupFolder = $null
     if (-not $NoBackup) {
-        if (Test-Path $globalClaudeDir) {
-            $existingFiles = Get-ChildItem $globalClaudeDir -Recurse -File -ErrorAction SilentlyContinue
+        if ((Test-Path $globalClaudeDir) -or (Test-Path $globalCodexDir) -or (Test-Path $globalGeminiDir)) {
+            $existingFiles = @()
+            if (Test-Path $globalClaudeDir) {
+                $existingFiles += Get-ChildItem $globalClaudeDir -Recurse -File -ErrorAction SilentlyContinue
+            }
+            if (Test-Path $globalCodexDir) {
+                $existingFiles += Get-ChildItem $globalCodexDir -Recurse -File -ErrorAction SilentlyContinue
+            }
+            if (Test-Path $globalGeminiDir) {
+                $existingFiles += Get-ChildItem $globalGeminiDir -Recurse -File -ErrorAction SilentlyContinue
+            }
             if (($existingFiles -and ($existingFiles | Measure-Object).Count -gt 0)) {
                 $backupFolder = Get-BackupDirectory -TargetDirectory $userProfile
                 Write-ColorOutput "Backup folder created: $backupFolder" $ColorInfo
@@ -649,6 +674,14 @@ function Install-Global {
     Write-ColorOutput "Installing CLAUDE.md to global .claude directory..." $ColorInfo
     $claudeMdInstalled = Copy-FileToDestination -Source $sourceClaudeMd -Destination $globalClaudeMd -Description "CLAUDE.md" -BackupFolder $backupFolder
 
+    # Merge .codex directory contents
+    Write-ColorOutput "Merging .codex directory contents..." $ColorInfo
+    $codexMerged = Merge-DirectoryContents -Source $sourceCodexDir -Destination $globalCodexDir -Description ".codex directory contents" -BackupFolder $backupFolder
+
+    # Merge .gemini directory contents
+    Write-ColorOutput "Merging .gemini directory contents..." $ColorInfo
+    $geminiMerged = Merge-DirectoryContents -Source $sourceGeminiDir -Destination $globalGeminiDir -Description ".gemini directory contents" -BackupFolder $backupFolder
+
     if ($backupFolder -and (Test-Path $backupFolder)) {
         $backupFiles = Get-ChildItem $backupFolder -Recurse -File -ErrorAction SilentlyContinue
         if (-not $backupFiles -or ($backupFiles | Measure-Object).Count -eq 0) {
@@ -679,14 +712,18 @@ function Install-Path {
     $sourceDir = $PSScriptRoot
     $sourceClaudeDir = Join-Path $sourceDir ".claude"
     $sourceClaudeMd = Join-Path $sourceDir "CLAUDE.md"
+    $sourceCodexDir = Join-Path $sourceDir ".codex"
+    $sourceGeminiDir = Join-Path $sourceDir ".gemini"
 
-    # Local paths - only for agents, commands, output-styles
+    # Local paths - for agents, commands, output-styles, .codex, .gemini
     $localClaudeDir = Join-Path $TargetDirectory ".claude"
+    $localCodexDir = Join-Path $TargetDirectory ".codex"
+    $localGeminiDir = Join-Path $TargetDirectory ".gemini"
 
     # Create backup folder if needed
     $backupFolder = $null
     if (-not $NoBackup) {
-        if ((Test-Path $localClaudeDir) -or (Test-Path $globalClaudeDir)) {
+        if ((Test-Path $localClaudeDir) -or (Test-Path $localCodexDir) -or (Test-Path $localGeminiDir) -or (Test-Path $globalClaudeDir)) {
             $backupFolder = Get-BackupDirectory -TargetDirectory $TargetDirectory
             Write-ColorOutput "Backup folder created: $backupFolder" $ColorInfo
         }
@@ -774,6 +811,14 @@ function Install-Path {
     Write-ColorOutput "Installing CLAUDE.md to global .claude directory..." $ColorInfo
     Copy-FileToDestination -Source $sourceClaudeMd -Destination $globalClaudeMd -Description "CLAUDE.md" -BackupFolder $backupFolder
 
+    # Merge .codex directory contents to local location
+    Write-ColorOutput "Merging .codex directory contents to local location..." $ColorInfo
+    $codexMerged = Merge-DirectoryContents -Source $sourceCodexDir -Destination $localCodexDir -Description ".codex directory contents" -BackupFolder $backupFolder
+
+    # Merge .gemini directory contents to local location
+    Write-ColorOutput "Merging .gemini directory contents to local location..." $ColorInfo
+    $geminiMerged = Merge-DirectoryContents -Source $sourceGeminiDir -Destination $localGeminiDir -Description ".gemini directory contents" -BackupFolder $backupFolder
+
     if ($backupFolder -and (Test-Path $backupFolder)) {
         $backupFiles = Get-ChildItem $backupFolder -Recurse -File -ErrorAction SilentlyContinue
         if (-not $backupFiles -or ($backupFiles | Measure-Object).Count -eq 0) {
@@ -879,10 +924,11 @@ function Show-Summary {
     if ($Mode -eq "Path") {
         Write-Host "  Local Path: $Path"
         Write-Host "  Global Path: $([Environment]::GetFolderPath('UserProfile'))"
-        Write-Host "  Local Components: agents, commands, output-styles"
+        Write-Host "  Local Components: agents, commands, output-styles, .codex, .gemini"
         Write-Host "  Global Components: workflows, scripts, python_script, etc."
     } else {
         Write-Host "  Path: $Path"
+        Write-Host "  Global Components: .claude, .codex, .gemini"
     }
 
     if ($NoBackup) {
@@ -896,10 +942,12 @@ function Show-Summary {
     Write-Host ""
     Write-ColorOutput "Next steps:" $ColorInfo
     Write-Host "1. Review CLAUDE.md - Customize guidelines for your project"
-    Write-Host "2. Configure settings - Edit .claude/settings.local.json as needed"
-    Write-Host "3. Start using Claude Code with Agent workflow coordination!"
-    Write-Host "4. Use /workflow commands for task execution"
-    Write-Host "5. Use /update-memory commands for memory system management"
+    Write-Host "2. Review .codex/Agent.md - Codex agent execution protocol"
+    Write-Host "3. Review .gemini/CLAUDE.md - Gemini agent execution protocol"
+    Write-Host "4. Configure settings - Edit .claude/settings.local.json as needed"
+    Write-Host "5. Start using Claude Code with Agent workflow coordination!"
+    Write-Host "6. Use /workflow commands for task execution"
+    Write-Host "7. Use /update-memory commands for memory system management"
 
     Write-Host ""
     Write-ColorOutput "Documentation: https://github.com/catlog22/Claude-CCW" $ColorInfo

Install-Claude.sh

@@ -97,6 +97,8 @@ function test_prerequisites() {
     local script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
     local claude_dir="$script_dir/.claude"
     local claude_md="$script_dir/CLAUDE.md"
+    local codex_dir="$script_dir/.codex"
+    local gemini_dir="$script_dir/.gemini"
 
     if [ ! -d "$claude_dir" ]; then
         write_color "ERROR: .claude directory not found in $script_dir" "$COLOR_ERROR"
@@ -108,6 +110,16 @@ function test_prerequisites() {
         return 1
     fi
 
+    if [ ! -d "$codex_dir" ]; then
+        write_color "ERROR: .codex directory not found in $script_dir" "$COLOR_ERROR"
+        return 1
+    fi
+
+    if [ ! -d "$gemini_dir" ]; then
+        write_color "ERROR: .gemini directory not found in $script_dir" "$COLOR_ERROR"
+        return 1
+    fi
+
     write_color "✓ Prerequisites check passed" "$COLOR_SUCCESS"
     return 0
 }
@@ -389,6 +401,8 @@ function install_global() {
     local user_home="$HOME"
     local global_claude_dir="${user_home}/.claude"
     local global_claude_md="${global_claude_dir}/CLAUDE.md"
+    local global_codex_dir="${user_home}/.codex"
+    local global_gemini_dir="${user_home}/.gemini"
 
     write_color "Global installation path: $user_home" "$COLOR_INFO"
 
