release: version v3.4.2 - CLI documentation refactoring

Updated documentation for v3.4.2 release focusing on CLI command
documentation refactoring and single source of truth pattern.

## Changes

**CHANGELOG.md**:
- Added comprehensive v3.4.2 release notes
- Documented 681 lines reduction across 7 CLI command files
- Detailed removed duplicate sections and preserved unique content
- Explained single source of truth pattern with intelligent-tools-strategy.md

**README.md & README_CN.md**:
- Updated version badge from v3.4.0 to v3.4.2
- Updated "What's New" section with v3.4.2 highlights
- Documented CLI documentation refactoring benefits

## Release Summary

v3.4.2 focuses on documentation quality and maintenance optimization:
- Eliminated redundant documentation content
- Established implicit reference pattern to strategy guide
- Preserved all unique command-specific capabilities
- Reduced maintenance overhead for future updates

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

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

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

@@ -13,7 +13,6 @@ description: |
     user: "Create implementation plan for: real-time notifications system"
     assistant: "I'll create a staged implementation plan using provided context"
     commentary: Agent executes planning based on provided requirements and context
-model: sonnet
 color: yellow
 ---
 

.claude/agents/code-developer.md

@@ -13,7 +13,6 @@ description: |
     user: "Add user authentication"
     assistant: "I need to analyze the codebase first to understand the patterns"
     commentary: Use Gemini to gather implementation context, then execute
-model: sonnet
 color: blue
 ---
 

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

@@ -20,7 +20,6 @@ description: |
     auto.md: Assigns dedicated agent with ASSIGNED_ROLE: ui-designer
     agent: "I'll execute ui-designer analysis for this topic, creating UX-focused conceptual analysis in .brainstorming/ui-designer/ directory"
 
-model: sonnet
 color: purple
 ---
 

.claude/agents/doc-generator.md

@@ -22,7 +22,6 @@ description: |
   </commentary>
   </example>
 
-model: sonnet
 color: green
 ---
 

.claude/agents/general-purpose.md

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

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

@@ -1,82 +1,88 @@
 ---
 name: memory-gemini-bridge
 description: Execute complex project documentation updates using script coordination
-model: haiku
 color: purple
 ---
 
-You are a documentation update coordinator for complex projects. Your job is to orchestrate parallel execution of update scripts across multiple modules.
+You are a documentation update coordinator for complex projects. Orchestrate parallel CLAUDE.md updates efficiently and track every module.
 
-## Core Responsibility
+## Core Mission
 
-Coordinate parallel execution of `~/.claude/scripts/update_module_claude.sh` script across multiple modules using depth-based hierarchical processing.
+Execute depth-parallel updates for all modules using `~/.claude/scripts/update_module_claude.sh`. **Every module path must be processed**.
 
-## Execution Protocol
+## Input Context
 
-### 1. Analyze Project Structure
+You will receive:
+```
+- Total modules: [count]
+- Tool: [gemini|qwen|codex]
+- Mode: [full|related]
+- Module list (depth|path|files|types|has_claude format)
+```
+
+## Execution Steps
+
+**MANDATORY: Use TodoWrite to track all modules before execution**
+
+### Step 1: Create Task List
 ```bash
-# Step 1: Code Index architecture analysis
-mcp__code-index__search_code_advanced(pattern="class|function|interface", file_pattern="**/*.{ts,js,py}")
-mcp__code-index__find_files(pattern="**/*.{md,json,yaml,yml}")
-
-# Step 2: Get module list with depth information
-modules=$(Bash(~/.claude/scripts/get_modules_by_depth.sh list))
-count=$(echo "$modules" | wc -l)
-
-# Step 3: Display project structure
-Bash(~/.claude/scripts/get_modules_by_depth.sh grouped)
+# Parse module list and create todo items
+TodoWrite([
+  {content: "Process depth 5 modules (N modules)", status: "pending", activeForm: "Processing depth 5 modules"},
+  {content: "Process depth 4 modules (N modules)", status: "pending", activeForm: "Processing depth 4 modules"},
+  # ... for each depth level
+  {content: "Safety check: verify only CLAUDE.md modified", status: "pending", activeForm: "Running safety check"}
+])
 ```
 
-### 2. Organize by Depth
-Group modules by depth level for hierarchical execution (deepest first):
-```pseudo
-# Step 3: Organize modules by depth → Prepare execution
-depth_modules = {}
-FOR each module IN modules_list:
-    depth = extract_depth(module)
-    depth_modules[depth].add(module)
+### Step 2: Execute by Depth (Deepest First)
+```bash
+# For each depth level (5 → 0):
+# 1. Mark depth task as in_progress
+# 2. Extract module paths for current depth
+# 3. Launch parallel jobs (max 4)
+
+# Depth 5 example:
+~/.claude/scripts/update_module_claude.sh "./.claude/workflows/cli-templates/prompts/analysis" "full" "gemini" &
+~/.claude/scripts/update_module_claude.sh "./.claude/workflows/cli-templates/prompts/development" "full" "gemini" &
+# ... up to 4 concurrent jobs
+
+# 4. Wait for all depth jobs to complete
+wait
+
+# 5. Mark depth task as completed
+# 6. Move to next depth
 ```
 
-### 3. Execute Updates
-For each depth level, run parallel updates:
-```pseudo
-# Step 4: Execute depth-parallel updates → Process by depth
-FOR depth FROM max_depth DOWN TO 0:
-    FOR each module IN depth_modules[depth]:
-        WHILE active_jobs >= 4: wait(0.1)
-        Bash(~/.claude/scripts/update_module_claude.sh "$module" "$mode" &)
-    wait_all_jobs()
+### Step 3: Safety Check
+```bash
+# After all depths complete:
+git diff --cached --name-only | grep -v "CLAUDE.md" || echo "✅ Safe"
+git status --short
 ```
 
-### 4. Execution Rules
+## Tool Parameter Flow
 
-- **Core Command**: `Bash(~/.claude/scripts/update_module_claude.sh "$module" "$mode" &)`
-- **Concurrency Control**: Maximum 4 parallel jobs per depth level
-- **Execution Order**: Process depths sequentially, deepest first
-- **Job Control**: Monitor active jobs before spawning new ones
-- **Independence**: Each module update is independent within the same depth
+**Command Format**: `update_module_claude.sh <path> <mode> <tool>`
 
-### 5. Update Modes
+Examples:
+- Gemini: `update_module_claude.sh "./.claude/agents" "full" "gemini" &`
+- Qwen: `update_module_claude.sh "./src/api" "full" "qwen" &`
+- Codex: `update_module_claude.sh "./tests" "full" "codex" &`
 
-- **"full"** mode: Complete refresh → `Bash(update_module_claude.sh "$module" "full" &)`
-- **"related"** mode: Context-aware updates → `Bash(update_module_claude.sh "$module" "related" &)`
+## Execution Rules
 
-### 6. Agent Protocol
+1. **Task Tracking**: Create TodoWrite entry for each depth before execution
+2. **Parallelism**: Max 4 jobs per depth, sequential across depths
+3. **Tool Passing**: Always pass tool parameter as 3rd argument
+4. **Path Accuracy**: Extract exact path from `depth:N|path:X|...` format
+5. **Completion**: Mark todo completed only after all depth jobs finish
+6. **No Skipping**: Process every module from input list
 
-```pseudo
-# Agent Coordination Flow:
-RECEIVE task_with(module_count, update_mode)
-modules = Bash(get_modules_by_depth.sh list) 
-Bash(get_modules_by_depth.sh grouped)
-depth_modules = organize_by_depth(modules)
+## Concise Output
 
-FOR depth FROM max_depth DOWN TO 0:
-    FOR module IN depth_modules[depth]:
-        WHILE active_jobs >= 4: wait(0.1)
-        Bash(update_module_claude.sh module update_mode &)
-    wait_all_jobs()
+- Start: "Processing [count] modules with [tool]"
+- Progress: Update TodoWrite for each depth
+- End: "✅ Updated [count] CLAUDE.md files" + git status
 
-REPORT final_status()
-```
-
-This agent coordinates the same `Bash()` commands used in direct execution, providing intelligent orchestration for complex projects.
+**Do not explain, just execute efficiently.**

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

@@ -18,7 +18,6 @@ description: |
     user: "Run the full test suite and ensure everything passes"
     assistant: "I'll use the test-fix-agent to execute all tests and fix any issues found"
     commentary: test-fix-agent serves as the quality gate - passing tests = approved code.
-model: sonnet
 color: green
 ---
 

.claude/commands/cli/analyze.md

@@ -14,71 +14,47 @@ allowed-tools: SlashCommand(*), Bash(*), TodoWrite(*), Read(*), Glob(*)
 
 ## Purpose
 
-Execute CLI tool analysis on codebase patterns, architecture, or code quality.
+Quick codebase analysis using CLI tools. Automatically detects analysis type and selects appropriate template.
 
 **Supported Tools**: codex, gemini (default), qwen
-**Reference**: @~/.claude/workflows/intelligent-tools-strategy.md for complete tool details
+
+## Parameters
+
+- `--tool <codex|gemini|qwen>` - Tool selection (default: gemini)
+- `--enhance` - Use `/enhance-prompt` for context-aware enhancement
+- `<analysis-target>` - Description of what to analyze
 
 ## Execution Flow
 
 1. Parse tool selection (default: gemini)
-2. If `--enhance`: Execute `/enhance-prompt` first
-3. Detect analysis type and select template
-4. Build and execute command
-5. Return results
+2. If `--enhance`: Execute `/enhance-prompt` first to expand user intent
+3. Auto-detect analysis type from keywords → select template
+4. Build command with auto-detected file patterns
+5. Execute and return results
 
-## Enhancement Integration
+## File Pattern Auto-Detection
 
-**When `--enhance` flag present**: Execute `/enhance-prompt "[analysis-target]"` first, then use enhanced output (INTENT/CONTEXT/ACTION) to build the analysis command.
+Keywords trigger specific file patterns:
+- "auth" → `@{**/*auth*,**/*user*}`
+- "component" → `@{src/components/**/*,**/*.component.*}`
+- "API" → `@{**/api/**/*,**/routes/**/*}`
+- "test" → `@{**/*.test.*,**/*.spec.*}`
+- "config" → `@{*.config.*,**/config/**/*}`
+- Generic → `@{src/**/*}`
 
-
-## Command Template
-
-**Gemini/Qwen**:
-```bash
-cd [dir] && ~/.claude/scripts/[gemini|qwen]-wrapper -p "
-PURPOSE: [analysis goal]
-TASK: [specific task]
-CONTEXT: @{[file-patterns]} @{CLAUDE.md}
-EXPECTED: [output format]
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/[category]/[template].txt) | [constraints]
-"
-```
-
-**Codex**:
-```bash
-codex -C [dir] --full-auto exec "
-PURPOSE: [analysis goal]
-TASK: [specific task]
-CONTEXT: @{[file-patterns]} @{CLAUDE.md}
-EXPECTED: [output format]
-RULES: [constraints]
-" --skip-git-repo-check -s danger-full-access
-
-# With image attachment (e.g., UI screenshots, diagrams)
-codex -C [dir] -i screenshot.png --full-auto exec "..." --skip-git-repo-check -s danger-full-access
-```
+For complex patterns, use `rg` or MCP tools to discover files first, then execute CLI with precise file references.
 
 ## Examples
 
 ```bash
-/cli:analyze "authentication patterns"              # Gemini (default)
-/cli:analyze --tool qwen "component architecture"   # Qwen architecture
+/cli:analyze "authentication patterns"              # Auto: gemini + auth patterns
+/cli:analyze --tool qwen "component architecture"   # Qwen architecture analysis
 /cli:analyze --tool codex "performance bottlenecks" # Codex deep analysis
-/cli:analyze --enhance "fix auth issues"            # Enhanced prompt first
+/cli:analyze --enhance "fix auth issues"            # Enhanced prompt → analysis
 ```
 
-## File Pattern Logic
-
-Auto-detect file patterns from keywords:
-- "auth" → `@{**/*auth*}`
-- "component" → `@{src/components/**/*}`
-- "API" → `@{**/api/**/*}`
-- "test" → `@{**/*.test.*}`
-- Generic → `@{src/**/*}`
-
-## Session Integration
-
-- **Active Session**: Save results to `.workflow/WFS-[id]/.chat/analysis-[timestamp].md`
-- **No Session**: Return results directly to user
+## Notes
 
+- Command templates, file patterns, and best practices: see intelligent-tools-strategy.md (loaded in memory)
+- Active workflow session: results saved to `.workflow/WFS-[id]/.chat/`
+- No session: results returned directly

.claude/commands/cli/chat.md

@@ -1,6 +1,5 @@
 ---
 name: chat
-
 description: Simple CLI interaction command for direct codebase analysis
 usage: /cli:chat [--tool <codex|gemini|qwen>] [--enhance] "inquiry"
 argument-hint: "[--tool codex|gemini|qwen] [--enhance] inquiry"
@@ -9,72 +8,41 @@ examples:
   - /cli:chat --tool qwen --enhance "optimize React component"
   - /cli:chat --tool codex "review security vulnerabilities"
 allowed-tools: SlashCommand(*), Bash(*)
-model: sonnet
 ---
 
+# CLI Chat Command (/cli:chat)
+
 ## Purpose
 
-Direct interaction with CLI tools for codebase analysis and Q&A.
+Direct Q&A interaction with CLI tools for codebase analysis.
 
 **Supported Tools**: codex, gemini (default), qwen
-**Reference**: @~/.claude/workflows/intelligent-tools-strategy.md for complete tool details
 
 ## Parameters
 
-- `<inquiry>` (Required): Question or analysis request
-- `--tool <codex|gemini|qwen>` (Optional): Select CLI tool (default: gemini)
-- `--enhance` (Optional): Enhance inquiry with `/enhance-prompt` first
-- `--all-files` (Optional): Include entire codebase in context
-- `--save-session` (Optional): Save interaction to workflow session
+- `<inquiry>` (Required) - Question or analysis request
+- `--tool <codex|gemini|qwen>` - Select CLI tool (default: gemini)
+- `--enhance` - Enhance inquiry with `/enhance-prompt` first
+- `--all-files` - Include entire codebase in context
+- `--save-session` - Save interaction to workflow session
 
 ## Execution Flow
 
 1. Parse tool selection (default: gemini)
-2. If `--enhance`: Execute `/enhance-prompt` first
-3. Assemble context (files + CLAUDE.md)
-4. Execute CLI tool
-5. Optional: Save to session
-
-## Enhancement Integration
-
-**When `--enhance` flag present**: Execute `/enhance-prompt "[inquiry]"` first, then use enhanced output (INTENT/CONTEXT/ACTION) to build the chat command.
+2. If `--enhance`: Execute `/enhance-prompt` to expand user intent
+3. Assemble context: `@{CLAUDE.md}` + user-specified files or `--all-files`
+4. Execute CLI tool with assembled context
+5. Optionally save to workflow session
 
 ## Context Assembly
 
-Context gathered from:
-1. **Project Guidelines**: `@{CLAUDE.md,**/*CLAUDE.md}` (always)
-2. **User-Explicit Files**: Files specified by user
-3. **All Files Flag**: `--all-files` includes entire codebase
+**Always included**: `@{CLAUDE.md,**/*CLAUDE.md}` (project guidelines)
 
-## Command Template
+**Optional**:
+- User-explicit files from inquiry keywords
+- `--all-files` flag includes entire codebase (`--all-files` wrapper parameter)
 
-**Gemini/Qwen**:
-```bash
-cd [dir] && ~/.claude/scripts/[gemini|qwen]-wrapper -p "
-PURPOSE: [inquiry goal]
-TASK: [specific question]
-CONTEXT: @{CLAUDE.md} @{target_files}
-EXPECTED: [response format]
-RULES: [constraints]
-"
-
-# With --all-files
-cd [dir] && ~/.claude/scripts/[gemini|qwen]-wrapper --all-files -p "..."
-```
-
-**Codex**:
-```bash
-codex -C [dir] --full-auto exec "
-PURPOSE: [inquiry goal]
-TASK: [specific question]
-CONTEXT: @{CLAUDE.md} @{target_files}
-EXPECTED: [response format]
-RULES: [constraints]
-" --skip-git-repo-check -s danger-full-access
-
-# With image attachment
-codex -C [dir] -i screenshot.png --full-auto exec "..." --skip-git-repo-check -s danger-full-access
-```
+For targeted analysis, use `rg` or MCP tools to discover relevant files first, then build precise CONTEXT field.
 
