release: v3.3.0 - CLI Tool Enhancements & Codex Multi-Step Execution

✨ Features: - New /cli:codex-execute command for automated multi-step task execution - Codex resume mechanism (codex exec "..." resume --last) for context continuity - TodoWrite progress tracking for subtask execution - Optional Git verification after each subtask (--verify-git flag) - Automatic task JSON detection and loading - Enhanced Codex agent configuration (.codex/AGENTS.md v2.1.0) 📚 Documentation: - Streamlined CLI documentation (60% reduction in redundancy) - Updated /cli:analyze, /cli:chat, /cli:execute commands - Enhanced intelligent-tools-strategy.md with Codex resume patterns - Unified command templates for Gemini/Qwen vs Codex - Added Codex -i parameter documentation for image attachment 🔧 Technical: - Multi-task prompt format (Single-Task & Multi-Task) - Subtask coordination guidelines and best practices - Enhanced MODE: auto with subtask execution flow - Progress reporting for multi-step workflows 📦 Updates: - Version bumped to 3.3.0 in README.md, README_CN.md - Created .claude/version.json for version tracking - Comprehensive CHANGELOG.md entry with all changes 🤖 Generated with Claude Code (https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
refactor: Enhance tool write protection and lower Bash requirement
2026-02-05 01:50:27 +08:00 · 2025-10-04 00:51:34 +08:00 · 2025-10-04 00:09:17 +08:00 · 2025-10-03 23:56:09 +08:00 · 2025-10-03 21:23:23 +08:00 · 2025-10-03 13:46:44 +08:00
28 changed files with 1600 additions and 965 deletions
--- a/.claude/commands/cli/analyze.md
+++ b/.claude/commands/cli/analyze.md
@@ -17,185 +17,68 @@ allowed-tools: SlashCommand(*), Bash(*), TodoWrite(*), Read(*), Glob(*)
 Execute CLI tool analysis on codebase patterns, architecture, or code quality.

 **Supported Tools**: codex, gemini (default), qwen
+**Reference**: @~/.claude/workflows/intelligent-tools-strategy.md for complete tool details

 ## Execution Flow

-1. **Parse tool selection**: Extract `--tool` flag (default: gemini)
-2. **If `--enhance` flag present**: Execute `/enhance-prompt "[analysis-target]"` and use enhanced output
-3. Parse analysis target (original or enhanced)
-4. Detect analysis type (pattern/architecture/security/quality)
-5. Build command for selected tool with template
-6. Execute analysis
-7. Return results
-
-## Core Rules
-
-1. **Tool Selection**: Use `--tool` value or default to gemini
-2. **Enhance First (if flagged)**: Execute `/enhance-prompt` before analysis when `--enhance` present
-3. **Execute Immediately**: Build and run command without preliminary analysis
-4. **Template Selection**: Auto-select template based on keywords
-5. **Context Inclusion**: Always include CLAUDE.md in context
-6. **Direct Output**: Return tool output directly to user
-
-## Tool Selection
-
-| Tool | Wrapper | Best For | Permissions |
-|------|---------|----------|-------------|
-| **gemini** (default) | `~/.claude/scripts/gemini-wrapper` | Analysis, exploration, documentation | Read-only |
-| **qwen** | `~/.claude/scripts/qwen-wrapper` | Architecture, code generation | Read-only for analyze |
-| **codex** | `codex --full-auto exec` | Development analysis, deep inspection | `-s danger-full-access --skip-git-repo-check` |
+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