@@ -396,14 +410,25 @@ function install_global() {
     local script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
     local source_claude_dir="${script_dir}/.claude"
     local source_claude_md="${script_dir}/CLAUDE.md"
+    local source_codex_dir="${script_dir}/.codex"
+    local source_gemini_dir="${script_dir}/.gemini"
 
     # Create backup folder if needed
     local backup_folder=""
     if [ "$NO_BACKUP" = false ]; then
+        local has_existing_files=false
+
         if [ -d "$global_claude_dir" ] && [ "$(ls -A "$global_claude_dir" 2>/dev/null)" ]; then
-            backup_folder=$(get_backup_directory "$user_home")
-            write_color "Backup folder created: $backup_folder" "$COLOR_INFO"
+            has_existing_files=true
+        elif [ -d "$global_codex_dir" ] && [ "$(ls -A "$global_codex_dir" 2>/dev/null)" ]; then
+            has_existing_files=true
+        elif [ -d "$global_gemini_dir" ] && [ "$(ls -A "$global_gemini_dir" 2>/dev/null)" ]; then
+            has_existing_files=true
         elif [ -f "$global_claude_md" ]; then
+            has_existing_files=true
+        fi
+
+        if [ "$has_existing_files" = true ]; then
             backup_folder=$(get_backup_directory "$user_home")
             write_color "Backup folder created: $backup_folder" "$COLOR_INFO"
         fi
@@ -417,6 +442,14 @@ function install_global() {
     write_color "Installing CLAUDE.md to global .claude directory..." "$COLOR_INFO"
     copy_file_to_destination "$source_claude_md" "$global_claude_md" "CLAUDE.md" "$backup_folder"
 
+    # Merge .codex directory contents
+    write_color "Merging .codex directory contents..." "$COLOR_INFO"
+    merge_directory_contents "$source_codex_dir" "$global_codex_dir" ".codex directory contents" "$backup_folder"
+
+    # Merge .gemini directory contents
+    write_color "Merging .gemini directory contents..." "$COLOR_INFO"
+    merge_directory_contents "$source_gemini_dir" "$global_gemini_dir" ".gemini directory contents" "$backup_folder"
+
     # Remove empty backup folder
     if [ -n "$backup_folder" ] && [ -d "$backup_folder" ]; then
         if [ -z "$(ls -A "$backup_folder" 2>/dev/null)" ]; then
@@ -442,14 +475,18 @@ function install_path() {
     local script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
     local source_claude_dir="${script_dir}/.claude"
     local source_claude_md="${script_dir}/CLAUDE.md"
+    local source_codex_dir="${script_dir}/.codex"
+    local source_gemini_dir="${script_dir}/.gemini"
 
     # Local paths
     local local_claude_dir="${target_dir}/.claude"
+    local local_codex_dir="${target_dir}/.codex"
+    local local_gemini_dir="${target_dir}/.gemini"
 
     # Create backup folder if needed
     local backup_folder=""
     if [ "$NO_BACKUP" = false ]; then
-        if [ -d "$local_claude_dir" ] || [ -d "$global_claude_dir" ]; then
+        if [ -d "$local_claude_dir" ] || [ -d "$local_codex_dir" ] || [ -d "$local_gemini_dir" ] || [ -d "$global_claude_dir" ]; then
             backup_folder=$(get_backup_directory "$target_dir")
             write_color "Backup folder created: $backup_folder" "$COLOR_INFO"
         fi
@@ -530,6 +567,14 @@ function install_path() {
     write_color "Installing CLAUDE.md to global .claude directory..." "$COLOR_INFO"
     copy_file_to_destination "$source_claude_md" "$global_claude_md" "CLAUDE.md" "$backup_folder"
 
+    # Merge .codex directory contents to local location
+    write_color "Merging .codex directory contents to local location..." "$COLOR_INFO"
+    merge_directory_contents "$source_codex_dir" "$local_codex_dir" ".codex directory contents" "$backup_folder"
+
+    # Merge .gemini directory contents to local location
+    write_color "Merging .gemini directory contents to local location..." "$COLOR_INFO"
+    merge_directory_contents "$source_gemini_dir" "$local_gemini_dir" ".gemini directory contents" "$backup_folder"
+
     # Remove empty backup folder
     if [ -n "$backup_folder" ] && [ -d "$backup_folder" ]; then
         if [ -z "$(ls -A "$backup_folder" 2>/dev/null)" ]; then
@@ -631,10 +676,11 @@ function show_summary() {
     if [ "$mode" = "Path" ]; then
         echo "  Local Path: $path"
         echo "  Global Path: $HOME"
-        echo "  Local Components: agents, commands, output-styles"
+        echo "  Local Components: agents, commands, output-styles, .codex, .gemini"
         echo "  Global Components: workflows, scripts, python_script, etc."
     else
         echo "  Path: $path"
+        echo "  Global Components: .claude, .codex, .gemini"
     fi
 
     if [ "$NO_BACKUP" = true ]; then
@@ -648,10 +694,12 @@ function show_summary() {
     echo ""
     write_color "Next steps:" "$COLOR_INFO"
     echo "1. Review CLAUDE.md - Customize guidelines for your project"
-    echo "2. Configure settings - Edit .claude/settings.local.json as needed"
-    echo "3. Start using Claude Code with Agent workflow coordination!"
-    echo "4. Use /workflow commands for task execution"
-    echo "5. Use /update-memory commands for memory system management"
+    echo "2. Review .codex/Agent.md - Codex agent execution protocol"
+    echo "3. Review .gemini/CLAUDE.md - Gemini agent execution protocol"
+    echo "4. Configure settings - Edit .claude/settings.local.json as needed"
+    echo "5. Start using Claude Code with Agent workflow coordination!"
+    echo "6. Use /workflow commands for task execution"
+    echo "7. Use /update-memory commands for memory system management"
 
     echo ""
     write_color "Documentation: https://github.com/catlog22/Claude-Code-Workflow" "$COLOR_INFO"

PROJECT_INTRODUCTION.md

@@ -1,6 +1,6 @@
 # 🚀 Claude Code Workflow (CCW): 下一代多智能体软件开发自动化框架
 
-[![Version](https://img.shields.io/badge/version-v2.1.0--experimental-blue.svg)](https://github.com/catlog22/Claude-Code-Workflow/releases)
+[![Version](https://img.shields.io/badge/version-v3.2.1-blue.svg)](https://github.com/catlog22/Claude-Code-Workflow/releases)
 [![MCP工具](https://img.shields.io/badge/🔧_MCP工具-实验性-orange.svg)](https://github.com/modelcontextprotocol)
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
 

README.md

@@ -2,7 +2,7 @@
 
 <div align="center">
 
-[![Version](https://img.shields.io/badge/version-v3.1.0-blue.svg)](https://github.com/catlog22/Claude-Code-Workflow/releases)
+[![Version](https://img.shields.io/badge/version-v3.2.1-blue.svg)](https://github.com/catlog22/Claude-Code-Workflow/releases)
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
 [![Platform](https://img.shields.io/badge/platform-Windows%20%7C%20Linux%20%7C%20macOS-lightgrey.svg)]()
 [![MCP Tools](https://img.shields.io/badge/🔧_MCP_Tools-Experimental-orange.svg)](https://github.com/modelcontextprotocol)
@@ -15,9 +15,13 @@
 
 **Claude Code Workflow (CCW)** is a next-generation multi-agent automation framework that orchestrates complex software development tasks through intelligent workflow management and autonomous execution.
 