 ## Examples
 
@@ -82,11 +50,12 @@ codex -C [dir] -i screenshot.png --full-auto exec "..." --skip-git-repo-check -s
 /cli:chat "analyze the authentication flow"              # Gemini (default)
 /cli:chat --tool qwen "optimize React component"         # Qwen
 /cli:chat --tool codex "review security vulnerabilities" # Codex
-/cli:chat --enhance "fix the login"                      # Enhanced prompt
-/cli:chat --all-files "find all API endpoints"           # Full codebase
+/cli:chat --enhance "fix the login"                      # Enhanced prompt first
+/cli:chat --all-files "find all API endpoints"           # Full codebase context
 ```
 
-## Session Persistence
+## Notes
 
-- **Active Session**: Save to `.workflow/WFS-[id]/.chat/chat-[timestamp].md`
-- **No Session**: Return results directly
+- Command templates and file patterns: see intelligent-tools-strategy.md (loaded in memory)
+- Active workflow session: results saved to `.workflow/WFS-[id]/.chat/`
+- No session: results returned directly

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

@@ -17,18 +17,23 @@ allowed-tools: SlashCommand(*), Bash(*), TodoWrite(*), Read(*), Glob(*)
 Automated task decomposition and sequential execution with Codex, using `codex exec "..." resume --last` mechanism for continuity between subtasks.
 
 **Input**: User description or task ID (automatically loads from `.task/[ID].json` if applicable)
-**Reference**: @~/.claude/workflows/intelligent-tools-strategy.md for Codex details
 
 ## Core Workflow
 
 ```
-Task Input → Decompose into Subtasks → TodoWrite Tracking →
-For Each Subtask:
-  0. Stage existing changes (git add -A) if valid git repo
-  1. Execute with Codex
-  2. [Optional] Git verification
-  3. Mark complete in TodoWrite
-  4. Resume next subtask with `codex resume --last`
+Task Input → Analyze Dependencies → Create Task Flow Diagram →
+Decompose into Subtask Groups → TodoWrite Tracking →
+For Each Subtask Group:
+  For First Subtask in Group:
+    0. Stage existing changes (git add -A) if valid git repo
+    1. Execute with Codex (new session)
+    2. [Optional] Git verification
+    3. Mark complete in TodoWrite
+  For Related Subtasks in Same Group:
+    0. Stage changes from previous subtask
+    1. Execute with `codex exec "..." resume --last` (continue session)
+    2. [Optional] Git verification
+    3. Mark complete in TodoWrite
 → Final Summary
 ```
 
@@ -41,17 +46,49 @@ For Each Subtask:
 
 ## Execution Flow
 
-### Phase 1: Input Processing & Decomposition
+### Phase 1: Input Processing & Task Flow Analysis
 
 1. **Parse Input**:
    - Check if input matches task ID pattern (e.g., `IMPL-001`, `TASK-123`)
    - If yes: Load from `.task/[ID].json` and extract requirements
    - If no: Use input as task description directly
 
-2. **Analyze & Decompose**:
+2. **Analyze Dependencies & Create Task Flow Diagram**:
    - Analyze task complexity and scope
-   - Break down into 3-8 subtasks
-   - Create TodoWrite tracker with all subtasks
+   - Identify dependencies and relationships between subtasks
+   - Create visual task flow diagram showing:
+     - Independent task groups (parallel execution possible)
+     - Sequential dependencies (must use resume)
+     - Branching logic (conditional paths)
+   - Display flow diagram for user review
+
+**Task Flow Diagram Format**:
+```
+[Group A: Auth Core]
+  A1: Create user model ──┐
+  A2: Add validation     ─┤─► [resume] ─► A3: Database schema
+                          │
+[Group B: API Layer]      │
+  B1: Auth endpoints ─────┘─► [new session]
+  B2: Middleware ────────────► [resume] ─► B3: Error handling
+
+[Group C: Testing]
+  C1: Unit tests ─────────────► [new session]
+  C2: Integration tests ──────► [resume]
+```
+
+**Diagram Symbols**:
+- `──►` Sequential dependency (must resume previous session)
+- `─┐` Branch point (multiple paths)
+- `─┘` Merge point (wait for completion)
+- `[resume]` Use `codex exec "..." resume --last`
+- `[new session]` Start fresh Codex session
+
+3. **Decompose into Subtask Groups**:
+   - Group related subtasks that share context
+   - Break down into 3-8 subtasks total
+   - Assign each subtask to a group
+   - Create TodoWrite tracker with groups
    - Display decomposition for user review
 
 **Decomposition Criteria**:
@@ -59,8 +96,30 @@ For Each Subtask:
 - Clear, testable outcomes
 - Explicit dependencies
 - Focused file scope (1-5 files per subtask)
+- **Group coherence**: Subtasks in same group share context/files
 
-### Phase 2: Sequential Execution
+### File Discovery for Task Decomposition
+
+Use `rg` or MCP tools to discover relevant files, then group by domain:
+
+**Workflow**: Discover → Analyze scope → Group by files → Create task flow
+
+**Example**:
+```bash
+# Discover files
+rg "authentication" --files-with-matches --type ts
+
+# Group by domain
+# Group A: src/auth/model.ts, src/auth/schema.ts
+# Group B: src/api/auth.ts, src/middleware/auth.ts
+# Group C: tests/auth/*.test.ts
+
+# Each group becomes a session with related subtasks
+```
+
+File patterns: see intelligent-tools-strategy.md (loaded in memory)
+
+### Phase 2: Group-Based Execution
 
 **Pre-Execution Git Staging** (if valid git repository):
 ```bash
@@ -70,37 +129,61 @@ git add -A
 git status --short
 ```
 
-**For First Subtask**:
+**For First Subtask in Each Group** (New Session):
 ```bash
-# Initial execution (no resume needed)
+# Start new Codex session for independent task group
 codex -C [dir] --full-auto exec "
-PURPOSE: [task goal]
-TASK: [subtask 1 description]
+PURPOSE: [group goal]
+TASK: [subtask description - first in group]
 CONTEXT: @{relevant_files} @{CLAUDE.md}
 EXPECTED: [specific deliverables]
 RULES: [constraints]
-Subtask 1 of N: [subtask title]
+Group [X]: [group name] - Subtask 1 of N in this group
 " --skip-git-repo-check -s danger-full-access
 ```
 
-**For Subsequent Subtasks** (using resume --last):
+**For Related Subtasks in Same Group** (Resume Session):
 ```bash
 # Stage changes from previous subtask (if valid git repository)
 git add -A
 
-# Resume previous session for context continuity
+# Resume session ONLY for subtasks in same group
 codex exec "
-CONTINUE TO NEXT SUBTASK:
-Subtask N of M: [subtask title]
+CONTINUE IN SAME GROUP:
+Group [X]: [group name] - Subtask N of M
 
-PURPOSE: [continuation goal]
+PURPOSE: [continuation goal within group]
 TASK: [subtask N description]
-CONTEXT: Previous work completed, now focus on @{new_relevant_files}
+CONTEXT: Previous work in this group completed, now focus on @{new_relevant_files}
 EXPECTED: [specific deliverables]
-RULES: Build on previous subtask, maintain consistency
+RULES: Build on previous subtask in group, maintain consistency
 " resume --last --skip-git-repo-check -s danger-full-access
 ```
 
+**For First Subtask in Different Group** (New Session):
+```bash
+# Stage changes from previous group
+git add -A
+
+# Start NEW session for different group (no resume)
+codex -C [dir] --full-auto exec "
+PURPOSE: [new group goal]
+TASK: [subtask description - first in new group]
+CONTEXT: @{different_files} @{CLAUDE.md}
+EXPECTED: [specific deliverables]
+RULES: [constraints]
+Group [Y]: [new group name] - Subtask 1 of N in this group
+" --skip-git-repo-check -s danger-full-access
+```
+
+**Resume Decision Logic**:
+```
+if (subtask.group == previous_subtask.group):
+    use `codex exec "..." resume --last`  # Continue session
+else:
+    use `codex -C [dir] exec "..."`       # New session
+```
+
 ### Phase 3: Verification (if --verify-git enabled)
 
 After each subtask completion:
@@ -121,16 +204,26 @@ git ls-files --others --exclude-standard
 - No merge conflicts or errors
 - Code compiles/runs (if applicable)
 
-### Phase 4: TodoWrite Tracking
+### Phase 4: TodoWrite Tracking with Groups
 
-**Initial Setup**:
+**Initial Setup with Task Flow**:
 ```javascript
 TodoWrite({
   todos: [
-    { content: "Subtask 1: [description]", status: "in_progress", activeForm: "Executing subtask 1" },
-    { content: "Subtask 2: [description]", status: "pending", activeForm: "Executing subtask 2" },
-    { content: "Subtask 3: [description]", status: "pending", activeForm: "Executing subtask 3" },
-    // ... more subtasks
+    // Display task flow diagram first
+    { content: "Task Flow Analysis Complete - See diagram above", status: "completed", activeForm: "Analyzing task flow" },
+
+    // Group A subtasks (will use resume within group)
+    { content: "[Group A] Subtask 1: [description]", status: "in_progress", activeForm: "Executing Group A subtask 1" },
+    { content: "[Group A] Subtask 2: [description] [resume]", status: "pending", activeForm: "Executing Group A subtask 2" },
+
+    // Group B subtasks (new session, then resume within group)
+    { content: "[Group B] Subtask 1: [description] [new session]", status: "pending", activeForm: "Executing Group B subtask 1" },
+    { content: "[Group B] Subtask 2: [description] [resume]", status: "pending", activeForm: "Executing Group B subtask 2" },
+
+    // Group C subtasks (new session)
+    { content: "[Group C] Subtask 1: [description] [new session]", status: "pending", activeForm: "Executing Group C subtask 1" },
+
     { content: "Final verification and summary", status: "pending", activeForm: "Verifying and summarizing" }
   ]
 })
@@ -140,8 +233,9 @@ TodoWrite({
 ```javascript
 TodoWrite({
   todos: [
-    { content: "Subtask 1: [description]", status: "completed", activeForm: "Executing subtask 1" },
-    { content: "Subtask 2: [description]", status: "in_progress", activeForm: "Executing subtask 2" },
+    { content: "Task Flow Analysis Complete - See diagram above", status: "completed", activeForm: "Analyzing task flow" },
+    { content: "[Group A] Subtask 1: [description]", status: "completed", activeForm: "Executing Group A subtask 1" },
+    { content: "[Group A] Subtask 2: [description] [resume]", status: "in_progress", activeForm: "Executing Group A subtask 2" },
     // ... update status
   ]
 })
@@ -149,18 +243,36 @@ TodoWrite({
 
 ## Codex Resume Mechanism
 
-**Why `codex resume --last`?**
-- Maintains conversation context across subtasks
-- Codex remembers previous decisions and patterns
-- Reduces context repetition
-- Ensures consistency in implementation style
+**Why Group-Based Resume?**
+- **Within Group**: Maintains conversation context for related subtasks
+  - Codex remembers previous decisions and patterns
+  - Reduces context repetition
+  - Ensures consistency in implementation style
+- **Between Groups**: Fresh session for independent tasks
+  - Avoids context pollution from unrelated work
+  - Prevents confusion when switching domains
+  - Maintains focused attention on current group
 
 **How It Works**:
-1. First subtask creates new Codex session
-2. After completion, session is saved
-3. Subsequent subtasks use `codex resume --last` to continue
-4. Each subtask builds on previous context
-5. Final subtask completes full task
+1. **First subtask in Group A**: Creates new Codex session
+2. **Subsequent subtasks in Group A**: Use `codex resume --last` to continue session
+3. **First subtask in Group B**: Creates NEW Codex session (no resume)
+4. **Subsequent subtasks in Group B**: Use `codex resume --last` within Group B
+5. Each group builds on its own context, isolated from other groups
+
+**When to Resume vs New Session**:
+```
+✅ RESUME (same group):
+  - Subtasks share files/modules
+  - Logical continuation of previous work
+  - Same architectural domain
+
+❌ NEW SESSION (different group):
+  - Independent task area
+  - Different files/modules
+  - Switching architectural domains
+  - Testing after implementation
+```
 
 **Image Support**:
 ```bash
@@ -199,25 +311,47 @@ codex exec "CONTINUE TO NEXT SUBTASK: ..." resume --last --skip-git-repo-check -
 
 **During Execution**:
 ```
-📋 Task Decomposition:
-  1. [Subtask 1 description]
-  2. [Subtask 2 description]
-  ...
+📊 Task Flow Diagram:
+[Group A: Auth Core]
+  A1: Create user model ──┐
+  A2: Add validation     ─┤─► [resume] ─► A3: Database schema
+                          │
+[Group B: API Layer]      │
+  B1: Auth endpoints ─────┘─► [new session]
+  B2: Middleware ────────────► [resume] ─► B3: Error handling
 
-▶️  Executing Subtask 1/N: [title]
-  Codex session started...
+[Group C: Testing]
+  C1: Unit tests ─────────────► [new session]
+  C2: Integration tests ──────► [resume]
+
+📋 Task Decomposition:
+  [Group A] 1. Create user model
+  [Group A] 2. Add validation logic [resume]
+  [Group A] 3. Implement database schema [resume]
+  [Group B] 4. Create auth endpoints [new session]
+  [Group B] 5. Add middleware [resume]
+  [Group B] 6. Error handling [resume]
+  [Group C] 7. Unit tests [new session]
+  [Group C] 8. Integration tests [resume]
+
+▶️  [Group A] Executing Subtask 1/8: Create user model
+  Starting new Codex session for Group A...
   [Codex output]
   ✅ Subtask 1 completed
 
 🔍 Git Verification:
-  M  src/file1.ts
-  A  src/file2.ts
+  M  src/models/user.ts
   ✅ Changes verified
 
-▶️  Executing Subtask 2/N: [title]
-  Resuming Codex session...
+▶️  [Group A] Executing Subtask 2/8: Add validation logic
+  Resuming Codex session (same group)...
   [Codex output]
   ✅ Subtask 2 completed
+
+▶️  [Group B] Executing Subtask 4/8: Create auth endpoints
+  Starting NEW Codex session for Group B...
+  [Codex output]
+  ✅ Subtask 4 completed
 ...
 
 ✅ All Subtasks Completed
@@ -248,16 +382,30 @@ codex exec "CONTINUE TO NEXT SUBTASK: ..." resume --last --skip-git-repo-check -
 
 ## Examples
 
-**Example 1: Simple Task**
+**Example 1: Simple Task with Groups**
 ```bash
 /cli:codex-execute "implement user authentication system"
 