 ## Enhancement Integration

-**When `--enhance` flag present**:
+**When `--enhance` flag present**: Execute `/enhance-prompt "[analysis-target]"` first, then use enhanced output (INTENT/CONTEXT/ACTION) to build the analysis command.
+
+
+## Command Template
+
+**Gemini/Qwen**:
 ```bash
-# Step 1: Enhance the prompt
-SlashCommand(command="/enhance-prompt \"[analysis-target]\"")
-
-# Step 2: Use enhanced output as analysis target
-# Enhanced output provides:
-# - INTENT: Clear technical goal
-# - CONTEXT: Session memory + patterns
-# - ACTION: Implementation steps
-# - ATTENTION: Critical constraints
-```
-
-**Example**:
-```bash
-# User: /gemini:analyze --enhance "fix auth issues"
-
-# Step 1: Enhance
-/enhance-prompt "fix auth issues"
-# Returns:
-# INTENT: Debug authentication failures
-# CONTEXT: JWT implementation in src/auth/, known token expiry issue
-# ACTION: Analyze token lifecycle → verify refresh flow → check middleware
-# ATTENTION: Preserve existing session management
-
-# Step 2: Analyze with enhanced context
-cd . && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: Debug authentication failures (from enhanced: JWT token lifecycle)
-TASK: Analyze token lifecycle, refresh flow, and middleware integration
-CONTEXT: @{src/auth/**/*} @{CLAUDE.md} Session context: known token expiry issue
-EXPECTED: Root cause analysis with file references
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/security.txt) | Focus on JWT token handling
-"
-```
-
-## Analysis Types
-
-| Type | Keywords | Template | Context |
-|------|----------|----------|---------|
-| **pattern** | pattern, hooks, usage | analysis/pattern.txt | Matched files + CLAUDE.md |
-| **architecture** | architecture, structure, design | analysis/architecture.txt | Full codebase + CLAUDE.md |
-| **security** | security, vulnerability, auth | analysis/security.txt | Matched files + CLAUDE.md |
-| **quality** | quality, test, coverage | analysis/quality.txt | Source + test files + CLAUDE.md |
-
-## Command Templates
-
-### Gemini (Default)
-```bash
-cd [target-dir] && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: [analysis goal from user input]
-TASK: [specific analysis task]
+cd [dir] && ~/.claude/scripts/[gemini|qwen]-wrapper -p "
+PURPOSE: [analysis goal]
+TASK: [specific task]
 CONTEXT: @{[file-patterns]} @{CLAUDE.md}
-EXPECTED: [expected output format]
+EXPECTED: [output format]
 RULES: $(cat ~/.claude/workflows/cli-templates/prompts/[category]/[template].txt) | [constraints]
 "
 ```

-### Qwen
+**Codex**:
 ```bash
-cd [target-dir] && ~/.claude/scripts/qwen-wrapper -p "
-PURPOSE: [analysis goal from user input]
-TASK: [specific analysis task]
+codex -C [dir] --full-auto exec "
+PURPOSE: [analysis goal]
+TASK: [specific task]
 CONTEXT: @{[file-patterns]} @{CLAUDE.md}
-EXPECTED: [expected output format]
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/[category]/[template].txt) | [constraints]
-"
-```
-
-### Codex
-```bash
-codex -C [target-dir] --full-auto exec "
-PURPOSE: [analysis goal from user input]
-TASK: [specific analysis task]
-CONTEXT: @{[file-patterns]} @{CLAUDE.md}
-EXPECTED: [expected output format]
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/[category]/[template].txt) | [constraints]
+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
 ```

 ## Examples

-**Pattern Analysis (Gemini - default)**:
 ```bash
-cd . && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: Analyze authentication patterns
-TASK: Identify auth implementation patterns and conventions
-CONTEXT: @{**/*auth*} @{CLAUDE.md}
-EXPECTED: Pattern summary with file references
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/pattern.txt) | Focus on security
-"
-```
-
-**Architecture Review (Qwen)**:
-```bash
-# User: /cli:analyze --tool qwen "component architecture"
-
-cd . && ~/.claude/scripts/qwen-wrapper -p "
-PURPOSE: Review component architecture
-TASK: Analyze component structure and dependencies
-CONTEXT: @{src/**/*} @{CLAUDE.md}
-EXPECTED: Architecture diagram and integration points
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/architecture.txt) | Focus on modularity
-"
-```
-
-**Deep Inspection (Codex)**:
-```bash
-# User: /cli:analyze --tool codex "performance bottlenecks"
-
-codex -C . --full-auto exec "
-PURPOSE: Identify performance bottlenecks
-TASK: Deep analysis of performance issues
-CONTEXT: @{src/**/*} @{CLAUDE.md}
-EXPECTED: Performance metrics and optimization recommendations
-RULES: Focus on computational complexity and memory usage
-" --skip-git-repo-check -s danger-full-access
+/cli:analyze "authentication patterns"              # Gemini (default)
+/cli:analyze --tool qwen "component architecture"   # Qwen architecture
+/cli:analyze --tool codex "performance bottlenecks" # Codex deep analysis
+/cli:analyze --enhance "fix auth issues"            # Enhanced prompt first
 ```