-> **🎉 Latest: v3.1.0** - TDD Workflow Support with Red-Green-Refactor cycle enforcement. See [CHANGELOG.md](CHANGELOG.md) for details.
+> **🎉 Latest: v3.2.0** - Simplified agent architecture with "Tests Are the Review" philosophy. See [CHANGELOG.md](CHANGELOG.md) for details.
 >
-> **v3.0.0**: Introduced **unified CLI command structure**. The `/cli:*` commands consolidate all tool interactions (Gemini, Qwen, Codex) using a `--tool` flag for selection.
+> **What's New in v3.2.0**:
+> - 🔄 Simplified from 3 agents to 2 core agents (`@code-developer`, `@test-fix-agent`)
+> - ✅ "Tests Are the Review" - Passing tests = approved code
+> - 🧪 Enhanced test-fix workflow with automatic execution and fixing
+> - 📦 Interactive installation with version selection menu
 
 ---
 
@@ -49,12 +53,59 @@ Invoke-Expression (Invoke-WebRequest -Uri "https://raw.githubusercontent.com/cat
 bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.sh)
 ```
 
+### **📋 Interactive Version Selection**
+
+After running the installation command, you'll see an interactive menu with real-time version information:
+
+```
+Detecting latest release and commits...
+Latest stable: v3.2.0 (2025-10-02 04:27 UTC)
+Latest commit: cdea58f (2025-10-02 08:15 UTC)
+
+====================================================
+            Version Selection Menu
+====================================================
+
+1) Latest Stable Release (Recommended)
+   |-- Version: v3.2.0
+   |-- Released: 2025-10-02 04:27 UTC
+   \-- Production-ready
+
+2) Latest Development Version
+   |-- Branch: main
+   |-- Commit: cdea58f
+   |-- Updated: 2025-10-02 08:15 UTC
+   |-- Cutting-edge features
+   \-- May contain experimental changes
+
+3) Specific Release Version
+   |-- Install a specific tagged release
+   \-- Recent: v3.2.0, v3.1.0, v3.0.1
+
+====================================================
+
+Select version to install (1-3, default: 1):
+```
+
+**Version Options:**
+- **Option 1 (Recommended)**: Latest stable release with verified production quality
+- **Option 2**: Latest development version from main branch with newest features
+- **Option 3**: Specific version tag for controlled deployments
+
+> 💡 **Pro Tip**: The installer automatically detects and displays the latest version numbers and release dates from GitHub. Just press Enter to select the recommended stable release.
+
 ### **✅ Verify Installation**
 After installation, run the following command to ensure CCW is working:
 ```bash
 /workflow:session:list
 ```
 
+> **📝 Important Notes:**
+> - The installer will automatically install/update `.codex/` and `.gemini/` directories
+> - **Global mode**: Installs to `~/.codex` and `~/.gemini`
+> - **Path mode**: Installs to your specified directory (e.g., `project/.codex`, `project/.gemini`)
+> - Existing files will be backed up automatically before installation
+
 ---
 
 ## 🚀 Getting Started
@@ -117,6 +168,22 @@ After installation, run the following command to ensure CCW is working:
 /workflow:execute
 ```
 
+> **💡 When to Use Which Approach?**
+>
+> **Use `/workflow:plan` + `/workflow:execute` for:**
+> - Complex features requiring multiple modules (>3 modules)
+> - Tasks with multiple subtasks (>5 subtasks)
+> - Cross-cutting changes affecting architecture
+> - Features requiring coordination between components
+> - When you need structured planning and progress tracking
+>
+> **Use Claude Code directly for:**
+> - Simple, focused changes (single file or module)
+> - Quick bug fixes with clear solutions
+> - Documentation updates
+> - Code refactoring within one component
+> - Straightforward feature additions
+
 **Code Analysis:**
 ```bash
 # Deep codebase analysis
@@ -166,6 +233,41 @@ After installation, run the following command to ensure CCW is working:
 
 ## ⚙️ Configuration
 
+### **Prerequisites: Required Tools**
+
+Before using CCW, install the following command-line tools:
+
+#### **Core CLI Tools**
+
+| Tool | Purpose | Installation |
+|------|---------|--------------|
+| **Gemini CLI** | AI analysis & documentation | `npm install -g @google/gemini-cli` ([GitHub](https://github.com/google-gemini/gemini-cli)) |
+| **Codex CLI** | AI development & implementation | `npm install -g @openai/codex` ([GitHub](https://github.com/openai/codex)) |
+| **Qwen Code** | AI architecture & code generation | `npm install -g @qwen-code/qwen-code` ([Docs](https://github.com/QwenLM/qwen-code)) |
+
+#### **System Utilities**
+
+| Tool | Purpose | Installation |
+|------|---------|--------------|
+| **ripgrep (rg)** | Fast code search | [Download](https://github.com/BurntSushi/ripgrep/releases) or `brew install ripgrep` (macOS), `apt install ripgrep` (Ubuntu) |
+| **jq** | JSON processing | [Download](https://jqlang.github.io/jq/download/) or `brew install jq` (macOS), `apt install jq` (Ubuntu) |
+
+**Quick Install (All Tools):**
+
+```bash
+# macOS
+brew install ripgrep jq
+npm install -g @google/gemini-cli @openai/codex @qwen-code/qwen-code
+
+# Ubuntu/Debian
+sudo apt install ripgrep jq
+npm install -g @google/gemini-cli @openai/codex @qwen-code/qwen-code
+
+# Windows (Chocolatey)
+choco install ripgrep jq
+npm install -g @google/gemini-cli @openai/codex @qwen-code/qwen-code
+```
+
 ### **Essential: Gemini CLI Setup**
 
 Configure Gemini CLI for optimal integration:

README_CN.md

@@ -2,7 +2,7 @@
 
 <div align="center">
 
-[![Version](https://img.shields.io/badge/version-v3.1.0-blue.svg)](https://github.com/catlog22/Claude-Code-Workflow/releases)
+[![Version](https://img.shields.io/badge/version-v3.2.1-blue.svg)](https://github.com/catlog22/Claude-Code-Workflow/releases)
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
 [![Platform](https://img.shields.io/badge/platform-Windows%20%7C%20Linux%20%7C%20macOS-lightgrey.svg)]()
 [![MCP工具](https://img.shields.io/badge/🔧_MCP工具-实验性-orange.svg)](https://github.com/modelcontextprotocol)
@@ -15,9 +15,13 @@
 
 **Claude Code Workflow (CCW)** 是一个新一代的多智能体自动化开发框架，通过智能工作流管理和自主执行来协调复杂的软件开发任务。
 
-> **🎉 最新版本: v3.1.0** - TDD 工作流支持，包含 Red-Green-Refactor 循环强制执行。详见 [CHANGELOG.md](CHANGELOG.md)。
+> **🎉 最新版本: v3.2.0** - 采用"测试即审查"理念简化智能体架构。详见 [CHANGELOG.md](CHANGELOG.md)。
 >
-> **v3.0.0 版本**: 引入了**统一的 CLI 命令结构**。`/cli:*` 命令通过 `--tool` 标志整合了所有工具（Gemini, Qwen, Codex）的交互。
+> **v3.2.0 版本新特性**:
+> - 🔄 从 3 个智能体简化为 2 个核心智能体（`@code-developer`、`@test-fix-agent`）
+> - ✅ "测试即审查" - 测试通过 = 代码批准
+> - 🧪 增强的测试修复工作流，支持自动执行和修复
+> - 📦 交互式安装，包含版本选择菜单
 
 ---
 
@@ -49,12 +53,59 @@ Invoke-Expression (Invoke-WebRequest -Uri "https://raw.githubusercontent.com/cat
 bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.sh)
 ```
 