-# Decomposes into:
-# 1. Create user model and database schema
-# 2. Implement JWT token generation
-# 3. Create authentication middleware
-# 4. Add login/logout endpoints
-# 5. Write tests for auth flow
+# Task Flow Diagram:
+# [Group A: Data Layer]
+#   A1: Create user model ──► [resume] ──► A2: Database schema
+#
+# [Group B: Auth Logic]
+#   B1: JWT token generation ──► [new session]
+#   B2: Authentication middleware ──► [resume]
+#
+# [Group C: API Endpoints]
+#   C1: Login/logout endpoints ──► [new session]
+#
+# [Group D: Testing]
+#   D1: Unit tests ──► [new session]
+#   D2: Integration tests ──► [resume]
+
+# Execution:
+# Group A: A1 (new) → A2 (resume)
+# Group B: B1 (new) → B2 (resume)
+# Group C: C1 (new)
+# Group D: D1 (new) → D2 (resume)
 ```
 
 **Example 2: With Git Verification**
@@ -280,13 +428,16 @@ codex exec "CONTINUE TO NEXT SUBTASK: ..." resume --last --skip-git-repo-check -
 
 ## Best Practices
 
-1. **Subtask Granularity**: Keep subtasks small and focused
-2. **Clear Boundaries**: Each subtask should have well-defined input/output
-3. **Git Hygiene**: Use `--verify-git` for critical refactoring
-4. **Pre-Execution Staging**: Stage changes before each subtask to clearly see codex modifications
-5. **Context Continuity**: Let `codex resume --last` maintain context
-6. **Recovery Points**: TodoWrite provides clear progress tracking
-7. **Image References**: Attach design files for UI tasks
+1. **Task Flow First**: Always create visual flow diagram before execution
+2. **Group Related Work**: Cluster subtasks by domain/files for efficient resume
+3. **Subtask Granularity**: Keep subtasks small and focused (5-15 min each)
+4. **Clear Boundaries**: Each subtask should have well-defined input/output
+5. **Git Hygiene**: Use `--verify-git` for critical refactoring
+6. **Pre-Execution Staging**: Stage changes before each subtask to clearly see codex modifications
+7. **Smart Resume**: Use `resume --last` ONLY within same group
+8. **Fresh Sessions**: Start new session when switching to different group/domain
+9. **Recovery Points**: TodoWrite with group labels provides clear progress tracking
+10. **Image References**: Attach design files for UI tasks (first subtask in group)
 
 ## Input Processing
 

.claude/commands/cli/execute.md

@@ -9,29 +9,23 @@ examples:
   - /cli:execute --tool codex IMPL-001
   - /cli:execute --enhance "fix API performance issues"
 allowed-tools: SlashCommand(*), Bash(*)
-model: sonnet
 ---
 
 # CLI Execute Command (/cli:execute)
 
 ## Purpose
 
-Execute implementation tasks with YOLO permissions (auto-approves all confirmations).
+Execute implementation tasks with **YOLO permissions** (auto-approves all confirmations).
 
 **Supported Tools**: codex, gemini (default), qwen
-**Reference**: @~/.claude/workflows/intelligent-tools-strategy.md for complete tool details
+**Key Feature**: Automatic context inference and file pattern detection
 
-## YOLO Permissions
+## Core Concepts
 
+### YOLO Permissions
 Auto-approves: file pattern inference, execution, file modifications, summary generation
 
-## Enhancement Integration
-
-**When `--enhance` flag present** (Description Mode only): Execute `/enhance-prompt "[description]"` first, then use enhanced output (INTENT/CONTEXT/ACTION) for execution.
-
-**Note**: Task ID Mode uses task JSON directly (no enhancement).
-
-## Execution Modes
+### Execution Modes
 
 **1. Description Mode** (supports `--enhance`):
 - Input: Natural language description
@@ -41,71 +35,65 @@ Auto-approves: file pattern inference, execution, file modifications, summary ge
 - Input: Workflow task identifier (e.g., `IMPL-001`)
 - Process: Task JSON parsing → Scope analysis → Execute
 
-## Context Inference
+### Context Inference
 
-Auto-selects files based on:
-- **Keywords**: "auth" → `@{**/*auth*,**/*user*}`
-- **Technology**: "React" → `@{src/**/*.{jsx,tsx}}`
-- **Task Type**: "api" → `@{**/api/**/*,**/routes/**/*}`
-- **Always**: `@{CLAUDE.md,**/*CLAUDE.md}`
+Auto-selects files based on keywords and technology:
+- "auth" → `@{**/*auth*,**/*user*}`
+- "React" → `@{src/**/*.{jsx,tsx}}`
+- "api" → `@{**/api/**/*,**/routes/**/*}`
+- Always includes: `@{CLAUDE.md,**/*CLAUDE.md}`
 
-## Options
+For precise file targeting, use `rg` or MCP tools to discover files first.
 
-- `--debug`: Verbose logging
-- `--save-session`: Save execution to workflow session
+### Codex Session Continuity
+
+**Resume Pattern** for related tasks:
+```bash
+# First task - establish session
+codex -C [dir] --full-auto exec "[task]" --skip-git-repo-check -s danger-full-access
+
+# Related task - continue session
+codex --full-auto exec "[related-task]" resume --last --skip-git-repo-check -s danger-full-access
+```
+
+Use `resume --last` when current task extends/relates to previous execution. See intelligent-tools-strategy.md for auto-resume rules.
+
+## Parameters
+
+- `--tool <codex|gemini|qwen>` - Select CLI tool (default: gemini)
+- `--enhance` - Enhance input with `/enhance-prompt` first (Description Mode only)
+- `<description|task-id>` - Natural language description or task identifier
+- `--debug` - Verbose logging
+- `--save-session` - Save execution to workflow session
 
 ## Workflow Integration
 
 **Session Management**: Auto-detects `.workflow/.active-*` marker
-- **Active**: Save to `.workflow/WFS-[id]/.chat/execute-[timestamp].md`
-- **None**: Create new session
+- Active session: Save to `.workflow/WFS-[id]/.chat/execute-[timestamp].md`
+- No session: Create new session
 
 **Task Integration**: Load from `.task/[TASK-ID].json`, update status, generate summary
 
-## Command Template
-
-**Gemini/Qwen** (with YOLO approval):
-```bash
-cd [dir] && ~/.claude/scripts/[gemini|qwen]-wrapper --approval-mode yolo -p "
-PURPOSE: [implementation goal]
-TASK: [specific task]
-MODE: write
-CONTEXT: @{inferred_patterns} @{CLAUDE.md}
-EXPECTED: Implementation with file:line references
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/[category]/[template].txt) | [constraints]
-"
-```
-
-**Codex**:
-```bash
-codex -C [dir] --full-auto exec "
-PURPOSE: [implementation goal]
-TASK: [specific task]
-MODE: auto
-CONTEXT: @{inferred_patterns} @{CLAUDE.md}
-EXPECTED: Implementation with file:line references
-RULES: [constraints]
-" --skip-git-repo-check -s danger-full-access
-
-# With image attachment
-codex -C [dir] -i design.png --full-auto exec "..." --skip-git-repo-check -s danger-full-access
-```
-
 ## Examples
 
 ```bash
-/cli:execute "implement JWT authentication with middleware"  # Description mode
-/cli:execute --enhance "implement JWT authentication"        # Enhanced
-/cli:execute IMPL-001                                        # Task ID mode
-/cli:execute --tool codex "optimize database queries"        # Codex execution
+# Description mode with auto-detection
+/cli:execute "implement JWT authentication with middleware"
+
+# Enhanced prompt
+/cli:execute --enhance "implement JWT authentication"
+
+# Task ID mode
+/cli:execute IMPL-001
+
+# Codex execution
+/cli:execute --tool codex "optimize database queries"
+
+# Qwen with enhancement
+/cli:execute --tool qwen --enhance "refactor auth module"
 ```
 
-## Auto-Generated Outputs
-
-- **Summary**: `.summaries/[TASK-ID]-summary.md`
-- **Session**: `.chat/execute-[timestamp].md`
-
 ## Notes
 
-**vs. `/cli:analyze`**: Execute performs implementation, analyze is read-only.
-
+- Command templates, YOLO mode details, and session management: see intelligent-tools-strategy.md (loaded in memory)
+- Auto-generated outputs: `.summaries/[TASK-ID]-summary.md`, `.chat/execute-[timestamp].md`

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

@@ -8,107 +8,67 @@ examples:
   - /cli:mode:bug-index --tool qwen --enhance "login not working"
   - /cli:mode:bug-index --tool codex --cd "src/auth" "token validation fails"
 allowed-tools: SlashCommand(*), Bash(*)
-model: sonnet
 ---
 
 # CLI Mode: Bug Index (/cli:mode:bug-index)
 
 ## Purpose
 
-Execute systematic bug analysis and fix suggestions using CLI tools with diagnostic template.
+Systematic bug analysis with diagnostic template (`~/.claude/prompt-templates/bug-fix.md`).
 
 **Supported Tools**: codex, gemini (default), qwen
+**Key Feature**: `--cd` flag for directory-scoped analysis
+
+## Parameters
+
+- `--tool <codex|gemini|qwen>` - Tool selection (default: gemini)
+- `--enhance` - Enhance bug description with `/enhance-prompt` first
+- `--cd "path"` - Target directory for focused analysis
+- `<bug-description>` (Required) - Bug description or error message
 
 ## Execution Flow
 
-1. **Parse tool selection**: Extract `--tool` flag (default: gemini)
-2. **If `--enhance` flag present**: Execute `/enhance-prompt "[bug-description]"` first
-3. Parse bug description (original or enhanced)
-4. Detect target directory (from `--cd` or auto-infer)
-5. Build command for selected tool with bug-fix template
-6. Execute analysis
-7. Save to session (if active)
+1. Parse tool and directory options
+2. If `--enhance`: Execute `/enhance-prompt` to expand bug context
+3. Use bug-fix template: `~/.claude/prompt-templates/bug-fix.md`
+4. Execute with `--all-files` in target directory
+5. Save to `.workflow/WFS-[id]/.chat/bug-index-[timestamp].md`
 
-## Core Rules
+## Analysis Focus (via Template)
 
-1. **Enhance First (if flagged)**: Execute `/enhance-prompt` before analysis
-2. **Directory Context**: Use `cd` when `--cd` provided or auto-detected
-3. **Template Required**: Always use bug-fix template
-4. **Session Output**: Save to `.workflow/WFS-[id]/.chat/bug-index-[timestamp].md`
-
-## Command Template
-
-**Core Guidelines**: @~/.claude/workflows/intelligent-tools-strategy.md
-
-```bash
-cd [directory] && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: [bug analysis goal]
-TASK: Systematic bug analysis and fix recommendations
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} [entire codebase in directory]
-EXPECTED: Root cause analysis, code path tracing, targeted fixes
-RULES: $(cat ~/.claude/prompt-templates/bug-fix.md) | Bug: [description]
-"
-```
+- Root cause investigation
+- Code path tracing
+- Targeted minimal fixes
+- Impact assessment
 
 ## Examples
 
-**Basic Bug Analysis**:
 ```bash
-cd . && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: Debug authentication null pointer error
-TASK: Identify root cause and provide fix
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Root cause, code path, minimal fix, impact assessment
-RULES: $(cat ~/.claude/prompt-templates/bug-fix.md) | Bug: null pointer in login flow
-"
+# Basic bug analysis
+/cli:mode:bug-index "null pointer in authentication"
+
+# Directory-specific
+/cli:mode:bug-index --cd "src/auth" "token validation fails"
+
+# Enhanced description
+/cli:mode:bug-index --enhance "login broken"
+
+# Qwen for architecture-related bugs
+/cli:mode:bug-index --tool qwen "circular dependency in modules"
 ```
 
-**Directory-Specific**:
+## Bug Investigation Workflow
+
 ```bash
-cd src/auth && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: Fix token validation failure
-TASK: Analyze token validation bug in auth module
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Validation logic analysis, fix recommendation
-RULES: $(cat ~/.claude/prompt-templates/bug-fix.md) | Bug: token validation fails intermittently
-"
+# 1. Find bug-related files
+rg "error_keyword" --files-with-matches
+
+# 2. Execute bug analysis with focused context
+/cli:mode:bug-index --cd "src/module" "specific error description"
 ```
 
-**With Enhancement**:
-```bash
-# User: /gemini:mode:bug-index --enhance "login broken"
+## Notes
 
-# Step 1: Enhance
-/enhance-prompt "login broken"
-# Returns:
-# INTENT: Debug login authentication failure
-# CONTEXT: Known session state issue
-# ACTION: Check session management → verify token → test flow
-
-# Step 2: Analyze with enhanced context
-cd . && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: Debug login authentication failure
-TASK: Analyze session management, token handling, auth flow
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} Known: session state issue
-EXPECTED: Root cause in session/token, targeted fix
-RULES: $(cat ~/.claude/prompt-templates/bug-fix.md) | Focus on session management
-"
-```
-
-## Analysis Focus
-
-**Template provides**:
-- **Root Cause Analysis**: Systematic investigation
-- **Code Path Tracing**: Execution flow analysis
-- **Targeted Solutions**: Minimal, specific fixes
-- **Impact Assessment**: Side effect evaluation
-
-## Session Output
-
-**Location**: `.workflow/WFS-[topic]/.chat/bug-index-[timestamp].md`
-
-**Includes**:
-- Bug description
-- Template used
-- Analysis results
-- Recommended actions
+- Command templates and file patterns: see intelligent-tools-strategy.md (loaded in memory)
+- Template path: `~/.claude/prompt-templates/bug-fix.md`
+- Always uses `--all-files` for comprehensive codebase context

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

@@ -8,197 +8,68 @@ examples:
   - /cli:mode:code-analysis --tool qwen --enhance "explain data transformation pipeline"
   - /cli:mode:code-analysis --tool codex --cd "src/core" "trace execution path for user registration"
 allowed-tools: SlashCommand(*), Bash(*)
-model: sonnet
 ---
 
 # CLI Mode: Code Analysis (/cli:mode:code-analysis)
 
 ## Purpose
 
-Execute systematic code analysis and debugging using CLI tools with specialized code analysis template.
+Systematic code analysis with execution path tracing template (`~/.claude/prompt-templates/code-analysis.md`).
 
 **Supported Tools**: codex, gemini (default), qwen
+**Key Feature**: `--cd` flag for directory-scoped analysis
+
+## Parameters
+
+- `--tool <codex|gemini|qwen>` - Tool selection (default: gemini)
+- `--enhance` - Enhance analysis target with `/enhance-prompt` first
+- `--cd "path"` - Target directory for focused analysis
+- `<analysis-target>` (Required) - Code analysis target or question
 
 ## Execution Flow
 
-1. **Parse tool selection**: Extract `--tool` flag (default: gemini)
-2. **If `--enhance` flag present**: Execute `/enhance-prompt "[analysis-target]"` first
-3. Parse analysis target (original or enhanced)
-4. Detect target directory (from `--cd` or auto-infer)
-5. Build command for selected tool with code-analysis template
-6. Execute deep analysis
-7. Save to session (if active)
+1. Parse tool and directory options
+2. If `--enhance`: Execute `/enhance-prompt` to expand analysis intent
+3. Use code-analysis template: `~/.claude/prompt-templates/code-analysis.md`
+4. Execute with `--all-files` in target directory
+5. Save to `.workflow/WFS-[id]/.chat/code-analysis-[timestamp].md`
 
-## Core Rules
+## Analysis Capabilities (via Template)
 
-1. **Tool Selection**: Use `--tool` value or default to gemini
-2. **Enhance First (if flagged)**: Execute `/enhance-prompt` before analysis
-3. **Directory Context**: Use `cd` when `--cd` provided or auto-detected
-4. **Template Required**: Always use code-analysis template
-5. **Session Output**: Save to `.workflow/WFS-[id]/.chat/code-analysis-[timestamp].md`
-
-## Analysis Capabilities
-
-The code-analysis template provides:
-- **Systematic Code Analysis**: Break down complex code into manageable parts
-- **Execution Path Tracing**: Track variable states and call stacks
-- **Control & Data Flow**: Understand code logic and data transformations
-- **Call Flow Visualization**: Diagram function calling sequences
-- **Logical Reasoning**: Explain "why" behind code behavior
-- **Debugging Insights**: Identify potential bugs or inefficiencies
-
-## Command Templates
-
-**Core Guidelines**: @~/.claude/workflows/intelligent-tools-strategy.md
-
-### Gemini (Default)
-```bash
-cd [directory] && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: [analysis goal from target]
-TASK: Deep code analysis with execution path tracing
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} [entire codebase in directory]
-EXPECTED: Systematic analysis, call flow diagram, data transformations, logical explanation
-RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on [specific aspect]
-"
-```
-
-### Qwen
-```bash
-cd [directory] && ~/.claude/scripts/qwen-wrapper --all-files -p "
-PURPOSE: [analysis goal from target]
-TASK: Architecture-level code analysis and pattern recognition
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} [entire codebase in directory]
-EXPECTED: Architectural insights, design patterns, code structure analysis
-RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on [specific aspect]
-"
-```
-
-### Codex
-```bash
-codex -C [directory] --full-auto exec "
-PURPOSE: [analysis goal from target]
-TASK: Deep code inspection with debugging insights
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} [entire codebase in directory]
-EXPECTED: Execution trace, bug identification, optimization opportunities
-RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on [specific aspect]
-" --skip-git-repo-check -s danger-full-access
-```
+- Execution path tracing with variable states
+- Call flow visualization and diagrams
+- Control & data flow analysis
+- Logical reasoning ("why" behind code behavior)
+- Debugging insights and inefficiency detection
 
 ## Examples
 
-**Basic Code Analysis (Gemini)**:
 ```bash
-cd . && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: Analyze authentication flow logic
-TASK: Trace authentication execution path and identify key functions
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Step-by-step flow, call diagram, data passing between functions
-RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on control flow and security
-"
+# Basic code analysis
+/cli:mode:code-analysis "trace authentication flow"
+
+# Directory-specific with enhancement
+/cli:mode:code-analysis --cd "src/auth" --enhance "how does JWT work"
+
+# Qwen for architecture analysis
+/cli:mode:code-analysis --tool qwen "explain microservices communication"
+
+# Codex for deep tracing
+/cli:mode:code-analysis --tool codex --cd "src/api" "trace request lifecycle"
 ```
 
-**Architecture Analysis (Qwen)**:
-```bash
-# User: /cli:mode:code-analysis --tool qwen "explain data transformation pipeline"
+## Code Tracing Workflow
 
-cd . && ~/.claude/scripts/qwen-wrapper --all-files -p "
-PURPOSE: Explain data transformation pipeline architecture
-TASK: Analyze data flow and transformation patterns
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Pipeline structure, transformation stages, data format changes
-RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on data flow and patterns
-"
+```bash
+# 1. Find entry points
+rg "function.*main|export.*handler" --files-with-matches
+
+# 2. Execute deep analysis
+/cli:mode:code-analysis --cd "src" "trace execution from entry point"
 ```
 