 ## File Pattern Logic

-**Keyword Matching**:
+Auto-detect file patterns from keywords:
 - "auth" → `@{**/*auth*}`
 - "component" → `@{src/components/**/*}`
 - "API" → `@{**/api/**/*}`
 - "test" → `@{**/*.test.*}`
- Generic → `@{src/**/*}` or `@{**/*}`
+- Generic → `@{src/**/*}`

 ## Session Integration

-**Detect Active Session**: Check for `.workflow/.active-*` marker file
-
-**If Session Active**:
- Save results to `.workflow/WFS-[id]/.chat/analysis-[timestamp].md`
- Include session context in analysis
-
-**If No Session**:
- Return results directly to user
-
-## Output Format
-
-Return Gemini's output directly, which includes:
- File references (file:line format)
- Code snippets
- Pattern analysis
- Recommendations
-
-## Error Handling
-
- **Missing Template**: Use generic analysis prompt
- **No Context**: Use `@{**/*}` as fallback
- **Command Failure**: Report error and suggest manual command
+- **Active Session**: Save results to `.workflow/WFS-[id]/.chat/analysis-[timestamp].md`
+- **No Session**: Return results directly to user

--- a/.claude/commands/cli/chat.md
+++ b/.claude/commands/cli/chat.md
@@ -12,150 +12,81 @@ allowed-tools: SlashCommand(*), Bash(*)
 model: sonnet
 ---

-### 🚀 **Command Overview: `/cli:chat`**
+## Purpose

-   **Type**: CLI Tool Wrapper for Interactive Analysis
-   **Purpose**: Direct interaction with CLI tools for codebase analysis
-   **Supported Tools**: codex, gemini (default), qwen
+Direct interaction with CLI tools for codebase analysis and Q&A.

-### 📥 **Parameters & Usage**
+**Supported Tools**: codex, gemini (default), qwen
+**Reference**: @~/.claude/workflows/intelligent-tools-strategy.md for complete tool details

-   **`<inquiry>` (Required)**: Your question or analysis request
-   **`--tool <codex|gemini|qwen>` (Optional)**: Select CLI tool (default: gemini)
-   **`--enhance` (Optional)**: Enhance inquiry with `/enhance-prompt` before execution
-   **`--all-files` (Optional)**: Includes the entire codebase in the analysis context
-   **`--save-session` (Optional)**: Saves the interaction to current workflow session directory
-   **File References**: Specify files or patterns using `@{path/to/file}` syntax
+## Parameters

-### 🔄 **Execution Workflow**
+- `<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

-`Parse Tool` **->** `Parse Input` **->** `[Optional] Enhance` **->** `Assemble Context` **->** `Construct Prompt` **->** `Execute CLI Tool` **->** `(Optional) Save Session`
+## Execution Flow

-### 🛠️ **Tool Selection**
+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

-| Tool | Best For | Wrapper |
-|------|----------|---------|
-| **gemini** (default) | General analysis, exploration | `~/.claude/scripts/gemini-wrapper` |
-| **qwen** | Architecture, design patterns | `~/.claude/scripts/qwen-wrapper` |
-| **codex** | Development queries, deep analysis | `codex --full-auto exec` |
+## Enhancement Integration

-### 🔄 **Original Execution Workflow**
+**When `--enhance` flag present**: Execute `/enhance-prompt "[inquiry]"` first, then use enhanced output (INTENT/CONTEXT/ACTION) to build the chat command.

-`Parse Input` **->** `[Optional] Enhance` **->** `Assemble Context` **->** `Construct Prompt` **->** `Execute Gemini CLI` **->** `(Optional) Save Session`
+## Context Assembly

-### 🎯 **Enhancement Integration**
+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