+### **📋 交互式版本选择**
+
+运行安装命令后，您将看到包含实时版本信息的交互式菜单：
+
+```
+正在检测最新版本和提交...
+最新稳定版: v3.2.0 (2025-10-02 04:27 UTC)
+最新提交: cdea58f (2025-10-02 08:15 UTC)
+
+====================================================
+            版本选择菜单
+====================================================
+
+1) 最新稳定版（推荐）
+   |-- 版本: v3.2.0
+   |-- 发布时间: 2025-10-02 04:27 UTC
+   \-- 生产就绪
+
+2) 最新开发版
+   |-- 分支: main
+   |-- 提交: cdea58f
+   |-- 更新时间: 2025-10-02 08:15 UTC
+   |-- 最新功能
+   \-- 可能包含实验性更改
+
+3) 指定版本
+   |-- 安装特定标签版本
+   \-- 最近版本: v3.2.0, v3.1.0, v3.0.1
+
+====================================================
+
+选择要安装的版本 (1-3, 默认: 1):
+```
+
+**版本选项：**
+- **选项 1（推荐）**：经过验证的最新稳定版本，生产环境可用
+- **选项 2**：来自 main 分支的最新开发版本，包含最新功能
+- **选项 3**：指定版本标签，用于受控部署
+
+> 💡 **提示**：安装程序会自动从 GitHub 检测并显示最新的版本号和发布日期。只需按 Enter 键即可选择推荐的稳定版本。
+
 ### **✅ 验证安装**
 安装后，运行以下命令以确保 CCW 正常工作：
 ```bash
 /workflow:session:list
 ```
 
+> **📝 重要说明：**
+> - 安装程序将自动安装/更新 `.codex/` 和 `.gemini/` 目录
+> - **全局模式**：安装到 `~/.codex` 和 `~/.gemini`
+> - **路径模式**：安装到指定目录（例如 `project/.codex`、`project/.gemini`）
+> - 安装前会自动备份现有文件
+
 ---
 
 ## 🚀 快速入门
@@ -120,6 +171,22 @@ bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflo
 /workflow:execute
 ```
 
+> **💡 何时使用哪种方式？**
+>
+> **使用 `/workflow:plan` + `/workflow:execute` 适用于：**
+> - 需要多个模块的复杂功能（>3 个模块）
+> - 包含多个子任务的任务（>5 个子任务）
+> - 影响架构的横切变更
+> - 需要组件间协调的功能
+> - 需要结构化规划和进度跟踪时
+>
+> **直接使用 Claude Code 适用于：**
+> - 简单、聚焦的变更（单个文件或模块）
+> - 解决方案明确的快速 bug 修复
+> - 文档更新
+> - 单个组件内的代码重构
+> - 简单直接的功能添加
+
 **代码分析：**
 ```bash
 # 深度代码库分析
@@ -169,6 +236,41 @@ bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflo
 
 ## ⚙️ 配置
 
+### **前置要求：必需工具**
+
+在使用 CCW 之前，请安装以下命令行工具：
+
+#### **核心 CLI 工具**
+
+| 工具 | 用途 | 安装方式 |
+|------|------|----------|
+| **Gemini CLI** | AI 分析与文档生成 | `npm install -g @google/gemini-cli` ([GitHub](https://github.com/google-gemini/gemini-cli)) |
+| **Codex CLI** | AI 开发与实现 | `npm install -g @openai/codex` ([GitHub](https://github.com/openai/codex)) |
+| **Qwen Code** | AI 架构与代码生成 | `npm install -g @qwen-code/qwen-code` ([文档](https://github.com/QwenLM/qwen-code)) |
+
+#### **系统实用工具**
+
+| 工具 | 用途 | 安装方式 |
+|------|------|----------|
+| **ripgrep (rg)** | 快速代码搜索 | [下载](https://github.com/BurntSushi/ripgrep/releases) 或 `brew install ripgrep` (macOS), `apt install ripgrep` (Ubuntu) |
+| **jq** | JSON 处理 | [下载](https://jqlang.github.io/jq/download/) 或 `brew install jq` (macOS), `apt install jq` (Ubuntu) |
+
+**快速安装（所有工具）：**
+
+```bash
+# macOS
+brew install ripgrep jq
+npm install -g @google/gemini-cli @openai/codex @qwen-code/qwen-code
+
+# Ubuntu/Debian
+sudo apt install ripgrep jq
+npm install -g @google/gemini-cli @openai/codex @qwen-code/qwen-code
+
+# Windows (Chocolatey)
+choco install ripgrep jq
+npm install -g @google/gemini-cli @openai/codex @qwen-code/qwen-code
+```
+
 ### **必需: Gemini CLI 设置**
 
 配置 Gemini CLI 以实现最佳集成：

RELEASE_NOTES_v3.2.1.md

@@ -0,0 +1,142 @@
+# 🔧 Claude Code Workflow (CCW) v3.2.1 Release Notes
+
+**Release Date**: October 2, 2025
+**Release Type**: Patch Release - Documentation Fix
+**Repository**: https://github.com/catlog22/Claude-Code-Workflow
+
+---
+
+## 📋 Overview
+
+CCW v3.2.1 is a critical documentation fix release that corrects `workflow-session.json` path references throughout the brainstorming workflow documentation. This ensures consistency with the architecture specification defined in `workflow-architecture.md`.
+
+---
+
+## 🐛 Bug Fixes
+
+### **Documentation Path Corrections**
+
+**Issue**: Documentation incorrectly referenced `workflow-session.json` inside the `.brainstorming/` subdirectory
+
+**Impact**:
+- Confusing path references in 9 brainstorming role documentation files
+- Inconsistency with architectural specifications
+- Potential runtime errors when commands attempt to read session metadata
+
+**Fixed Files** (9 total):
+1. ✅ `data-architect.md`
+2. ✅ `product-manager.md`
+3. ✅ `product-owner.md`
+4. ✅ `scrum-master.md`
+5. ✅ `subject-matter-expert.md`
+6. ✅ `ui-designer.md`
+7. ✅ `ux-expert.md`
+8. ✅ `auto-parallel.md`
+9. ✅ `artifacts.md`
+
+**Corrections Applied**:
+- ❌ **Incorrect**: `.workflow/WFS-{session}/.brainstorming/workflow-session.json`
+- ✅ **Correct**: `.workflow/WFS-{session}/workflow-session.json`
+
+---
+
+## 📐 Architecture Alignment
+
+### Confirmed Standard Structure
+```
+.workflow/WFS-[topic-slug]/
+├── workflow-session.json        # ✅ Session metadata (root level)
+├── .brainstorming/              # Brainstorming artifacts subdirectory
+│   └── topic-framework.md
+├── IMPL_PLAN.md
+├── TODO_LIST.md
+└── .task/
+    └── IMPL-*.json
+```
+
+### Key Points
+- `workflow-session.json` is **always at session root level**
+- `.brainstorming/` directory contains **only** framework and analysis files
+- No session metadata files inside subdirectories
+
+---
+
+## 📊 Changes Summary
+
+| Category | Files Changed | Lines Modified |
+|----------|--------------|----------------|
+| Documentation Fixes | 9 | 19 insertions, 18 deletions |
+| Path Corrections | 8 role files | 2 corrections per file |
+| Structure Clarifications | 1 artifacts file | Added architectural note |
+
+---
+
+## ✅ Verification
+
+**Pre-Release Checks**:
+- ✅ No incorrect `.brainstorming/workflow-session.json` references
+- ✅ No legacy `session.json` references
+- ✅ All brainstorming roles use correct paths
+- ✅ Architecture consistency verified with Gemini analysis
+
+---
+
+## 🔄 Upgrade Instructions
+
+### For Existing Users
+
+**No action required** - This is a documentation-only fix.
+
+1. Pull the latest changes:
+   ```bash
+   git pull origin main
+   ```
+
+2. Review updated documentation:
+   - `.claude/commands/workflow/brainstorm/*.md`
+
+### For New Users
+
+Simply clone the repository with the correct documentation:
+```bash
+git clone https://github.com/catlog22/Claude-Code-Workflow.git
+```
+
+---
+
+## 📚 Related Documentation
+
+- **Architecture Reference**: `.claude/workflows/workflow-architecture.md`
+- **Brainstorming Commands**: `.claude/commands/workflow/brainstorm/`
+- **Session Management**: `.claude/commands/workflow/session/`
+
+---
+
+## 🙏 Acknowledgments
+
+Special thanks to the analysis tools used in this fix:
+- **Gemini CLI**: Path verification and consistency checking
+- **Codex**: Initial codebase analysis
+- **Claude Code**: Documentation review and corrections
+
+---
+
+## 🔗 Links
+
+- **Full Changelog**: [v3.2.0...v3.2.1](https://github.com/catlog22/Claude-Code-Workflow/compare/v3.2.0...v3.2.1)
+- **Issues Fixed**: Documentation consistency issue
+- **Previous Release**: [v3.2.0 Release Notes](RELEASE_NOTES_v3.2.0.md)
+
+---
+
+## 📝 Notes
+
+- This is a **non-breaking change** - existing workflows will continue to function
+- Documentation now correctly reflects the implemented architecture
+- No code changes were necessary - this was purely a documentation correction
+
+---
+
+**Contributors**: Claude Code Development Team
+**License**: MIT
+**Support**: [GitHub Issues](https://github.com/catlog22/Claude-Code-Workflow/issues)