-**Deep Debugging (Codex)**:
-```bash
-# User: /cli:mode:code-analysis --tool codex --cd "src/core" "trace execution path for user registration"
+## Notes
 
-codex -C src/core --full-auto exec "
-PURPOSE: Trace execution path for user registration
-TASK: Deep analysis of registration flow with debugging insights
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Complete execution trace, variable states, potential issues
-RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on edge cases and error handling
-" --skip-git-repo-check -s danger-full-access
-```
-
-**With Enhancement**:
-```bash
-# User: /cli:mode:code-analysis --enhance "why is login slow"
-
-# Step 1: Enhance
-/enhance-prompt "why is login slow"
-# Returns:
-# INTENT: Identify performance bottlenecks in login flow
-# CONTEXT: Authentication module, database queries
-# ACTION: Trace execution path → identify slow operations → suggest optimizations
-
-# Step 2: Analyze with enhanced context
-cd . && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: Identify performance bottlenecks in login flow
-TASK: Trace login execution path and measure operation costs
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} @{**/*auth*,**/*login*}
-EXPECTED: Performance analysis, bottleneck identification, optimization recommendations
-RULES: $(cat ~/.claude/prompt-templates/code-analysis.md) | Focus on performance and database queries
-"
-```
-
-## Analysis Output Structure
-
-Based on code-analysis.md template, output includes:
-
-### 1. 思考过程 (Thinking Process)
-- Analysis strategy and approach
-- Key assumptions about code behavior
-
-### 2. 对问题的理解 (Understanding)
-- Restate analysis target
-- Confirm understanding of requirements
-
-### 3. 核心解答 (Core Answer)
-- Direct, concise answer to analysis question
-
-### 4. 详细分析与调用逻辑 (Detailed Analysis)
-- **代码段识别**: Relevant code sections
-- **执行流程**: Step-by-step execution flow
-- **调用图**: Visual call flow diagram with symbols:
-  - `───►` Function call
-  - `◄───` Return
-  - `│` Continuation
-  - `├─` Intermediate step
-  - `└─` Last step in block
-- **数据传递**: Data passing and state changes
-- **逻辑解释**: Why code behaves this way
-
-### 5. 总结 (Summary)
-- Key findings and recommendations
-
-## Session Output
-
-**Location**: `.workflow/WFS-[topic]/.chat/code-analysis-[timestamp].md`
-
-**Includes**:
-- Analysis target
-- Template used
-- Complete structured analysis
-- Call flow diagrams
-- Debugging insights
-- Recommendations
-
-## Use Cases
-
-| Use Case | Best Tool | Focus |
-|----------|-----------|-------|
-| **Understand execution flow** | gemini | Call sequences, data flow |
-| **Architectural patterns** | qwen | Design patterns, structure |
-| **Performance debugging** | codex | Bottlenecks, optimizations |
-| **Bug investigation** | codex | Error paths, edge cases |
-| **Code review** | gemini | Logic correctness, clarity |
-| **Refactoring planning** | qwen | Structure improvements |
-
-## Tool Selection Guide
-
-- **Gemini**: Best for general code understanding and tracing
-- **Qwen**: Best for architectural analysis and pattern recognition
-- **Codex**: Best for deep debugging and performance analysis
+- Command templates and file patterns: see intelligent-tools-strategy.md (loaded in memory)
+- Template path: `~/.claude/prompt-templates/code-analysis.md`
+- Always uses `--all-files` for comprehensive code context

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

@@ -8,97 +8,68 @@ examples:
   - /cli:mode:plan --tool qwen --enhance "plan microservices migration"
   - /cli:mode:plan --tool codex --cd "src/auth" "authentication system"
 allowed-tools: SlashCommand(*), Bash(*)
-model: sonnet
 ---
 
 # CLI Mode: Plan (/cli:mode:plan)
 
 ## Purpose
 
-Execute planning and architecture analysis using CLI tools with specialized template.
+Comprehensive planning and architecture analysis with strategic planning template (`~/.claude/prompt-templates/plan.md`).
 
 **Supported Tools**: codex, gemini (default), qwen
+**Key Feature**: `--cd` flag for directory-scoped planning
+
+## Parameters
+
+- `--tool <codex|gemini|qwen>` - Tool selection (default: gemini)
+- `--enhance` - Enhance topic with `/enhance-prompt` first
+- `--cd "path"` - Target directory for focused planning
+- `<topic>` (Required) - Planning topic or architectural question
 
 ## Execution Flow
 
-1. **Parse tool selection**: Extract `--tool` flag (default: gemini)
-2. **If `--enhance` flag present**: Execute `/enhance-prompt "[topic]"` first
-3. Parse topic (original or enhanced)
-4. Detect target directory (from `--cd` or auto-infer)
-5. Build command for selected tool with planning template
-6. Execute analysis
-7. Save to session (if active)
+1. Parse tool and directory options
+2. If `--enhance`: Execute `/enhance-prompt` to expand planning context
+3. Use planning template: `~/.claude/prompt-templates/plan.md`
+4. Execute with `--all-files` in target directory
+5. Save to `.workflow/WFS-[id]/.chat/plan-[timestamp].md`
 
-## Core Rules
+## Planning Capabilities (via Template)
 
-1. **Enhance First (if flagged)**: Execute `/enhance-prompt` before planning
-2. **Directory Context**: Use `cd` when `--cd` provided or auto-detected
-3. **Template Required**: Always use planning template
-4. **Session Output**: Save to `.workflow/WFS-[id]/.chat/plan-[timestamp].md`
-
-## Command Template
-
-**Core Guidelines**: @~/.claude/workflows/intelligent-tools-strategy.md
-
-```bash
-cd [directory] && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: [planning goal from topic]
-TASK: Comprehensive planning and architecture analysis
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} [entire codebase in directory]
-EXPECTED: Strategic insights, implementation roadmap, key decisions
-RULES: $(cat ~/.claude/prompt-templates/plan.md) | Focus on [topic area]
-"
-```
+- Strategic architecture insights
+- Implementation roadmaps
+- Key technical decisions
+- Risk assessment
+- Resource planning
 
 ## Examples
 
-**Basic Planning**:
 ```bash
-cd . && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: Design user dashboard feature architecture
-TASK: Comprehensive architecture planning for dashboard
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Architecture design, component structure, implementation roadmap
-RULES: $(cat ~/.claude/prompt-templates/plan.md) | Focus on scalability and UX
-"
+# Basic planning
+/cli:mode:plan "design user dashboard"
+
+# Enhanced with directory scope
+/cli:mode:plan --cd "src/api" --enhance "plan API refactoring"
+
+# Qwen for architecture planning
+/cli:mode:plan --tool qwen "plan microservices migration"
+
+# Codex for technical planning
+/cli:mode:plan --tool codex "plan testing strategy"
 ```
 
-**Directory-Specific**:
+## Planning Workflow
+
 ```bash
-cd src/auth && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: Plan authentication system redesign
-TASK: Analyze current auth and plan improvements
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Migration strategy, security improvements, timeline
-RULES: $(cat ~/.claude/prompt-templates/plan.md) | Focus on security and backward compatibility
-"
+# 1. Gather existing architecture info
+rg "architecture|design" --files-with-matches
+
+# 2. Execute planning analysis
+/cli:mode:plan "topic for strategic planning"
 ```
 
-**With Enhancement**:
-```bash
-# User: /gemini:mode:plan --enhance "fix auth issues"
+## Notes
 
-# Step 1: Enhance
-/enhance-prompt "fix auth issues"
-# Returns structured planning context
-
-# Step 2: Plan with enhanced input
-cd . && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: [enhanced goal]
-TASK: [enhanced task description]
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} [enhanced context]
-EXPECTED: Strategic plan with enhanced requirements
-RULES: $(cat ~/.claude/prompt-templates/plan.md) | [enhanced constraints]
-"
-```
-
-## Session Output
-
-**Location**: `.workflow/WFS-[topic]/.chat/plan-[timestamp].md`
-
-**Includes**:
-- Planning topic
-- Template used
-- Analysis results
-- Implementation roadmap
-- Key decisions
+- Command templates and file patterns: see intelligent-tools-strategy.md (loaded in memory)
+- Template path: `~/.claude/prompt-templates/plan.md`
+- Always uses `--all-files` for comprehensive project context

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

@@ -1,33 +1,46 @@
 ---
 name: update-memory-full
 description: Complete project-wide CLAUDE.md documentation update
-usage: /update-memory-full
+usage: /update-memory-full [--tool <gemini|qwen|codex>]
+argument-hint: "[--tool gemini|qwen|codex]"
 examples:
-  - /update-memory-full                      # Full project documentation update
+  - /update-memory-full                      # Full project documentation update (gemini default)
+  - /update-memory-full --tool qwen          # Use Qwen for architecture analysis
+  - /update-memory-full --tool codex         # Use Codex for implementation validation
 ---
 
 ### 🚀 Command Overview: `/update-memory-full`
 
 Complete project-wide documentation update using depth-parallel execution.
 
+**Tool Selection**:
+- **Gemini (default)**: Documentation generation, pattern recognition, architecture review
+- **Qwen**: Architecture analysis, system design documentation
+- **Codex**: Implementation validation, code quality analysis
+
 ### 📝 Execution Template
 
 ```bash
 #!/bin/bash
 # Complete project-wide CLAUDE.md documentation update
 
-# Step 1: Code Index architecture analysis
+# Step 1: Parse tool selection (default: gemini)
+tool="gemini"
+[[ "$*" == *"--tool qwen"* ]] && tool="qwen"
+[[ "$*" == *"--tool codex"* ]] && tool="codex"
+
+# Step 2: Code Index architecture analysis
 mcp__code-index__search_code_advanced(pattern="class|function|interface", file_pattern="**/*.{ts,js,py}")
 mcp__code-index__find_files(pattern="**/*.{md,json,yaml,yml}")
 
-# Step 2: Cache git changes
+# Step 3: Cache git changes
 Bash(git add -A 2>/dev/null || true)
 
-# Step 3: Get and display project structure
+# Step 4: Get and display project structure
 modules=$(Bash(~/.claude/scripts/get_modules_by_depth.sh list))
 count=$(echo "$modules" | wc -l)
 
-# Step 3: Analysis handover → Model takes control
+# Step 5: Analysis handover → Model takes control
 # BASH_EXECUTION_STOPS → MODEL_ANALYSIS_BEGINS
 
 # Pseudocode flow:
@@ -35,6 +48,8 @@ count=$(echo "$modules" | wc -l)
 #     → Task "Complex project full update" subagent_type: "memory-gemini-bridge"
 # ELSE:
 #     → Present plan and WAIT FOR USER APPROVAL before execution
+#
+# Pass tool parameter to update_module_claude.sh: "$tool"
 ```
 
 ### 🧠 Model Analysis Phase
@@ -43,7 +58,7 @@ After the bash script completes the initial analysis, the model takes control to
 
 1. **Analyze Complexity**: Review module count and project context
 2. **Parse CLAUDE.md Status**: Extract which modules have/need CLAUDE.md files
-3. **Choose Strategy**: 
+3. **Choose Strategy**:
    - Simple projects: Present execution plan with CLAUDE.md paths to user
    - Complex projects: Delegate to memory-gemini-bridge agent
 4. **Present Detailed Plan**: Show user exactly which CLAUDE.md files will be created/updated
@@ -56,17 +71,19 @@ After the bash script completes the initial analysis, the model takes control to
 Model will present detailed plan:
 ```
 📋 Update Plan:
+  Tool: [gemini|qwen|codex] (from --tool parameter)
+
   NEW CLAUDE.md files (X):
     - ./src/components/CLAUDE.md
     - ./src/services/CLAUDE.md
-  
+
   UPDATE existing CLAUDE.md files (Y):
     - ./CLAUDE.md
     - ./src/CLAUDE.md
     - ./tests/CLAUDE.md
 
   Total: N CLAUDE.md files will be processed
-  
+
   ⚠️ Confirm execution? (y/n)
 ```
 
@@ -84,7 +101,7 @@ depth_modules = organize_by_depth(modules)
 FOR depth FROM max_depth DOWN TO 0:
     FOR each module IN depth_modules[depth]:
         WHILE active_jobs >= 4: wait(0.1)
-        Bash(~/.claude/scripts/update_module_claude.sh "$module" "full" &)
+        Bash(~/.claude/scripts/update_module_claude.sh "$module" "full" "$tool" &)
     wait_all_jobs()
 
 # Step 6: Safety check and restore staging state
@@ -102,13 +119,43 @@ Bash(git status --short)
 ```
 
 **For Complex Projects (>20 modules):**
-The model will delegate to the memory-gemini-bridge agent using the Task tool:
-```
+
+The model will delegate to the memory-gemini-bridge agent with structured context:
+
+```javascript
 Task "Complex project full update"
-prompt: "Execute full documentation update for [count] modules using depth-parallel execution"
 subagent_type: "memory-gemini-bridge"
+prompt: `
+CONTEXT:
+- Total modules: ${module_count}
+- Tool: ${tool}  // from --tool parameter, default: gemini
+- Mode: full
+- Existing CLAUDE.md: ${existing_count}
+- New CLAUDE.md needed: ${new_count}
+
+MODULE LIST:
+${modules_output}  // Full output from get_modules_by_depth.sh list
+
+REQUIREMENTS:
+1. Use TodoWrite to track each depth level before execution
+2. Process depths 5→0 sequentially, max 4 parallel jobs per depth
+3. Command format: update_module_claude.sh "<path>" "full" "${tool}" &
+4. Extract exact path from "depth:N|path:<PATH>|..." format
+5. Verify all ${module_count} modules are processed
+6. Run safety check after completion
+7. Display git status
+
+Execute depth-parallel updates for all modules.
+`
 ```
 
+**Agent receives complete context:**
+- Module count and tool selection
+- Full structured module list
+- Clear execution requirements
+- Path extraction format
+- Success criteria
+
 
 ### 📚 Usage Examples
 

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

@@ -1,15 +1,23 @@
 ---
 name: update-memory-related
 description: Context-aware CLAUDE.md documentation updates based on recent changes
-usage: /update-memory-related
+usage: /update-memory-related [--tool <gemini|qwen|codex>]
+argument-hint: "[--tool gemini|qwen|codex]"
 examples:
-  - /update-memory-related                    # Update documentation based on recent changes
+  - /update-memory-related                    # Update documentation based on recent changes (gemini default)
+  - /update-memory-related --tool qwen        # Use Qwen for architecture analysis
+  - /update-memory-related --tool codex       # Use Codex for implementation validation
 ---
 
 ### 🚀 Command Overview: `/update-memory-related`
 
 Context-aware documentation update for modules affected by recent changes.
 
+**Tool Selection**:
+- **Gemini (default)**: Documentation generation, pattern recognition, architecture review
+- **Qwen**: Architecture analysis, system design documentation
+- **Codex**: Implementation validation, code quality analysis
+
 
 ### 📝 Execution Template
 
@@ -17,23 +25,28 @@ Context-aware documentation update for modules affected by recent changes.
 #!/bin/bash
 # Context-aware CLAUDE.md documentation update
 
-# Step 1: Code Index refresh and architecture analysis
+# Step 1: Parse tool selection (default: gemini)
+tool="gemini"
+[[ "$*" == *"--tool qwen"* ]] && tool="qwen"
+[[ "$*" == *"--tool codex"* ]] && tool="codex"
+
+# Step 2: Code Index refresh and architecture analysis
 mcp__code-index__refresh_index()
 mcp__code-index__search_code_advanced(pattern="class|function|interface", file_pattern="**/*.{ts,js,py}")
 
-# Step 2: Detect changed modules (before staging)
+# Step 3: Detect changed modules (before staging)
 changed=$(Bash(~/.claude/scripts/detect_changed_modules.sh list))
 
-# Step 3: Cache git changes (protect current state)
+# Step 4: Cache git changes (protect current state)
 Bash(git add -A 2>/dev/null || true)
 
-# Step 3: Use detected changes or fallback
+# Step 5: Use detected changes or fallback
 if [ -z "$changed" ]; then
     changed=$(Bash(~/.claude/scripts/get_modules_by_depth.sh list | head -10))
 fi
 count=$(echo "$changed" | wc -l)
 
-# Step 4: Analysis handover → Model takes control  
+# Step 6: Analysis handover → Model takes control
 # BASH_EXECUTION_STOPS → MODEL_ANALYSIS_BEGINS
 
 # Pseudocode flow:
@@ -41,6 +54,8 @@ count=$(echo "$changed" | wc -l)
 #     → Task "Complex project related update" subagent_type: "memory-gemini-bridge"
 # ELSE:
 #     → Present plan and WAIT FOR USER APPROVAL before execution
+#
+# Pass tool parameter to update_module_claude.sh: "$tool"
 ```
 
 ### 🧠 Model Analysis Phase
@@ -62,18 +77,20 @@ After the bash script completes change detection, the model takes control to:
 Model will present detailed plan for affected modules:
 ```
 📋 Related Update Plan:
+  Tool: [gemini|qwen|codex] (from --tool parameter)
+
   CHANGED modules affecting CLAUDE.md:
-  
+
   NEW CLAUDE.md files (X):
     - ./src/api/auth/CLAUDE.md  [new module]
     - ./src/utils/helpers/CLAUDE.md  [new module]
-  
+
   UPDATE existing CLAUDE.md files (Y):
     - ./src/api/CLAUDE.md  [parent of changed auth/]
     - ./src/CLAUDE.md  [root level]
 
   Total: N CLAUDE.md files will be processed for recent changes
-  
+
   ⚠️ Confirm execution? (y/n)
 ```
 
@@ -91,7 +108,7 @@ depth_modules = organize_by_depth(changed_modules)
 FOR depth FROM max_depth DOWN TO 0:
     FOR each module IN depth_modules[depth]:
         WHILE active_jobs >= 4: wait(0.1)
-        Bash(~/.claude/scripts/update_module_claude.sh "$module" "related" &)
+        Bash(~/.claude/scripts/update_module_claude.sh "$module" "related" "$tool" &)
     wait_all_jobs()
 
 # Step 6: Safety check and restore staging state
@@ -109,13 +126,44 @@ Bash(git diff --stat)
 ```
 
 **For Complex Changes (>15 modules):**
-The model will delegate to the memory-gemini-bridge agent using the Task tool:
-```
+
+The model will delegate to the memory-gemini-bridge agent with structured context:
+
+```javascript
 Task "Complex project related update"
-prompt: "Execute context-aware update for [count] changed modules using depth-parallel execution"
 subagent_type: "memory-gemini-bridge"
+prompt: `
+CONTEXT:
+- Total modules: ${change_count}
+- Tool: ${tool}  // from --tool parameter, default: gemini
+- Mode: related
+- Changed modules detected via: detect_changed_modules.sh
+- Existing CLAUDE.md: ${existing_count}
+- New CLAUDE.md needed: ${new_count}
+
+MODULE LIST:
+${changed_modules_output}  // Full output from detect_changed_modules.sh list
+
+REQUIREMENTS:
+1. Use TodoWrite to track each depth level before execution
+2. Process depths sequentially (deepest→shallowest), max 4 parallel jobs per depth
+3. Command format: update_module_claude.sh "<path>" "related" "${tool}" &
+4. Extract exact path from "depth:N|path:<PATH>|..." format
+5. Verify all ${change_count} modules are processed
+6. Run safety check after completion
+7. Display git diff --stat
+
+Execute depth-parallel updates for changed modules only.
+`
 ```
 
+**Agent receives complete context:**
+- Changed module count and tool selection
+- Full structured module list (changed only)
+- Clear execution requirements with "related" mode
+- Path extraction format
+- Success criteria
+
 
 ### 📚 Usage Examples
 

.claude/scripts/update_module_claude.sh

@@ -1,13 +1,15 @@
 #!/bin/bash
 # Update CLAUDE.md for a specific module with automatic layer detection
-# Usage: update_module_claude.sh <module_path> [update_type]
+# Usage: update_module_claude.sh <module_path> [update_type] [tool]
 #   module_path: Path to the module directory
 #   update_type: full|related (default: full)
+#   tool: gemini|qwen|codex (default: gemini)
 #   Script automatically detects layer depth and selects appropriate template
 
 update_module_claude() {
     local module_path="$1"
     local update_type="${2:-full}"
+    local tool="${3:-gemini}"
     
     # Validate parameters
     if [ -z "$module_path" ]; then
@@ -61,9 +63,9 @@ update_module_claude() {
     
     # Prepare logging info
     local module_name=$(basename "$module_path")
-    
+
     echo "⚡ Updating: $module_path"
-    echo "   Layer: $layer | Type: $update_type | Files: $file_count"
+    echo "   Layer: $layer | Type: $update_type | Tool: $tool | Files: $file_count"
     echo "   Template: $(basename "$template_path") | Strategy: $analysis_strategy"
     
     # Generate prompt with template injection
@@ -106,31 +108,50 @@ update_module_claude() {
     # Execute update
     local start_time=$(date +%s)
     echo "   🔄 Starting update..."
-    
+
     if cd "$module_path" 2>/dev/null; then
-        # Execute gemini command with layer-specific analysis strategy
-        local gemini_result=0
-        if [ "$analysis_strategy" = "--all-files" ]; then
-            gemini --all-files --yolo -p "$base_prompt
+        local tool_result=0
+        local final_prompt="$base_prompt
 
         Module Information:
         - Name: $module_name
         - Path: $module_path
         - Layer: $layer
-        - Analysis Strategy: $analysis_strategy" 2>&1
-            gemini_result=$?
-        else
-            gemini --yolo -p "$analysis_strategy $base_prompt
+        - Tool: $tool
+        - Analysis Strategy: $analysis_strategy"
 
-        Module Information:
-        - Name: $module_name
-        - Path: $module_path
-        - Layer: $layer
-        - Analysis Strategy: $analysis_strategy" 2>&1
-            gemini_result=$?
-        fi
-        
-        if [ $gemini_result -eq 0 ]; then
+        # Execute with selected tool
+        case "$tool" in
+            qwen)
+                if [ "$analysis_strategy" = "--all-files" ]; then
+                    qwen --all-files --yolo -p "$final_prompt" 2>&1
+                    tool_result=$?
+                else
+                    qwen --yolo -p "$analysis_strategy $final_prompt" 2>&1
+                    tool_result=$?
+                fi
+                ;;
+            codex)
+                if [ "$analysis_strategy" = "--all-files" ]; then
+                    codex --full-auto exec "$final_prompt" --skip-git-repo-check -s danger-full-access 2>&1
+                    tool_result=$?
+                else
+                    codex --full-auto exec "$final_prompt CONTEXT: $analysis_strategy" --skip-git-repo-check -s danger-full-access 2>&1
+                    tool_result=$?
+                fi
+                ;;
+            gemini|*)
+                if [ "$analysis_strategy" = "--all-files" ]; then
+                    gemini --all-files --yolo -p "$final_prompt" 2>&1
+                    tool_result=$?
+                else
+                    gemini --yolo -p "$analysis_strategy $final_prompt" 2>&1
+                    tool_result=$?
+                fi
+                ;;
+        esac
+
+        if [ $tool_result -eq 0 ]; then
             local end_time=$(date +%s)
             local duration=$((end_time - start_time))
             echo "   ✅ Completed in ${duration}s"

.claude/version.json

@@ -1,7 +0,0 @@
-{
-  "version": "3.4.0",
-  "installation_mode": "Local",
-  "installation_path": "D:\\Claude_dms3\\.claude",
-  "source_branch": "main",
-  "installation_date_utc": "2025-10-04T00:00:00Z"
-}

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

@@ -6,11 +6,22 @@ type: strategic-guideline
 
 # Intelligent Tools Selection Strategy
 
+## 📋 Table of Contents
+1. [Core Framework](#-core-framework)
+2. [Tool Specifications](#-tool-specifications)
+3. [Command Templates](#-command-templates)
+4. [Tool Selection Guide](#-tool-selection-guide)
+5. [Usage Patterns](#-usage-patterns)
+6. [Best Practices](#-best-practices)
+
+---
+
 ## ⚡ Core Framework
 
-**Gemini**: Analysis, understanding, exploration & documentation
-**Qwen**: Architecture analysis, code generation & implementation
-**Codex**: Development, implementation & automation
+### Tool Overview
+- **Gemini**: Analysis, understanding, exploration & documentation
+- **Qwen**: Architecture analysis, code generation & implementation
+- **Codex**: Development, implementation & automation
 
 ### Decision Principles
 - **Use tools early and often** - Tools are faster, more thorough, and reliable than manual approaches
@@ -27,40 +38,118 @@ type: strategic-guideline
 4. **Not sure?** → Use multiple tools in parallel
 5. **Small task?** → Still use tools - they're faster than manual work
 
-### Core Execution Rules
-- **Dynamic Timeout (20-120min)**: Allocate execution time based on task complexity
-  - Simple tasks (analysis, search): 20-40min (1200000-2400000ms)
-  - Medium tasks (refactoring, documentation): 40-60min (2400000-3600000ms)
-  - Complex tasks (implementation, migration): 60-120min (3600000-7200000ms)
-- **Codex Multiplier**: Codex commands use 1.5x of allocated time
-- **Apply to All Tools**: All bash() wrapped commands including Gemini, Qwen wrapper and Codex executions
-- **Command Examples**: `bash(~/.claude/scripts/gemini-wrapper -p "prompt")`, `bash(codex -C directory --full-auto exec "task")`
-- **Auto-detect**: Analyze PURPOSE and TASK fields to determine appropriate timeout
+---
 
-### Permission Framework
-- **⚠️ WRITE PROTECTION**: Local codebase write/modify requires EXPLICIT user confirmation
-  - **Analysis Mode (default)**: Read-only, safe for auto-execution
-  - **Write Mode**: Requires user explicitly states MODE=write or MODE=auto in prompt
-  - **Exception**: User provides clear instructions like "modify", "create", "implement"
-- **Gemini/Qwen Write Access**: Use `--approval-mode yolo` ONLY when MODE=write explicitly specified
-- **Codex Write Access**: Use `-s danger-full-access` and `--skip-git-repo-check` ONLY when MODE=auto explicitly specified
-- **Default Behavior**: All tools default to analysis/read-only mode without explicit write permission
+## 🎯 Tool Specifications
 
-## 🎯 Universal Command Template
+### Gemini
+- **Command**: `~/.claude/scripts/gemini-wrapper`
+- **Strengths**: Large context window, pattern recognition
+- **Best For**: Analysis, documentation generation, code exploration
+- **Permissions**: Default read-only analysis, MODE=write requires explicit specification (auto-enables --approval-mode yolo)
+- **Default MODE**: `analysis` (read-only)
+- **⚠️ Write Trigger**: Only when user explicitly requests "generate documentation", "modify code", or specifies MODE=write
 
-### Standard Format (REQUIRED)
+#### MODE Options
+- `analysis` (default) - Read-only analysis and documentation generation
+- `write` - ⚠️ Create/modify codebase files (requires explicit specification, auto-enables --approval-mode yolo)
+
+### Qwen
+- **Command**: `~/.claude/scripts/qwen-wrapper`
+- **Strengths**: Architecture analysis, pattern recognition
+- **Best For**: System design analysis, architectural review
+- **Permissions**: Architecture analysis only, no automatic code generation
+- **Default MODE**: `analysis` (read-only)
+- **⚠️ Write Trigger**: Explicitly prohibited from auto-calling write mode
+
+#### MODE Options
+- `analysis` (default) - Architecture analysis only, no code generation/modification (read-only)
+- `write` - ⚠️ Code generation (requires explicit specification, disabled by default)
+
+### Codex
+- **Command**: `codex --full-auto exec`
+- **Strengths**: Autonomous development, mathematical reasoning
+- **Best For**: Implementation, testing, automation
+- **Permissions**: Requires explicit MODE=auto or MODE=write specification
+- **Default MODE**: No default, must be explicitly specified
+- **⚠️ Write Trigger**: Only when user explicitly requests "implement", "modify", "generate code" AND specifies MODE
+
+#### MODE Options
+- `auto` - ⚠️ Autonomous development with full file operations (requires explicit specification, enables -s danger-full-access)
+- `write` - ⚠️ Test generation and file modification (requires explicit specification)
+- **Default**: No default mode, MODE must be explicitly specified
+
+#### Session Management
+- `codex resume` - Resume previous interactive session (picker by default)
+- `codex exec "task" resume --last` - Continue most recent session with new task (maintains context)
+- `codex -i <image_file>` - Attach image(s) to initial prompt (useful for UI/design references)
+- **Multi-task Pattern**: First task uses `exec`, subsequent tasks use `exec "..." resume --last` for context continuity
+  - **Parameter Position**: `resume --last` must be placed AFTER the prompt string at command END
+  - **Example**:
+    ```bash
+    # First task - establish session
+    codex -C project --full-auto exec "Implement auth module" --skip-git-repo-check -s danger-full-access
+
+    # Subsequent tasks - continue same session
+    codex --full-auto exec "Add JWT validation" resume --last --skip-git-repo-check -s danger-full-access
+    codex --full-auto exec "Write auth tests" resume --last --skip-git-repo-check -s danger-full-access
+    ```
+
+#### Auto-Resume Decision Rules
+**When to use `resume --last`**:
+- Current task is related to/extends previous Codex task in conversation memory
+- Current task requires context from previous implementation
+- Current task is part of multi-step workflow (e.g., implement → enhance → test)
+- Session memory indicates recent Codex execution on same module/feature
+
+**When NOT to use `resume --last`**:
+- First Codex task in conversation
+- New independent task unrelated to previous work
+- Switching to different module/feature area
+- No recent Codex task in conversation memory
+
+---
+
+## 🎯 Command Templates
+
+### Universal Template Structure
+Every command MUST follow this structure:
+- [ ] **PURPOSE** - Clear goal and intent
+- [ ] **TASK** - Specific execution task
+- [ ] **MODE** - Execution mode and permission level
+- [ ] **CONTEXT** - File references and memory context from previous sessions
+- [ ] **EXPECTED** - Clear expected results
+- [ ] **RULES** - Template reference and constraints
+
+### Standard Command Formats
+
+#### Gemini Commands
 ```bash
-# Gemini Analysis (read/write capable)
+# Gemini Analysis (read-only, default)
 cd [directory] && ~/.claude/scripts/gemini-wrapper -p "
 PURPOSE: [clear analysis goal]
 TASK: [specific analysis task]
-MODE: [analysis|write]
+MODE: analysis
 CONTEXT: [file references and memory context]
 EXPECTED: [expected output]
 RULES: [template reference and constraints]
 "
 