install-remote.ps1

@@ -1,16 +1,88 @@
 #!/usr/bin/env pwsh
-# Claude Code Workflow (CCW) - Remote Installation Script
-# One-liner remote installation for Claude Code Workflow system
+<#
+.SYNOPSIS
+    Claude Code Workflow (CCW) - Remote Installation Script
+
+.DESCRIPTION
+    One-liner remote installation for Claude Code Workflow system.
+    Downloads and installs CCW from GitHub with flexible version selection.
+
+.PARAMETER Version
+    Installation version type:
+    - "stable" (default): Latest stable release tag
+    - "latest": Latest main branch (development version)
+    - "branch": Install from specific branch
+
+.PARAMETER Tag
+    Specific release tag to install (e.g., "v3.2.0")
+    Only used when Version is "stable"
+
+.PARAMETER Branch
+    Branch name to install from (default: "main")
+    Only used when Version is "branch"
+
+.PARAMETER Global
+    Install to global user directory (~/.claude)
+
+.PARAMETER Directory
+    Install to custom directory
+
+.PARAMETER Force
+    Skip confirmation prompts
+
+.PARAMETER NoBackup
+    Skip backup of existing installation
+
+.PARAMETER NonInteractive
+    Run in non-interactive mode
+
+.PARAMETER BackupAll
+    Backup all files including git-ignored files
+
+.EXAMPLE
+    # Install latest stable release (recommended)
+    .\install-remote.ps1
+
+.EXAMPLE
+    # Install specific stable version
+    .\install-remote.ps1 -Version stable -Tag "v3.2.0"
+
+.EXAMPLE
+    # Install latest development version
+    .\install-remote.ps1 -Version latest
+
+.EXAMPLE
+    # Install from specific branch
+    .\install-remote.ps1 -Version branch -Branch "feature/new-feature"
+
+.EXAMPLE
+    # Install to global directory without prompts
+    .\install-remote.ps1 -Global -Force
+
+.LINK
+    https://github.com/catlog22/Claude-Code-Workflow
+#>
 
 [CmdletBinding()]
 param(
+    [ValidateSet("stable", "latest", "branch")]
+    [string]$Version = "stable",
+
+    [string]$Tag = "",
+
+    [string]$Branch = "main",
+
     [switch]$Global,
+
     [string]$Directory = "",
+
     [switch]$Force,
+
     [switch]$NoBackup,
+
     [switch]$NonInteractive,
-    [switch]$BackupAll,
-    [string]$Branch = "main"
+
+    [switch]$BackupAll
 )
 
 # Set encoding for proper Unicode support
@@ -26,7 +98,7 @@ if ($PSVersionTable.PSVersion.Major -ge 6) {
 
 # Script metadata
 $ScriptName = "Claude Code Workflow (CCW) Remote Installer"
-$Version = "2.1.1"
+$InstallerVersion = "2.2.0"
 
 # Colors for output
 $ColorSuccess = "Green"
@@ -43,7 +115,7 @@ function Write-ColorOutput {
 }
 
 function Show-Header {
-    Write-ColorOutput "==== $ScriptName v$Version ====" $ColorInfo
+    Write-ColorOutput "==== $ScriptName v$InstallerVersion ====" $ColorInfo
     Write-ColorOutput "========================================================" $ColorInfo
     Write-Host ""
 }
@@ -78,29 +150,70 @@ function Get-TempDirectory {
     return $tempDir
 }
 
+function Get-LatestRelease {
+    try {
+        $apiUrl = "https://api.github.com/repos/catlog22/Claude-Code-Workflow/releases/latest"
+        $response = Invoke-RestMethod -Uri $apiUrl -UseBasicParsing
+        return $response.tag_name
+    } catch {
+        Write-ColorOutput "WARNING: Failed to fetch latest release, using 'main' branch" $ColorWarning
+        return $null
+    }
+}
+
 function Download-Repository {
     param(
         [string]$TempDir,
-        [string]$Branch = "main"
+        [string]$Version = "stable",
+        [string]$Branch = "main",
+        [string]$Tag = ""
     )
-    
+
     $repoUrl = "https://github.com/catlog22/Claude-Code-Workflow"
-    $zipUrl = "$repoUrl/archive/refs/heads/$Branch.zip"
+
+    # Determine download URL based on version type
+    if ($Version -eq "stable") {
+        # Download latest stable release
+        if ([string]::IsNullOrEmpty($Tag)) {
+            $latestTag = Get-LatestRelease
+            if ($latestTag) {
+                $Tag = $latestTag
+            } else {
+                # Fallback to main branch if API fails
+                $zipUrl = "$repoUrl/archive/refs/heads/main.zip"
+                $downloadType = "main branch (fallback)"
+            }
+        }
+
+        if (-not [string]::IsNullOrEmpty($Tag)) {
+            $zipUrl = "$repoUrl/archive/refs/tags/$Tag.zip"
+            $downloadType = "stable release $Tag"
+        }
+    } elseif ($Version -eq "latest") {
+        # Download latest main branch
+        $zipUrl = "$repoUrl/archive/refs/heads/main.zip"
+        $downloadType = "latest main branch"
+    } else {
+        # Download specific branch
+        $zipUrl = "$repoUrl/archive/refs/heads/$Branch.zip"
+        $downloadType = "branch $Branch"
+    }
+
     $zipPath = Join-Path $TempDir "repo.zip"
-    
+
     Write-ColorOutput "Downloading from GitHub..." $ColorInfo
     Write-ColorOutput "Source: $repoUrl" $ColorInfo
-    Write-ColorOutput "Branch: $Branch" $ColorInfo
-    
+    Write-ColorOutput "Type: $downloadType" $ColorInfo
+
     try {
         # Download with progress
         $progressPreference = $ProgressPreference
         $ProgressPreference = 'SilentlyContinue'
-        
+
         Invoke-WebRequest -Uri $zipUrl -OutFile $zipPath -UseBasicParsing
-        
+
         $ProgressPreference = $progressPreference
-        
+
         if (Test-Path $zipPath) {
             $fileSize = (Get-Item $zipPath).Length
             Write-ColorOutput "Download complete ($([math]::Round($fileSize/1024/1024, 2)) MB)" $ColorSuccess
@@ -225,29 +338,200 @@ function Wait-ForUserConfirmation {
     }
 }
 