-# Qwen Architecture Analysis (read-only analysis)
+# Gemini Write Mode (requires explicit MODE=write)
+# NOTE: --approval-mode yolo must be placed AFTER wrapper command, BEFORE -p
+cd [directory] && ~/.claude/scripts/gemini-wrapper --approval-mode yolo -p "
+PURPOSE: [clear goal]
+TASK: [specific task]
+MODE: write
+CONTEXT: [file references and memory context]
+EXPECTED: [expected output]
+RULES: [template reference and constraints]
+"
+```
+
+#### Qwen Commands
+```bash
+# Qwen Architecture Analysis (read-only, default)
 cd [directory] && ~/.claude/scripts/qwen-wrapper -p "
 PURPOSE: [clear architecture goal]
 TASK: [specific analysis task]
@@ -70,43 +159,44 @@ EXPECTED: [expected deliverables]
 RULES: [template reference and constraints]
 "
 
-# Codex Development
+# Qwen Write Mode (requires explicit MODE=write)
+# NOTE: --approval-mode yolo must be placed AFTER wrapper command, BEFORE -p
+cd [directory] && ~/.claude/scripts/qwen-wrapper --approval-mode yolo -p "
+PURPOSE: [clear goal]
+TASK: [specific task]
+MODE: write
+CONTEXT: [file references and memory context]
+EXPECTED: [expected deliverables]
+RULES: [template reference and constraints]
+"
+```
+
+#### Codex Commands
+```bash
+# Codex Development (requires explicit MODE=auto)
+# NOTE: --skip-git-repo-check and -s danger-full-access must be placed at command END
 codex -C [directory] --full-auto exec "
 PURPOSE: [clear development goal]
 TASK: [specific development task]
-MODE: [auto|write]
+MODE: auto
+CONTEXT: [file references and memory context]
+EXPECTED: [expected deliverables]
+RULES: [template reference and constraints]
+" --skip-git-repo-check -s danger-full-access
+
+# Codex Test/Write Mode (requires explicit MODE=write)
+# NOTE: --skip-git-repo-check and -s danger-full-access must be placed at command END
+codex -C [directory] --full-auto exec "
+PURPOSE: [clear goal]
+TASK: [specific task]
+MODE: write
 CONTEXT: [file references and memory context]
 EXPECTED: [expected deliverables]
 RULES: [template reference and constraints]
 " --skip-git-repo-check -s danger-full-access
 ```
 
-### 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**:
-- `analysis` (default) - Read-only analysis and documentation generation
-- `write` - ⚠️ Create/modify codebase files (requires explicit specification, auto-enables --approval-mode yolo)
-
-**For Qwen**:
-- `analysis` (default) - Architecture analysis only, no code generation/modification (read-only)
-- `write` - ⚠️ Code generation (requires explicit specification, disabled by default)
-
-**For Codex**:
-- `auto` - ⚠️ Autonomous development with full file operations (requires explicit specification, enables -s danger-full-access)
-- `write` - ⚠️ Test generation and file modification (requires explicit specification)
-- **Default**: No default mode, MODE must be explicitly specified
-
-### Directory Context
+### Directory Context Configuration
 Tools execute in current working directory:
 - **Gemini**: `cd path/to/project && ~/.claude/scripts/gemini-wrapper -p "prompt"`
 - **Qwen**: `cd path/to/project && ~/.claude/scripts/qwen-wrapper -p "prompt"`
@@ -114,7 +204,7 @@ Tools execute in current working directory:
 - **Path types**: Supports both relative (`../project`) and absolute (`/full/path`) paths
 - **Token analysis**: For gemini-wrapper and qwen-wrapper, token counting happens in current directory
 
-### Rules Field Format
+### RULES Field Format
 ```bash
 RULES: $(cat "~/.claude/workflows/cli-templates/prompts/[category]/[template].txt") | [constraints]
 ```
@@ -125,7 +215,44 @@ RULES: $(cat "~/.claude/workflows/cli-templates/prompts/[category]/[template].tx
 - No template: `Focus on security patterns, include dependency analysis`
 - File patterns: `@{src/**/*.ts,CLAUDE.md} - Stay within scope`
 
-## 📊 Tool Selection Matrix
+### File Pattern Reference
+- All files: `@{**/*}`
+- Source files: `@{src/**/*}`
+- TypeScript: `@{*.ts,*.tsx}`
+- With docs: `@{CLAUDE.md,**/*CLAUDE.md}`
+- Tests: `@{src/**/*.test.*}`
+
+**Complex Pattern Discovery**:
+For complex file pattern requirements, use semantic discovery tools BEFORE CLI execution:
+- **rg (ripgrep)**: Content-based file discovery with regex patterns
+- **Code Index MCP**: Semantic file search based on task requirements
+- **Workflow**: Discover → Extract precise paths → Build CONTEXT field
+
+**Example**:
+```bash
+# Step 1: Discover files semantically
+rg "export.*Component" --files-with-matches --type ts  # Find component files
+mcp__code-index__search_code_advanced(pattern="interface.*Props", file_pattern="*.tsx")  # Find interface files
+
+# Step 2: Build precise CONTEXT from discovery results
+CONTEXT: @{src/components/Auth.tsx,src/types/auth.d.ts,src/hooks/useAuth.ts}
+
+# Step 3: Execute CLI with precise file references
+cd src && ~/.claude/scripts/gemini-wrapper -p "
+PURPOSE: Analyze authentication components
+TASK: Review auth component patterns and props interfaces
+MODE: analysis
+CONTEXT: @{components/Auth.tsx,types/auth.d.ts,hooks/useAuth.ts}
+EXPECTED: Pattern analysis and improvement suggestions
+RULES: Focus on type safety and component composition
+"
+```
+
+---
+
+## 📊 Tool Selection Guide
+
+### Selection Matrix
 
 | Task Type | Tool | Use Case | Template |
 |-----------|------|----------|-----------|
@@ -138,11 +265,11 @@ RULES: $(cat "~/.claude/workflows/cli-templates/prompts/[category]/[template].tx
 | **Security** | Codex | Vulnerability assessment, fixes | `analysis/security.txt` |
 | **Refactoring** | Multiple | Gemini for analysis, Qwen/Codex for execution | `development/refactor.txt` |
 
-## 📁 Template System
+### Template System
 
 **Base Structure**: `~/.claude/workflows/cli-templates/`
 
-### Available Templates
+#### Available Templates
 ```
 prompts/
 ├── analysis/
@@ -168,6 +295,8 @@ tech-stacks/
 └── react-dev.md         - React architecture
 ```
 
+---
+
 ## 🚀 Usage Patterns
 
 ### Workflow Integration (REQUIRED)
@@ -179,8 +308,9 @@ When planning any coding task, **ALWAYS** integrate CLI tools:
 4. **Quality Phase**: Use Codex for testing and validation
 
 ### Common Scenarios
+
+#### Code Analysis
 ```bash
-# Gemini - Code Analysis
 ~/.claude/scripts/gemini-wrapper -p "
 PURPOSE: Understand codebase architecture
 TASK: Analyze project structure and identify patterns
@@ -189,8 +319,10 @@ CONTEXT: @{src/**/*.ts,CLAUDE.md} Previous analysis of auth system
 EXPECTED: Architecture overview and integration points
 RULES: $(cat '~/.claude/workflows/cli-templates/prompts/analysis/architecture.txt') | Focus on integration points
 "
+```
 
-# Gemini - Generate Documentation
+#### Documentation Generation
+```bash
 ~/.claude/scripts/gemini-wrapper -p "
 PURPOSE: Generate API documentation
 TASK: Create comprehensive API reference from code
@@ -199,8 +331,10 @@ CONTEXT: @{src/api/**/*}
 EXPECTED: API.md with all endpoints documented
 RULES: Follow project documentation standards
 "
+```
 
-# Qwen - Architecture Analysis
+#### Architecture Analysis
+```bash
 cd src/auth && ~/.claude/scripts/qwen-wrapper -p "
 PURPOSE: Analyze authentication system architecture
 TASK: Review JWT-based auth system design
@@ -209,8 +343,11 @@ CONTEXT: @{src/auth/**/*} Existing patterns and requirements
 EXPECTED: Architecture analysis report with recommendations
 RULES: $(cat '~/.claude/workflows/cli-templates/prompts/analysis/architecture.txt') | Focus on security
 "
+```
 
-# Codex - Feature Development
+#### Feature Development (Multi-task with Resume)
+```bash
+# First task - establish session
 codex -C path/to/project --full-auto exec "
 PURPOSE: Implement user authentication
 TASK: Create JWT-based authentication system
@@ -220,74 +357,46 @@ EXPECTED: Complete auth module with tests
 RULES: $(cat '~/.claude/workflows/cli-templates/prompts/development/feature.txt') | Follow security best practices
 " --skip-git-repo-check -s danger-full-access
 
-# Codex - Test Generation
-codex -C src/auth --full-auto exec "
+# Continue in same session - Add JWT validation
+codex --full-auto exec "
+PURPOSE: Enhance authentication security
+TASK: Add JWT token validation and refresh logic
+MODE: auto
+CONTEXT: Previous auth implementation from current session
+EXPECTED: JWT validation middleware and token refresh endpoints
+RULES: Follow JWT best practices, maintain session context
+" resume --last --skip-git-repo-check -s danger-full-access
+
+# Continue in same session - Add tests
+codex --full-auto exec "
 PURPOSE: Increase test coverage
 TASK: Generate comprehensive tests for auth module
 MODE: write
-CONTEXT: @{**/*.ts} Exclude existing tests
+CONTEXT: Auth implementation from current session
 EXPECTED: Complete test suite with 80%+ coverage
 RULES: Use Jest, follow existing patterns
-" --skip-git-repo-check -s danger-full-access
+" resume --last --skip-git-repo-check -s danger-full-access
 ```
 
-## 📋 Planning Checklist
+#### Interactive Session Resume
+```bash
+# Resume previous session with picker
+codex resume
 
-For every development task:
-- [ ] **Purpose defined** - Clear goal and intent
-- [ ] **Mode selected** - Execution mode and permission level determined
-- [ ] **Context gathered** - File references and session memory documented
-- [ ] **Gemini analysis** completed for understanding
-- [ ] **Template selected** - Appropriate template chosen
-- [ ] **Constraints specified** - File patterns, scope, requirements
-- [ ] **Implementation approach** - Tool selection and workflow
-- [ ] **Quality measures** - Testing and validation plan
-- [ ] **Tool configuration** - Review `.gemini/CLAUDE.md` or `.codex/Agent.md` if needed
+# Or resume most recent session directly
+codex resume --last
+```
 
-## 🎯 Key Features
-
-### Gemini
-- **Command**: `~/.claude/scripts/gemini-wrapper`
-- **Strengths**: Large context window, pattern recognition
-- **Best For**: Analysis, documentation generation, code exploration
-- **Permissions**: Default read-only analysis, MODE=write requires explicit specification (auto-enables --approval-mode yolo)
-- **Default MODE**: `analysis` (read-only)
-- **⚠️ Write Trigger**: Only when user explicitly requests "generate documentation", "modify code", or specifies MODE=write
-
-### Qwen
-- **Command**: `~/.claude/scripts/qwen-wrapper`
-- **Strengths**: Architecture analysis, pattern recognition
-- **Best For**: System design analysis, architectural review
-- **Permissions**: Architecture analysis only, no automatic code generation
-- **Default MODE**: `analysis` (read-only)
-- **⚠️ Write Trigger**: Explicitly prohibited from auto-calling write mode
-
-### Codex
-- **Command**: `codex --full-auto exec`
-- **Strengths**: Autonomous development, mathematical reasoning
-- **Best For**: Implementation, testing, automation
-- **Permissions**: Requires explicit MODE=auto or MODE=write specification
-- **Default MODE**: No default, must be explicitly specified
-- **⚠️ Write Trigger**: Only when user explicitly requests "implement", "modify", "generate code" AND specifies MODE
-- **Session Management**:
-  - `codex resume` - Resume previous interactive session (picker by default)
-  - `codex exec "task" resume --last` - Continue most recent session with new task (maintains context)
-  - `codex -i <image_file>` - Attach image(s) to initial prompt (useful for UI/design references)
-  - **Multi-task Pattern**: First task uses `exec`, subsequent tasks use `exec "..." resume --last` for context continuity
-
-### File Patterns
-- All files: `@{**/*}`
-- Source files: `@{src/**/*}`
-- TypeScript: `@{*.ts,*.tsx}`
-- With docs: `@{CLAUDE.md,**/*CLAUDE.md}`
-- Tests: `@{src/**/*.test.*}`
+---
 
 ## 🔧 Best Practices
 
+### General Guidelines
 - **Start with templates** - Use predefined templates for consistency
 - **Be specific** - Clear PURPOSE, TASK, and EXPECTED fields
 - **Include constraints** - File patterns, scope, requirements in RULES
-- **Test patterns first** - Validate file patterns with `ls`
+- **Discover patterns first** - Use rg/MCP for complex file discovery before CLI execution
+- **Build precise CONTEXT** - Convert discovery results to explicit file references
 - **Document context** - Always reference CLAUDE.md for context
 
 ### Context Optimization Strategy
@@ -329,4 +438,42 @@ CONTEXT: @{**/*.ts}
 EXPECTED: Code improvements and fixes
 RULES: Maintain backward compatibility
 " --skip-git-repo-check -s danger-full-access
-```
+```
+
+### Planning Checklist
+
+For every development task:
+- [ ] **Purpose defined** - Clear goal and intent
+- [ ] **Mode selected** - Execution mode and permission level determined
+- [ ] **Context gathered** - File references and session memory documented
+- [ ] **Gemini analysis** completed for understanding
+- [ ] **Template selected** - Appropriate template chosen
+- [ ] **Constraints specified** - File patterns, scope, requirements
+- [ ] **Implementation approach** - Tool selection and workflow
+- [ ] **Quality measures** - Testing and validation plan
+- [ ] **Tool configuration** - Review `.gemini/CLAUDE.md` or `.codex/Agent.md` if needed
+
+---
+
+## ⚙️ Execution Configuration
+
+### Core Execution Rules
+- **Dynamic Timeout (20-120min)**: Allocate execution time based on task complexity
+  - Simple tasks (analysis, search): 20-40min (1200000-2400000ms)
+  - Medium tasks (refactoring, documentation): 40-60min (2400000-3600000ms)
+  - Complex tasks (implementation, migration): 60-120min (3600000-7200000ms)
+- **Codex Multiplier**: Codex commands use 1.5x of allocated time
+- **Apply to All Tools**: All bash() wrapped commands including Gemini, Qwen wrapper and Codex executions
+- **Command Examples**: `bash(~/.claude/scripts/gemini-wrapper -p "prompt")`, `bash(codex -C directory --full-auto exec "task")`
+- **Auto-detect**: Analyze PURPOSE and TASK fields to determine appropriate timeout
+
+### Permission Framework
+- **⚠️ WRITE PROTECTION**: Local codebase write/modify requires EXPLICIT user confirmation
+  - **Analysis Mode (default)**: Read-only, safe for auto-execution
+  - **Write Mode**: Requires user explicitly states MODE=write or MODE=auto in prompt
+  - **Exception**: User provides clear instructions like "modify", "create", "implement"
+- **Gemini/Qwen Write Access**: Use `--approval-mode yolo` ONLY when MODE=write explicitly specified
+  - **Parameter Position**: Place AFTER the wrapper command: `gemini-wrapper --approval-mode yolo -p "..."`
+- **Codex Write Access**: Use `-s danger-full-access` and `--skip-git-repo-check` ONLY when MODE=auto explicitly specified
+  - **Parameter Position**: Place AFTER the prompt string at command END: `codex ... exec "..." --skip-git-repo-check -s danger-full-access`
+- **Default Behavior**: All tools default to analysis/read-only mode without explicit write permission

.codex/AGENTS.md

@@ -46,6 +46,30 @@ RULES: Build on previous subtask, maintain consistency
 
 ## Execution Requirements
 
+### System Optimization
+
+**Hard Requirement**: Call binaries directly in `functions.shell`, always set `workdir`, and avoid shell wrappers such as `bash -lc`, `sh -lc`, `zsh -lc`, `cmd /c`, `pwsh.exe -NoLogo -NoProfile -Command`, and `powershell.exe -NoLogo -NoProfile -Command`.
+
+**Text Editing Priority**: Use the `apply_patch` tool for all routine text edits; fall back to `sed` for single-line substitutions only if `apply_patch` is unavailable, and avoid `python` editing scripts unless both options fail.
+
+**`apply_patch` Usage**: Invoke `apply_patch` with the patch payload as the second element in the command array (no shell-style flags). Provide `workdir` and, when helpful, a short `justification` alongside the command.
+
+**Example invocation**:
+```json
+{
+  "command": ["apply_patch", "*** Begin Patch\n*** Update File: path/to/file\n@@\n- old\n+ new\n*** End Patch\n"],
+  "workdir": "<workdir>",
+  "justification": "Brief reason for the change"
+}
+```
+
+**Windows UTF-8 Encoding**: Before executing commands on Windows systems, ensure proper UTF-8 encoding by running:
+```powershell
+[Console]::InputEncoding  = [Text.UTF8Encoding]::new($false)
+[Console]::OutputEncoding = [Text.UTF8Encoding]::new($false)
+chcp 65001 > $null
+```
+
 ### ALWAYS
 
 - **Parse all fields** - Understand PURPOSE, TASK, MODE, CONTEXT, EXPECTED, RULES
@@ -58,6 +82,9 @@ RULES: Build on previous subtask, maintain consistency
 - **Match project style** - Follow existing patterns exactly
 - **Validate EXPECTED** - Ensure all deliverables are met
 - **Report context** (subtasks) - Summarize key info for next subtask
+- **Use direct binary calls** - Avoid shell wrappers for efficiency
+- **Prefer apply_patch** - Use for text edits over Python scripts
+- **Configure Windows encoding** - Set UTF-8 for Chinese character support
 
 ### NEVER
 
@@ -335,6 +362,10 @@ Subtask 3: Add authentication (resume --last)
 
 ---
 
-**Version**: 2.1.0
+**Version**: 2.2.0
 **Last Updated**: 2025-10-04
-**Changes**: Added multi-step task execution support with resume mechanism
+**Changes**:
+- Added system optimization requirements for direct binary calls
+- Added apply_patch tool priority for text editing
+- Added Windows UTF-8 encoding configuration for Chinese character support
+- Previous: Multi-step task execution support with resume mechanism

.gitignore

@@ -18,4 +18,5 @@ Thumbs.db
 
 .env
 settings.local.json
-.workflow
+.workflow
+version.json

.qwen/QWEN.md

@@ -0,0 +1,143 @@
+# QWEN Execution Protocol
+
+## Overview
+
+**Role**: QWEN - 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
+

CHANGELOG.md

@@ -5,6 +5,119 @@ All notable changes to Claude Code Workflow (CCW) will be documented in this fil
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [3.4.2] - 2025-10-05
+
+### 📚 CLI Documentation Refactoring
+
+This release focuses on eliminating redundant documentation by establishing a single source of truth (SSOT) pattern for CLI command references.
+
+#### Changed
+
+**CLI Command Documentation Refactoring**:
+- Refactored 7 CLI command documentation files to eliminate redundancy
+- Removed **681 total lines** of duplicate content across all files
+- Established implicit reference pattern to `intelligent-tools-strategy.md` (loaded in memory)
+- Preserved all unique command-specific content and capabilities
+
+**Specific File Reductions**:
+- `analyze.md`: 117→61 lines (48% reduction)
+- `chat.md`: 118→62 lines (47% reduction)
+- `execute.md`: 180→100 lines (44% reduction)
+- `codex-execute.md`: 481→473 lines (2% - preserved unique workflow content)
+- `mode/bug-index.md`: 144→75 lines (48% reduction)
+- `mode/code-analysis.md`: 188→76 lines (60% reduction)
+- `mode/plan.md`: 100→76 lines (24% reduction)
+
+**Removed Duplicate Sections**:
+- Universal Command Template (now only in `intelligent-tools-strategy.md`)
+- File Pattern Reference (centralized in strategy guide)
+- Complex Pattern Discovery (centralized in strategy guide)
+- MODE Field Definition (centralized in strategy guide)
+- Enhancement Integration details (referenced implicitly)
+- Session Persistence details (referenced implicitly)
+
+**Preserved Unique Content**:
+- Command-specific purpose and parameters
+- Unique execution flows and capabilities
+- Specialized features (YOLO permissions, task decomposition, resume patterns)
+- Command-specific examples and workflows
+- File pattern auto-detection logic for analyze command
+- Group-based execution workflow for codex-execute command
+
+#### Added
+
+**Documentation Enhancement** (prior to refactoring):
+- Enhanced file pattern examples and complex pattern discovery documentation
+- Added semantic discovery workflow integration examples
+
+#### Technical Details
+
+**Single Source of Truth Pattern**:
+All CLI commands now reference `intelligent-tools-strategy.md` for:
+- Universal command template structure
+- File pattern syntax and examples
+- Complex pattern discovery workflows
+- MODE field definitions and permissions
+- Tool-specific features and capabilities
+
+**Reference Pattern**:
+```markdown
+## Notes
+- Command templates and file patterns: see intelligent-tools-strategy.md (loaded in memory)
+```
+
+This approach reduces maintenance overhead while ensuring documentation consistency across all CLI commands.
+
+## [3.4.1] - 2025-10-04
+
+### 🎯 Multi-Tool Support for Documentation Updates
+
+This release adds flexible tool selection for CLAUDE.md documentation generation, allowing users to choose between Gemini, Qwen, or Codex based on their analysis needs.
+
+#### Added
+
+**Multi-Tool Support**:
+- **`/update-memory-full --tool <gemini|qwen|codex>`**: Choose tool for full project documentation update
+- **`/update-memory-related --tool <gemini|qwen|codex>`**: Choose tool for context-aware documentation update
+- **Default**: Gemini (documentation generation, pattern recognition)
+- **Qwen**: Architecture analysis, system design documentation
+- **Codex**: Implementation validation, code quality analysis
+
+**Script Enhancement** (`update_module_claude.sh`):
+- Added third parameter for tool selection: `<module_path> [update_type] [tool]`
+- Support for three tools with consistent parameter syntax:
+  - `gemini --all-files --yolo -p` (default)
+  - `qwen --all-files --yolo -p` (direct command, no wrapper)
+  - `codex --full-auto exec` (with danger-full-access)
+- Automatic tool routing via case statement
+- Improved logging with tool information display
+
+#### Changed
+
+**Command Documentation**:
+- Updated `/update-memory-full.md` with tool selection usage and examples
+- Updated `/update-memory-related.md` with tool selection usage and examples
+- Added tool selection strategy and rationale documentation
+
+#### Technical Details
+
+**Tool Execution Patterns**:
+```bash
+# Gemini (default)
+gemini --all-files --yolo -p "$prompt"
+
+# Qwen (architecture analysis)
+qwen --all-files --yolo -p "$prompt"
+
+# Codex (implementation validation)
+codex --full-auto exec "$prompt" --skip-git-repo-check -s danger-full-access
+```
+
+**Backward Compatibility**:
+- ✅ Existing commands without `--tool` parameter default to Gemini
+- ✅ All three tools support Layer 1-4 template system
+- ✅ No breaking changes to existing workflows
+
 ## [3.3.0] - 2025-10-04
 
 ### 🚀 CLI Tool Enhancements & Codex Multi-Step Execution

Install-Claude.ps1

@@ -63,7 +63,9 @@ param(
 
     [string]$SourceVersion = "",
 
-    [string]$SourceBranch = ""
+    [string]$SourceBranch = "",
+
+    [string]$SourceCommit = ""
 )
 
 # Set encoding for proper Unicode support
@@ -78,7 +80,10 @@ if ($PSVersionTable.PSVersion.Major -ge 6) {
 
 # Script metadata
 $ScriptName = "Claude Code Workflow System Installer"
-$Version = "2.1.0"
+$ScriptVersion = "2.2.0"  # Installer script version
+
+# Default version (will be overridden by -SourceVersion from install-remote.ps1)
+$DefaultVersion = "unknown"
 
 # Initialize backup behavior - backup is enabled by default unless NoBackup is specified
 if (-not $BackupAll -and -not $NoBackup) {
@@ -141,8 +146,15 @@ function Show-Banner {
 }
 
 function Show-Header {
+    param(
+        [string]$InstallVersion = $DefaultVersion
+    )
+
     Show-Banner
-    Write-ColorOutput "    $ScriptName v$Version" $ColorInfo
+    Write-ColorOutput "    $ScriptName v$ScriptVersion" $ColorInfo
+    if ($InstallVersion -ne "unknown") {
+        Write-ColorOutput "    Installing Claude Code Workflow v$InstallVersion" $ColorInfo
+    }
     Write-ColorOutput "    Unified workflow system with comprehensive coordination" $ColorInfo
     Write-ColorOutput "========================================================================" $ColorInfo
     if ($NoBackup) {
@@ -167,6 +179,7 @@ function Test-Prerequisites {
     $claudeMd = Join-Path $sourceDir "CLAUDE.md"
     $codexDir = Join-Path $sourceDir ".codex"
     $geminiDir = Join-Path $sourceDir ".gemini"
+    $qwenDir = Join-Path $sourceDir ".qwen"
 
     if (-not (Test-Path $claudeDir)) {
         Write-ColorOutput "ERROR: .claude directory not found in $sourceDir" $ColorError
@@ -188,6 +201,11 @@ function Test-Prerequisites {
         return $false
     }
 
+    if (-not (Test-Path $qwenDir)) {
+        Write-ColorOutput "ERROR: .qwen directory not found in $sourceDir" $ColorError
+        return $false
+    }
+
     Write-ColorOutput "Prerequisites check passed" $ColorSuccess
     return $true
 }
@@ -632,24 +650,27 @@ function Create-VersionJson {
         [string]$InstallationMode
     )
 
-    # Determine version from source or default
-    $versionNumber = if ($SourceVersion) { $SourceVersion } else { $Version }
+    # Determine version from source parameter (passed from install-remote.ps1)
+    $versionNumber = if ($SourceVersion) { $SourceVersion } else { $DefaultVersion }
     $sourceBranch = if ($SourceBranch) { $SourceBranch } else { "unknown" }
+    $commitSha = if ($SourceCommit) { $SourceCommit } else { "unknown" }
 
     # Create version.json content
     $versionInfo = @{
         version = $versionNumber
+        commit_sha = $commitSha
         installation_mode = $InstallationMode
         installation_path = $TargetClaudeDir