+function Show-VersionMenu {
+    param(
+        [string]$LatestStableVersion = "Detecting...",
+        [string]$LatestStableDate = "",
+        [string]$LatestCommitId = "",
+        [string]$LatestCommitDate = ""
+    )
+
+    Write-Host ""
+    Write-ColorOutput "====================================================" $ColorInfo
+    Write-ColorOutput "            Version Selection Menu" $ColorInfo
+    Write-ColorOutput "====================================================" $ColorInfo
+    Write-Host ""
+
+    # Option 1: Latest Stable
+    Write-ColorOutput "1) Latest Stable Release (Recommended)" $ColorSuccess
+    if ($LatestStableVersion -ne "Detecting..." -and $LatestStableVersion -ne "Unknown") {
+        Write-Host "   |-- Version: $LatestStableVersion"
+        if ($LatestStableDate) {
+            Write-Host "   |-- Released: $LatestStableDate"
+        }
+        Write-Host "   \-- Production-ready"
+    } else {
+        Write-Host "   |-- Version: Auto-detected from GitHub"
+        Write-Host "   \-- Production-ready"
+    }
+    Write-Host ""
+
+    # Option 2: Latest Development
+    Write-ColorOutput "2) Latest Development Version" $ColorWarning
+    Write-Host "   |-- Branch: main"
+    if ($LatestCommitId -and $LatestCommitDate) {
+        Write-Host "   |-- Commit: $LatestCommitId"
+        Write-Host "   |-- Updated: $LatestCommitDate"
+    }
+    Write-Host "   |-- Cutting-edge features"
+    Write-Host "   \-- May contain experimental changes"
+    Write-Host ""
+
+    # Option 3: Specific Version
+    Write-ColorOutput "3) Specific Release Version" $ColorInfo
+    Write-Host "   |-- Install a specific tagged release"
+    Write-Host "   \-- Recent: v3.2.0, v3.1.0, v3.0.1"
+    Write-Host ""
+
+    Write-ColorOutput "====================================================" $ColorInfo
+    Write-Host ""
+}
+
+function Get-UserVersionChoice {
+    if ($NonInteractive -or $Force) {
+        # Non-interactive mode: use default stable version
+        return @{
+            Type = "stable"
+            Tag = $Tag
+            Branch = $Branch
+        }
+    }
+
+    # Detect latest stable version and commit info
+    Write-ColorOutput "Detecting latest release and commits..." $ColorInfo
+    $latestVersion = "Unknown"
+    $latestStableDate = ""
+    $latestCommitId = ""
+    $latestCommitDate = ""
+
+    try {
+        # Get latest release info
+        $apiUrl = "https://api.github.com/repos/catlog22/Claude-Code-Workflow/releases/latest"
+        $response = Invoke-RestMethod -Uri $apiUrl -UseBasicParsing -TimeoutSec 5
+        $latestVersion = $response.tag_name
+
+        # Parse and format release date
+        if ($response.published_at) {
+            $publishDate = [DateTime]::Parse($response.published_at)
+            $latestStableDate = $publishDate.ToString("yyyy-MM-dd HH:mm UTC")
+        }
+
+        Write-ColorOutput "Latest stable: $latestVersion ($latestStableDate)" $ColorSuccess
+    } catch {
+        Write-ColorOutput "Could not detect latest release" $ColorWarning
+    }
+
+    try {
+        # Get latest commit info from main branch
+        $commitUrl = "https://api.github.com/repos/catlog22/Claude-Code-Workflow/commits/main"
+        $commitResponse = Invoke-RestMethod -Uri $commitUrl -UseBasicParsing -TimeoutSec 5
+        $latestCommitId = $commitResponse.sha.Substring(0, 7)
+
+        # Parse and format commit date
+        if ($commitResponse.commit.committer.date) {
+            $commitDate = [DateTime]::Parse($commitResponse.commit.committer.date)
+            $latestCommitDate = $commitDate.ToString("yyyy-MM-dd HH:mm UTC")
+        }
+
+        Write-ColorOutput "Latest commit: $latestCommitId ($latestCommitDate)" $ColorSuccess
+    } catch {
+        Write-ColorOutput "Could not detect latest commit" $ColorWarning
+    }
+
+    Show-VersionMenu -LatestStableVersion $latestVersion -LatestStableDate $latestStableDate -LatestCommitId $latestCommitId -LatestCommitDate $latestCommitDate
+
+    $choice = Read-Host "Select version to install (1-3, default: 1)"
+
+    switch ($choice) {
+        "2" {
+            Write-Host ""
+            Write-ColorOutput "✓ Selected: Latest Development Version (main branch)" $ColorSuccess
+            return @{
+                Type = "latest"
+                Tag = ""
+                Branch = "main"
+            }
+        }
+        "3" {
+            Write-Host ""
+            Write-ColorOutput "Available recent releases:" $ColorInfo
+            Write-Host "  v3.2.0, v3.1.0, v3.0.1, v3.0.0"
+            Write-Host ""
+            $tagInput = Read-Host "Enter version tag (e.g., v3.2.0)"
+
+            if ([string]::IsNullOrWhiteSpace($tagInput)) {
+                Write-ColorOutput "No tag specified, using latest stable" $ColorWarning
+                return @{
+                    Type = "stable"
+                    Tag = ""
+                    Branch = "main"
+                }
+            }
+
+            Write-ColorOutput "✓ Selected: Specific Version $tagInput" $ColorSuccess
+            return @{
+                Type = "stable"
+                Tag = $tagInput
+                Branch = "main"
+            }
+        }
+        default {
+            Write-Host ""
+            if ($latestVersion -ne "Unknown") {
+                Write-ColorOutput "✓ Selected: Latest Stable Release ($latestVersion)" $ColorSuccess
+            } else {
+                Write-ColorOutput "✓ Selected: Latest Stable Release (auto-detect)" $ColorSuccess
+            }
+            return @{
+                Type = "stable"
+                Tag = ""
+                Branch = "main"
+            }
+        }
+    }
+}
+
 function Main {
     Show-Header
-    
+
     Write-ColorOutput "This will download and install Claude Code Workflow System from GitHub." $ColorInfo
     Write-Host ""
-    
+
     # Test prerequisites
     Write-ColorOutput "Checking system requirements..." $ColorInfo
     if (-not (Test-Prerequisites)) {
         Wait-ForUserConfirmation "System check failed! Press any key to exit..." -ExitAfter
     }
-    
+
+    # Get version choice from user (interactive menu)
+    $versionChoice = Get-UserVersionChoice
+    $script:Version = $versionChoice.Type
+    $script:Tag = $versionChoice.Tag
+    $script:Branch = $versionChoice.Branch
+
+    # Determine version information for display
+    $versionInfo = switch ($Version) {
+        "stable" {
+            if ($Tag) { "Stable release: $Tag" }
+            else { "Latest stable release (auto-detected)" }
+        }
+        "latest" { "Latest main branch (development)" }
+        "branch" { "Custom branch: $Branch" }
+    }
+
     # Confirm installation
     if (-not $NonInteractive -and -not $Force) {
         Write-Host ""
-        Write-ColorOutput "SECURITY NOTE:" $ColorWarning
-        Write-Host "- This script will download and execute Claude Code Workflow from GitHub"
-        Write-Host "- Repository: https://github.com/catlog22/Claude-Code-Workflow"  
-        Write-Host "- Branch: $Branch (latest stable version)"
+        Write-ColorOutput "INSTALLATION DETAILS:" $ColorInfo
+        Write-Host "- Repository: https://github.com/catlog22/Claude-Code-Workflow"
+        Write-Host "- Version: $versionInfo"
         Write-Host "- Features: Intelligent workflow orchestration with multi-agent coordination"
+        Write-Host ""
+        Write-ColorOutput "SECURITY NOTE:" $ColorWarning
+        Write-Host "- This script will download and execute code from GitHub"
         Write-Host "- Please ensure you trust this source"
         Write-Host ""
-        
+
         $choice = Read-Host "Continue with installation? (y/N)"
         if ($choice -notmatch '^[Yy]') {
             Write-ColorOutput "Installation cancelled" $ColorWarning
@@ -261,7 +545,7 @@ function Main {
     
     try {
         # Download repository
-        $zipPath = Download-Repository $tempDir $Branch
+        $zipPath = Download-Repository -TempDir $tempDir -Version $Version -Branch $Branch -Tag $Tag
         if (-not $zipPath) {
             throw "Download failed"
         }

install-remote.sh

@@ -6,9 +6,13 @@ set -e  # Exit on error
 
 # Script metadata
 SCRIPT_NAME="Claude Code Workflow (CCW) Remote Installer"
-VERSION="2.1.1"
+INSTALLER_VERSION="2.2.0"
 BRANCH="${BRANCH:-main}"
 