         installation_date_utc = (Get-Date).ToUniversalTime().ToString("yyyy-MM-ddTHH:mm:ssZ")
         source_branch = $sourceBranch
+        installer_version = $ScriptVersion
     }
 
     $versionJsonPath = Join-Path $TargetClaudeDir "version.json"
 
     try {
         $versionInfo | ConvertTo-Json | Out-File -FilePath $versionJsonPath -Encoding utf8 -Force
-        Write-ColorOutput "Created version.json: $versionNumber ($InstallationMode)" $ColorSuccess
+        Write-ColorOutput "Created version.json: $versionNumber ($commitSha) - $InstallationMode" $ColorSuccess
         return $true
     } catch {
         Write-ColorOutput "WARNING: Failed to create version.json: $($_.Exception.Message)" $ColorWarning
@@ -666,6 +687,7 @@ function Install-Global {
     $globalClaudeMd = Join-Path $globalClaudeDir "CLAUDE.md"
     $globalCodexDir = Join-Path $userProfile ".codex"
     $globalGeminiDir = Join-Path $userProfile ".gemini"
+    $globalQwenDir = Join-Path $userProfile ".qwen"
 
     Write-ColorOutput "Global installation path: $userProfile" $ColorInfo
 
@@ -675,11 +697,12 @@ function Install-Global {
     $sourceClaudeMd = Join-Path $sourceDir "CLAUDE.md"
     $sourceCodexDir = Join-Path $sourceDir ".codex"
     $sourceGeminiDir = Join-Path $sourceDir ".gemini"
+    $sourceQwenDir = Join-Path $sourceDir ".qwen"
 
     # Create backup folder if needed (default behavior unless NoBackup is specified)
     $backupFolder = $null
     if (-not $NoBackup) {
-        if ((Test-Path $globalClaudeDir) -or (Test-Path $globalCodexDir) -or (Test-Path $globalGeminiDir)) {
+        if ((Test-Path $globalClaudeDir) -or (Test-Path $globalCodexDir) -or (Test-Path $globalGeminiDir) -or (Test-Path $globalQwenDir)) {
             $existingFiles = @()
             if (Test-Path $globalClaudeDir) {
                 $existingFiles += Get-ChildItem $globalClaudeDir -Recurse -File -ErrorAction SilentlyContinue
@@ -690,6 +713,9 @@ function Install-Global {
             if (Test-Path $globalGeminiDir) {
                 $existingFiles += Get-ChildItem $globalGeminiDir -Recurse -File -ErrorAction SilentlyContinue
             }
+            if (Test-Path $globalQwenDir) {
+                $existingFiles += Get-ChildItem $globalQwenDir -Recurse -File -ErrorAction SilentlyContinue
+            }
             if (($existingFiles -and ($existingFiles | Measure-Object).Count -gt 0)) {
                 $backupFolder = Get-BackupDirectory -TargetDirectory $userProfile
                 Write-ColorOutput "Backup folder created: $backupFolder" $ColorInfo
@@ -717,6 +743,10 @@ function Install-Global {
     Write-ColorOutput "Merging .gemini directory contents..." $ColorInfo
     $geminiMerged = Merge-DirectoryContents -Source $sourceGeminiDir -Destination $globalGeminiDir -Description ".gemini directory contents" -BackupFolder $backupFolder
 
+    # Merge .qwen directory contents
+    Write-ColorOutput "Merging .qwen directory contents..." $ColorInfo
+    $qwenMerged = Merge-DirectoryContents -Source $sourceQwenDir -Destination $globalQwenDir -Description ".qwen directory contents" -BackupFolder $backupFolder
+
     # Create version.json in global .claude directory
     Write-ColorOutput "Creating version.json..." $ColorInfo
     Create-VersionJson -TargetClaudeDir $globalClaudeDir -InstallationMode "Global"
@@ -753,16 +783,18 @@ function Install-Path {
     $sourceClaudeMd = Join-Path $sourceDir "CLAUDE.md"
     $sourceCodexDir = Join-Path $sourceDir ".codex"
     $sourceGeminiDir = Join-Path $sourceDir ".gemini"
+    $sourceQwenDir = Join-Path $sourceDir ".qwen"
 
-    # Local paths - for agents, commands, output-styles, .codex, .gemini
+    # Local paths - for agents, commands, output-styles, .codex, .gemini, .qwen
     $localClaudeDir = Join-Path $TargetDirectory ".claude"
     $localCodexDir = Join-Path $TargetDirectory ".codex"
     $localGeminiDir = Join-Path $TargetDirectory ".gemini"
+    $localQwenDir = Join-Path $TargetDirectory ".qwen"
 
     # Create backup folder if needed
     $backupFolder = $null
     if (-not $NoBackup) {
-        if ((Test-Path $localClaudeDir) -or (Test-Path $localCodexDir) -or (Test-Path $localGeminiDir) -or (Test-Path $globalClaudeDir)) {
+        if ((Test-Path $localClaudeDir) -or (Test-Path $localCodexDir) -or (Test-Path $localGeminiDir) -or (Test-Path $localQwenDir) -or (Test-Path $globalClaudeDir)) {
             $backupFolder = Get-BackupDirectory -TargetDirectory $TargetDirectory
             Write-ColorOutput "Backup folder created: $backupFolder" $ColorInfo
         }
@@ -858,6 +890,10 @@ function Install-Path {
     Write-ColorOutput "Merging .gemini directory contents to local location..." $ColorInfo
     $geminiMerged = Merge-DirectoryContents -Source $sourceGeminiDir -Destination $localGeminiDir -Description ".gemini directory contents" -BackupFolder $backupFolder
 
+    # Merge .qwen directory contents to local location
+    Write-ColorOutput "Merging .qwen directory contents to local location..." $ColorInfo
+    $qwenMerged = Merge-DirectoryContents -Source $sourceQwenDir -Destination $localQwenDir -Description ".qwen directory contents" -BackupFolder $backupFolder
+
     # Create version.json in local .claude directory
     Write-ColorOutput "Creating version.json in local directory..." $ColorInfo
     Create-VersionJson -TargetClaudeDir $localClaudeDir -InstallationMode "Path"
@@ -971,11 +1007,11 @@ function Show-Summary {
     if ($Mode -eq "Path") {
         Write-Host "  Local Path: $Path"
         Write-Host "  Global Path: $([Environment]::GetFolderPath('UserProfile'))"
-        Write-Host "  Local Components: agents, commands, output-styles, .codex, .gemini"
+        Write-Host "  Local Components: agents, commands, output-styles, .codex, .gemini, .qwen"
         Write-Host "  Global Components: workflows, scripts, python_script, etc."
     } else {
         Write-Host "  Path: $Path"
-        Write-Host "  Global Components: .claude, .codex, .gemini"
+        Write-Host "  Global Components: .claude, .codex, .gemini, .qwen"
     }
 
     if ($NoBackup) {
@@ -991,10 +1027,11 @@ function Show-Summary {
     Write-Host "1. Review CLAUDE.md - Customize guidelines for your project"
     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 "4. Review .qwen/QWEN.md - Qwen agent execution protocol"
+    Write-Host "5. Configure settings - Edit .claude/settings.local.json as needed"
+    Write-Host "6. Start using Claude Code with Agent workflow coordination!"
+    Write-Host "7. Use /workflow commands for task execution"
+    Write-Host "8. Use /update-memory commands for memory system management"
 
     Write-Host ""
     Write-ColorOutput "Documentation: https://github.com/catlog22/Claude-CCW" $ColorInfo
@@ -1002,7 +1039,10 @@ function Show-Summary {
 }
 
 function Main {
-    Show-Header
+    # Use SourceVersion parameter if provided, otherwise use default
+    $installVersion = if ($SourceVersion) { $SourceVersion } else { $DefaultVersion }
+
+    Show-Header -InstallVersion $installVersion
 
     # Test prerequisites
     Write-ColorOutput "Checking system requirements..." $ColorInfo

README.md

@@ -2,7 +2,7 @@
 
 <div align="center">
 
-[![Version](https://img.shields.io/badge/version-v3.4.0-blue.svg)](https://github.com/catlog22/Claude-Code-Workflow/releases)
+[![Version](https://img.shields.io/badge/version-v3.4.2-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)
@@ -15,15 +15,15 @@
 
 **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: v3.4.0** - TDD workflow optimization & test generation enhancements. See [CHANGELOG.md](CHANGELOG.md) for details.
+> **🎉 Latest: v3.4.2** - CLI documentation refactoring & single source of truth. See [CHANGELOG.md](CHANGELOG.md) for details.
 >
-> **What's New in v3.4.0**:
-> - 🧪 **TDD Workflow Streamlining**: Unified IMPL_PLAN.md structure, 33% reduction in redundant files
-> - 🔄 **Test Coverage Analysis**: TDD workflow upgraded to 6 phases with Phase 3 test context gathering
-> - 🔁 **Iterative Green Phase**: Built-in test-fix-cycle in IMPL tasks with Gemini auto-diagnosis
-> - 🛠️ **Manual-First Fixes**: Gemini + bug-fix template diagnosis by default, optional `--use-codex` automation
-> - ✅ **Test-Gen Workflow Enhancement**: Added 3 supporting tool commands for complete test generation flow
-> - ⏱️ **Dynamic Timeout Allocation**: CLI tools default to 20-120min for large-scale analysis
+> **What's New in v3.4.2**:
+> - 📚 **CLI Documentation Refactoring**: Eliminated 681 lines of duplicate content across 7 command files
+> - 🎯 **Single Source of Truth**: Established implicit reference pattern to `intelligent-tools-strategy.md`
+> - 🔍 **Documentation Consistency**: All CLI commands now reference centralized strategy guide
+> - 💡 **Maintenance Optimization**: Reduced maintenance overhead while preserving unique command features
+> - ✨ **Enhanced Clarity**: Streamlined documentation focuses on command-specific capabilities
+> - 📖 **Better Organization**: File patterns, templates, and MODE definitions centralized
 
 ---
 

README_CN.md

@@ -2,7 +2,7 @@
 
 <div align="center">
 
-[![Version](https://img.shields.io/badge/version-v3.4.0-blue.svg)](https://github.com/catlog22/Claude-Code-Workflow/releases)
+[![Version](https://img.shields.io/badge/version-v3.4.2-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)
@@ -15,15 +15,15 @@
 
 **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: v3.4.0** - TDD 工作流优化与测试生成增强。详见 [CHANGELOG.md](CHANGELOG.md)。
+> **🎉 最新版本: v3.4.2** - CLI 文档重构与单一信息源。详见 [CHANGELOG.md](CHANGELOG.md)。
 >
-> **v3.4.0 版本新特性**:
-> - 🧪 **TDD 工作流优化**: 精简文件结构，统一使用 IMPL_PLAN.md，减少 33% 冗余文件
-> - 🔄 **测试覆盖分析**: TDD 工作流升级至 6 阶段，新增 Phase 3 测试上下文收集
-> - 🔁 **迭代 Green Phase**: IMPL 任务内置 test-fix-cycle，支持 Gemini 自动诊断和修复
-> - 🛠️ **手动优先修复**: 默认使用 Gemini + bug-fix 模板诊断，可选 `--use-codex` 自动化
-> - ✅ **test-gen 工作流增强**: 新增 3 个配套工具命令，完整测试生成和修复流程
-> - ⏱️ **动态超时分配**: CLI 工具默认 20-120 分钟超时，适应大型项目分析
+> **v3.4.2 版本新特性**:
+> - 📚 **CLI 文档重构**: 消除 7 个命令文件中的 681 行重复内容
+> - 🎯 **单一信息源**: 建立对 `intelligent-tools-strategy.md` 的隐式引用模式
+> - 🔍 **文档一致性**: 所有 CLI 命令现在引用集中的策略指南
+> - 💡 **维护优化**: 降低维护开销，同时保留独特的命令功能
+> - ✨ **增强清晰度**: 精简的文档专注于命令特定功能
+> - 📖 **更好的组织**: 文件模式、模板和 MODE 定义集中化
 
 ---
 

install-remote.ps1

@@ -260,7 +260,8 @@ function Invoke-LocalInstaller {
     param(
         [string]$RepoDir,
         [string]$VersionInfo = "",
-        [string]$BranchInfo = ""
+        [string]$BranchInfo = "",
+        [string]$CommitSha = ""
     )
 
     $installerPath = Join-Path $RepoDir "Install-Claude.ps1"
@@ -285,9 +286,10 @@ function Invoke-LocalInstaller {
     if ($NonInteractive) { $params["NonInteractive"] = $NonInteractive }
     if ($BackupAll) { $params["BackupAll"] = $BackupAll }
 
-    # Pass version and branch information
+    # Pass version, branch, and commit information
     if ($VersionInfo) { $params["SourceVersion"] = $VersionInfo }
     if ($BranchInfo) { $params["SourceBranch"] = $BranchInfo }
+    if ($CommitSha) { $params["SourceCommit"] = $CommitSha }
 
     try {
         # Change to repo directory and run installer
@@ -562,14 +564,51 @@ function Main {
             throw "Extraction failed"
         }
 
+        # Get commit SHA from the downloaded repository first
+        $commitSha = ""
+        try {
+            Push-Location $repoDir
+            $commitSha = (git rev-parse --short HEAD 2>$null)
+            if (-not $commitSha) {
+                # Fallback: try to get from GitHub API
+                $commitUrl = "https://api.github.com/repos/catlog22/Claude-Code-Workflow/commits/$Branch"
+                $commitResponse = Invoke-RestMethod -Uri $commitUrl -UseBasicParsing -TimeoutSec 5 -ErrorAction SilentlyContinue
+                if ($commitResponse.sha) {
+                    $commitSha = $commitResponse.sha.Substring(0, 7)
+                }
+            }
+            Pop-Location
+        } catch {
+            Pop-Location
+            $commitSha = "unknown"
+        }
+
         # Determine version and branch information to pass
-        $versionToPass = if ($Tag) { $Tag } else { "latest" }
+        $versionToPass = ""
+
+        if ($Tag) {
+            # Specific tag version
+            $versionToPass = $Tag -replace '^v', ''  # Remove 'v' prefix
+        } elseif ($Version -eq "stable") {
+            # Auto-detected latest stable
+            $latestTag = Get-LatestRelease
+            if ($latestTag) {
+                $versionToPass = $latestTag -replace '^v', ''
+            } else {
+                # Fallback: use commit SHA as version
+                $versionToPass = "dev-$commitSha"
+            }
+        } else {
+            # Latest development or branch - use commit SHA as version
+            $versionToPass = "dev-$commitSha"
+        }
+
         $branchToPass = if ($Version -eq "branch") { $Branch } elseif ($Version -eq "latest") { "main" } elseif ($Tag) { $Tag } else { "main" }
 
-        Write-ColorOutput "Version info: $versionToPass (branch: $branchToPass)" $ColorInfo
+        Write-ColorOutput "Version info: $versionToPass (branch: $branchToPass, commit: $commitSha)" $ColorInfo
 
         # Run local installer with version information
-        $success = Invoke-LocalInstaller -RepoDir $repoDir -VersionInfo $versionToPass -BranchInfo $branchToPass
+        $success = Invoke-LocalInstaller -RepoDir $repoDir -VersionInfo $versionToPass -BranchInfo $branchToPass -CommitSha $commitSha
         if (-not $success) {
             throw "Installation script failed"
         }

install-remote.sh

@@ -209,6 +209,9 @@ function extract_repository() {
 
 function invoke_local_installer() {
     local repo_dir="$1"
+    local version_info="$2"
+    local branch_info="$3"
+    local commit_sha="$4"
     local installer_path="${repo_dir}/Install-Claude.sh"
 
     # Make installer executable
@@ -249,6 +252,19 @@ function invoke_local_installer() {
         params+=("-BackupAll")
     fi
 
+    # Pass version, branch, and commit information
+    if [ -n "$version_info" ]; then
+        params+=("-SourceVersion" "$version_info")
+    fi
+
+    if [ -n "$branch_info" ]; then
+        params+=("-SourceBranch" "$branch_info")
+    fi
+
+    if [ -n "$commit_sha" ]; then
+        params+=("-SourceCommit" "$commit_sha")
+    fi
+
     # Execute installer
     if (cd "$repo_dir" && "$installer_path" "${params[@]}"); then
         return 0
@@ -632,8 +648,54 @@ function main() {
         if [ $extract_status -eq 0 ] && [ -n "$repo_dir" ] && [ -d "$repo_dir" ]; then
             write_color "Extraction successful: $repo_dir" "$COLOR_SUCCESS"
 
-            # Run local installer
-            if invoke_local_installer "$repo_dir"; then
+            # Get commit SHA from the downloaded repository first
+            local commit_sha=""
+            if command -v git &> /dev/null && [ -d "$repo_dir/.git" ]; then
+                commit_sha=$(cd "$repo_dir" && git rev-parse --short HEAD 2>/dev/null || echo "unknown")
+            else
+                # Fallback: try to get from GitHub API
+                local temp_branch="main"
+                [ "$VERSION_TYPE" = "branch" ] && temp_branch="$BRANCH"
+                commit_sha=$(curl -fsSL "https://api.github.com/repos/catlog22/Claude-Code-Workflow/commits/$temp_branch" 2>/dev/null | grep -o '"sha": *"[^"]*"' | head -1 | cut -d'"' -f4 | cut -c1-7)
+                [ -z "$commit_sha" ] && commit_sha="unknown"
+            fi
+
+            # Determine version and branch information to pass
+            local version_to_pass=""
+            local branch_to_pass=""
+
+            if [ -n "$TAG_VERSION" ]; then
+                # Specific tag version - remove 'v' prefix
+                version_to_pass="${TAG_VERSION#v}"
+            elif [ "$VERSION_TYPE" = "stable" ]; then
+                # Auto-detected latest stable
+                local latest_tag
+                latest_tag=$(get_latest_release)
+                if [ -n "$latest_tag" ]; then
+                    version_to_pass="${latest_tag#v}"
+                else
+                    # Fallback: use commit SHA as version
+                    version_to_pass="dev-$commit_sha"
+                fi
+            else
+                # Latest development or branch - use commit SHA as version
+                version_to_pass="dev-$commit_sha"
+            fi
+
+            if [ "$VERSION_TYPE" = "branch" ]; then
+                branch_to_pass="$BRANCH"
+            elif [ "$VERSION_TYPE" = "latest" ]; then
+                branch_to_pass="main"
+            elif [ -n "$TAG_VERSION" ]; then
+                branch_to_pass="$TAG_VERSION"
+            else
+                branch_to_pass="main"
+            fi
+
+            write_color "Version info: $version_to_pass (branch: $branch_to_pass, commit: $commit_sha)" "$COLOR_INFO"
+
+            # Run local installer with version information
+            if invoke_local_installer "$repo_dir" "$version_to_pass" "$branch_to_pass" "$commit_sha"; then
                 success=true
                 echo ""
                 write_color "✓ Remote installation completed successfully!" "$COLOR_SUCCESS"