+# Version control
+VERSION_TYPE="${VERSION_TYPE:-stable}"  # stable, latest, branch
+TAG_VERSION=""
+
 # Colors for output
 COLOR_RESET='\033[0m'
 COLOR_SUCCESS='\033[0;32m'
@@ -32,7 +36,7 @@ function write_color() {
 }
 
 function show_header() {
-    write_color "==== $SCRIPT_NAME v$VERSION ====" "$COLOR_INFO"
+    write_color "==== $SCRIPT_NAME v$INSTALLER_VERSION ====" "$COLOR_INFO"
     write_color "========================================================" "$COLOR_INFO"
     echo ""
 }
@@ -72,17 +76,80 @@ function get_temp_directory() {
     echo "$temp_dir"
 }
 
+function get_latest_release() {
+    local api_url="https://api.github.com/repos/catlog22/Claude-Code-Workflow/releases/latest"
+
+    if command -v jq &> /dev/null; then
+        # Use jq if available
+        local tag
+        tag=$(curl -fsSL "$api_url" 2>/dev/null | jq -r '.tag_name' 2>/dev/null)
+        if [ -n "$tag" ] && [ "$tag" != "null" ]; then
+            echo "$tag"
+            return 0
+        fi
+    else
+        # Fallback: parse JSON with grep/sed
+        local tag
+        tag=$(curl -fsSL "$api_url" 2>/dev/null | grep -o '"tag_name":\s*"[^"]*"' | sed 's/"tag_name":\s*"\([^"]*\)"/\1/')
+        if [ -n "$tag" ]; then
+            echo "$tag"
+            return 0
+        fi
+    fi
+
+    write_color "WARNING: Failed to fetch latest release, using 'main' branch" "$COLOR_WARNING" >&2
+    return 1
+}
+
 function download_repository() {
     local temp_dir="$1"
-    local branch="${2:-main}"
+    local version_type="${2:-stable}"
+    local branch="${3:-main}"
+    local tag="${4:-}"
     local repo_url="https://github.com/catlog22/Claude-Code-Workflow"
-    local zip_url="${repo_url}/archive/refs/heads/${branch}.zip"
+    local zip_url=""
+    local download_type=""
+
+    # Determine download URL based on version type
+    case "$version_type" in
+        stable)
+            # Download latest stable release
+            if [ -z "$tag" ]; then
+                tag=$(get_latest_release)
+                if [ -z "$tag" ]; then
+                    # Fallback to main branch if API fails
+                    zip_url="${repo_url}/archive/refs/heads/main.zip"
+                    download_type="main branch (fallback)"
+                else
+                    zip_url="${repo_url}/archive/refs/tags/${tag}.zip"
+                    download_type="stable release $tag"
+                fi
+            else
+                zip_url="${repo_url}/archive/refs/tags/${tag}.zip"
+                download_type="stable release $tag"
+            fi
+            ;;
+        latest)
+            # Download latest main branch
+            zip_url="${repo_url}/archive/refs/heads/main.zip"
+            download_type="latest main branch"
+            ;;
+        branch)
+            # Download specific branch
+            zip_url="${repo_url}/archive/refs/heads/${branch}.zip"
+            download_type="branch $branch"
+            ;;
+        *)
+            write_color "ERROR: Invalid version type: $version_type" "$COLOR_ERROR" >&2
+            return 1
+            ;;
+    esac
+
     local zip_path="${temp_dir}/repo.zip"
 
     write_color "Downloading from GitHub..." "$COLOR_INFO" >&2
     write_color "Source: $repo_url" "$COLOR_INFO" >&2
-    write_color "Branch: $branch" "$COLOR_INFO" >&2
-    write_color "URL: $zip_url" "$COLOR_INFO" >&2
+    write_color "Type: $download_type" "$COLOR_INFO" >&2
 
     # Download with curl
     if curl -fsSL -o "$zip_path" "$zip_url" 2>&1 >&2; then
@@ -217,6 +284,23 @@ function wait_for_user() {
 function parse_arguments() {
     while [[ $# -gt 0 ]]; do
         case "$1" in
+            --version)
+                VERSION_TYPE="$2"
+                if [[ ! "$VERSION_TYPE" =~ ^(stable|latest|branch)$ ]]; then
+                    write_color "ERROR: Invalid version type: $VERSION_TYPE" "$COLOR_ERROR"
+                    write_color "Valid options: stable, latest, branch" "$COLOR_ERROR"
+                    exit 1
+                fi
+                shift 2
+                ;;
+            --tag)
+                TAG_VERSION="$2"
+                shift 2
+                ;;
+            --branch)
+                BRANCH="$2"
+                shift 2
+                ;;
             --global)
                 INSTALL_GLOBAL=true
                 shift
@@ -241,10 +325,6 @@ function parse_arguments() {
                 BACKUP_ALL=true
                 shift
                 ;;
-            --branch)
-                BRANCH="$2"
-                shift 2
-                ;;
             --help)
                 show_help
                 exit 0
@@ -260,33 +340,208 @@ function parse_arguments() {
 
 function show_help() {
     cat << EOF
-$SCRIPT_NAME v$VERSION
+$SCRIPT_NAME v$INSTALLER_VERSION
 
 Usage: $0 [OPTIONS]
 
-Options:
+Version Options:
+    --version TYPE        Version type: stable (default), latest, or branch
+    --tag TAG             Specific release tag (e.g., v3.2.0) - for stable version
+    --branch BRANCH       Branch name (default: main) - for branch version
+
+Installation Options:
     --global              Install to global user directory (~/.claude)
     --directory DIR       Install to custom directory
     --force               Force installation without prompts
     --no-backup           Skip backup creation
     --non-interactive     Non-interactive mode (no prompts)
     --backup-all          Backup all files before installation
-    --branch BRANCH       Specify GitHub branch (default: main)
     --help                Show this help message
 
 Examples:
-    # Interactive installation
+    # Install latest stable release (recommended)
     $0
 
+    # Install specific stable version
+    $0 --version stable --tag v3.2.0
+
+    # Install latest development version
+    $0 --version latest
+
+    # Install from specific branch
+    $0 --version branch --branch feature/new-feature
+
     # Global installation without prompts
     $0 --global --non-interactive
 
     # Custom directory installation
     $0 --directory /opt/claude-code-workflow
 
+Repository: https://github.com/catlog22/Claude-Code-Workflow
+
 EOF
 }
 
+function show_version_menu() {
+    local latest_version="$1"
+    local latest_date="$2"
+    local commit_id="$3"
+    local commit_date="$4"
+
+    echo ""
+    write_color "====================================================" "$COLOR_INFO"
+    write_color "            Version Selection Menu" "$COLOR_INFO"
+    write_color "====================================================" "$COLOR_INFO"
+    echo ""
+
+    # Option 1: Latest Stable
+    write_color "1) Latest Stable Release (Recommended)" "$COLOR_SUCCESS"
+    if [ -n "$latest_version" ] && [ "$latest_version" != "Unknown" ]; then
+        echo "   |-- Version: $latest_version"
+        if [ -n "$latest_date" ]; then
+            echo "   |-- Released: $latest_date"
+        fi
+        echo "   \-- Production-ready"
+    else
+        echo "   |-- Version: Auto-detected from GitHub"
+        echo "   \-- Production-ready"
+    fi
+    echo ""
+
+    # Option 2: Latest Development
+    write_color "2) Latest Development Version" "$COLOR_WARNING"
+    echo "   |-- Branch: main"
+    if [ -n "$commit_id" ] && [ -n "$commit_date" ]; then
+        echo "   |-- Commit: $commit_id"
+        echo "   |-- Updated: $commit_date"
+    fi
+    echo "   |-- Cutting-edge features"
+    echo "   \-- May contain experimental changes"
+    echo ""
+
+    # Option 3: Specific Version
+    write_color "3) Specific Release Version" "$COLOR_INFO"
+    echo "   |-- Install a specific tagged release"
+    echo "   \-- Recent: v3.2.0, v3.1.0, v3.0.1"
+    echo ""
+
+    write_color "====================================================" "$COLOR_INFO"
+    echo ""
+}
+
+function get_user_version_choice() {
+    if [ "$NON_INTERACTIVE" = true ] || [ "$FORCE" = true ]; then
+        # Non-interactive mode: use default stable version
+        echo "stable"
+        return 0
+    fi
+
+    # Detect latest stable version and commit info
+    write_color "Detecting latest release and commits..." "$COLOR_INFO"
+    local latest_version="Unknown"
+    local latest_date=""
+    local commit_id=""
+    local commit_date=""
+
+    # Get latest release info
+    local release_data
+    release_data=$(curl -fsSL --connect-timeout 5 "https://api.github.com/repos/catlog22/Claude-Code-Workflow/releases/latest" 2>/dev/null)
+
+    if [ -n "$release_data" ]; then
+        if command -v jq &> /dev/null; then
+            latest_version=$(echo "$release_data" | jq -r '.tag_name' 2>/dev/null)
+            local published_at=$(echo "$release_data" | jq -r '.published_at' 2>/dev/null)
+            if [ -n "$published_at" ] && [ "$published_at" != "null" ]; then
+                # Format: 2025-10-02T04:27:21Z -> 2025-10-02 04:27 UTC
+                latest_date=$(echo "$published_at" | sed 's/T/ /' | sed 's/Z/ UTC/' | cut -d'.' -f1)
+            fi
+        else
+            latest_version=$(echo "$release_data" | grep -o '"tag_name":\s*"[^"]*"' | sed 's/"tag_name":\s*"\([^"]*\)"/\1/')
+            local published_at=$(echo "$release_data" | grep -o '"published_at":\s*"[^"]*"' | sed 's/"published_at":\s*"\([^"]*\)"/\1/')
+            if [ -n "$published_at" ]; then
+                latest_date=$(echo "$published_at" | sed 's/T/ /' | sed 's/Z/ UTC/' | cut -d'.' -f1)
+            fi
+        fi
+    fi
+
+    if [ -n "$latest_version" ] && [ "$latest_version" != "null" ] && [ "$latest_version" != "Unknown" ]; then
+        write_color "Latest stable: $latest_version ($latest_date)" "$COLOR_SUCCESS"
+    else
+        latest_version="Unknown"
+        write_color "Could not detect latest release" "$COLOR_WARNING"
+    fi
+
+    # Get latest commit info
+    local commit_data
+    commit_data=$(curl -fsSL --connect-timeout 5 "https://api.github.com/repos/catlog22/Claude-Code-Workflow/commits/main" 2>/dev/null)
+
+    if [ -n "$commit_data" ]; then
+        if command -v jq &> /dev/null; then
+            commit_id=$(echo "$commit_data" | jq -r '.sha' 2>/dev/null | cut -c1-7)
+            local committer_date=$(echo "$commit_data" | jq -r '.commit.committer.date' 2>/dev/null)
+            if [ -n "$committer_date" ] && [ "$committer_date" != "null" ]; then
+                commit_date=$(echo "$committer_date" | sed 's/T/ /' | sed 's/Z/ UTC/' | cut -d'.' -f1)
+            fi
+        else
+            commit_id=$(echo "$commit_data" | grep -o '"sha":\s*"[^"]*"' | head -1 | sed 's/"sha":\s*"\([^"]*\)"/\1/' | cut -c1-7)
+            local committer_date=$(echo "$commit_data" | grep -o '"date":\s*"[^"]*"' | head -1 | sed 's/"date":\s*"\([^"]*\)"/\1/')
+            if [ -n "$committer_date" ]; then
+                commit_date=$(echo "$committer_date" | sed 's/T/ /' | sed 's/Z/ UTC/' | cut -d'.' -f1)
+            fi
+        fi
+    fi
+
+    if [ -n "$commit_id" ] && [ -n "$commit_date" ]; then
+        write_color "Latest commit: $commit_id ($commit_date)" "$COLOR_SUCCESS"
+    else
+        write_color "Could not detect latest commit" "$COLOR_WARNING"
+    fi
+
+    show_version_menu "$latest_version" "$latest_date" "$commit_id" "$commit_date"
+
+    read -p "Select version to install (1-3, default: 1): " choice
+
+    case "$choice" in
+        2)
+            echo ""
+            write_color "✓ Selected: Latest Development Version (main branch)" "$COLOR_SUCCESS"
+            VERSION_TYPE="latest"
+            TAG_VERSION=""
+            BRANCH="main"
+            ;;
+        3)
+            echo ""
+            write_color "Available recent releases:" "$COLOR_INFO"
+            echo "  v3.2.0, v3.1.0, v3.0.1, v3.0.0"
+            echo ""
+            read -p "Enter version tag (e.g., v3.2.0): " tag_input
+
+            if [ -z "$tag_input" ]; then
+                write_color "⚠ No tag specified, using latest stable" "$COLOR_WARNING"
+                VERSION_TYPE="stable"
+                TAG_VERSION=""
+            else
+                echo ""
+                write_color "✓ Selected: Specific Version $tag_input" "$COLOR_SUCCESS"
+                VERSION_TYPE="stable"
+                TAG_VERSION="$tag_input"
+            fi
+            BRANCH="main"
+            ;;
+        *)
+            echo ""
+            if [ "$latest_version" != "Unknown" ]; then
+                write_color "✓ Selected: Latest Stable Release ($latest_version)" "$COLOR_SUCCESS"
+            else
+                write_color "✓ Selected: Latest Stable Release (auto-detect)" "$COLOR_SUCCESS"
+            fi
+            VERSION_TYPE="stable"
+            TAG_VERSION=""
+            BRANCH="main"
+            ;;
+    esac
+}
+
 function main() {
     show_header
 
@@ -300,14 +555,37 @@ function main() {
         exit 1
     fi
 
+    # Get version choice from user (interactive menu)
+    get_user_version_choice
+
+    # Determine version information for display
+    local version_info=""
+    case "$VERSION_TYPE" in
+        stable)
+            if [ -n "$TAG_VERSION" ]; then
+                version_info="Stable release: $TAG_VERSION"
+            else
+                version_info="Latest stable release (auto-detected)"
+            fi
+            ;;
+        latest)
+            version_info="Latest main branch (development)"
+            ;;
+        branch)
+            version_info="Custom branch: $BRANCH"
+            ;;
+    esac
+
     # Confirm installation
     if [ "$NON_INTERACTIVE" != true ] && [ "$FORCE" != true ]; then
         echo ""
-        write_color "SECURITY NOTE:" "$COLOR_WARNING"
-        echo "- This script will download and execute Claude Code Workflow from GitHub"
+        write_color "INSTALLATION DETAILS:" "$COLOR_INFO"
         echo "- Repository: https://github.com/catlog22/Claude-Code-Workflow"
-        echo "- Branch: $BRANCH (latest stable version)"
+        echo "- Version: $version_info"
         echo "- Features: Intelligent workflow orchestration with multi-agent coordination"
+        echo ""
+        write_color "SECURITY NOTE:" "$COLOR_WARNING"
+        echo "- This script will download and execute code from GitHub"
         echo "- Please ensure you trust this source"
         echo ""
 
@@ -328,7 +606,7 @@ function main() {
     # Download repository
     local zip_path
     write_color "Starting download process..." "$COLOR_INFO"
-    zip_path=$(download_repository "$temp_dir" "$BRANCH")
+    zip_path=$(download_repository "$temp_dir" "$VERSION_TYPE" "$BRANCH" "$TAG_VERSION")
     local download_status=$?
 
     if [ $download_status -eq 0 ] && [ -n "$zip_path" ] && [ -f "$zip_path" ]; then