-**When `--enhance` flag present**:
+## Command Template
+
+**Gemini/Qwen**:
 ```bash
-# Step 1: Enhance the inquiry
-SlashCommand(command="/enhance-prompt \"[inquiry]\"")
-
-# Step 2: Use enhanced output for chat
-# Enhanced output provides enriched context and structured intent
-```
-
-**Example**:
-```bash
-# User: /gemini:chat --enhance "fix the login"
-
-# Step 1: Enhance
-/enhance-prompt "fix the login"
-# Returns:
-# INTENT: Debug login authentication failure
-# CONTEXT: JWT auth in src/auth/, session state issue
-# ACTION: Check token validation → verify middleware → test flow
-
-# Step 2: Chat with enhanced context
-gemini -p "Debug login authentication failure. Focus on JWT token validation
-in src/auth/, verify middleware integration, and test authentication flow.
-Known issue: session state management"
-```
-
-### 📚 **Context Assembly**
-
-Context is gathered from:
-1. **Project Guidelines**: Always includes `@{CLAUDE.md,**/*CLAUDE.md}`
-2. **User-Explicit Files**: Files specified by the user (e.g., `@{src/auth/*.js}`)
-3. **All Files Flag**: The `--all-files` flag includes the entire codebase
-
-### 📝 **Prompt Format**
-
-**Core Guidelines**: @~/.claude/workflows/intelligent-tools-strategy.md
-
-```bash
-cd [directory] && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: [clear analysis/inquiry goal]
-TASK: [specific analysis or question]
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} @{target_files}
-EXPECTED: [expected response format]
-RULES: [constraints or focus areas]
+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 "..."
 ```

-### ⚙️ **Execution Implementation**
-
-**Standard Template**:
+**Codex**:
 ```bash
-cd . && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: [user inquiry goal]
-TASK: [specific question or analysis]
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} @{inferred_or_specified_files}
-EXPECTED: Analysis with file references and code examples
-RULES: [focus areas based on inquiry]
-"
+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
 ```

-**With --all-files flag**:
+## Examples
+
 ```bash
-cd . && ~/.claude/scripts/gemini-wrapper --all-files -p "
-PURPOSE: [user inquiry goal]
-TASK: [specific question or analysis]
-CONTEXT: @{CLAUDE.md,**/*CLAUDE.md} [entire codebase]
-EXPECTED: Comprehensive analysis across all files
-RULES: [focus areas based on inquiry]
-"
+/cli:chat "analyze the authentication flow"              # 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
 ```

-**Example - Authentication Analysis**:
-```bash
-cd . && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: Understand authentication flow implementation
-TASK: Analyze authentication flow and identify patterns
-CONTEXT: @{**/*auth*,**/*login*} @{CLAUDE.md}
-EXPECTED: Flow diagram, security assessment, integration points
-RULES: Focus on security patterns and JWT handling
-"
-```
+## Session Persistence

-**Example - Performance Optimization**:
-```bash
-cd src/components && ~/.claude/scripts/gemini-wrapper -p "
-PURPOSE: Optimize React component performance
-TASK: Identify performance bottlenecks in component rendering
-CONTEXT: @{**/*.{jsx,tsx}} @{CLAUDE.md}
-EXPECTED: Specific optimization recommendations with file:line references
-RULES: Focus on re-render patterns and memoization opportunities
-"
-```
-
-### 💾 **Session Persistence**
-
-When `--save-session` flag is used:
-   Check for existing active session (`.workflow/.active-*` markers)
-   Save to existing session's `.chat/` directory or create new session
-   File format: `chat-YYYYMMDD-HHMMSS.md`
-   Include query, context, and response in saved file
-
-**Session Template:**
-```markdown
-# Chat Session: [Timestamp]
-
-## Query
-[Original user inquiry]
-
-## Context
-[Files and patterns included in analysis]
-
-## Gemini Response
-[Complete response from Gemini CLI]
-```
+- **Active Session**: Save to `.workflow/WFS-[id]/.chat/chat-[timestamp].md`
+- **No Session**: Return results directly
--- a/.claude/commands/cli/codex-execute.md
+++ b/.claude/commands/cli/codex-execute.md
@@ -0,0 +1,309 @@
+---
+name: codex-execute
+description: Automated task decomposition and execution with Codex using resume mechanism
+usage: /cli:codex-execute [--verify-git] <task-description|task-id>
+argument-hint: "[--verify-git] task description or task-id"
+examples:
+  - /cli:codex-execute "implement user authentication system"
+  - /cli:codex-execute --verify-git "refactor API layer"
+  - /cli:codex-execute IMPL-001
+allowed-tools: SlashCommand(*), Bash(*), TodoWrite(*), Read(*), Glob(*)
+---
+
+# CLI Codex Execute Command (/cli:codex-execute)
+
+## Purpose
+
+Automated task decomposition and sequential execution with Codex, using `codex exec "..." resume --last` mechanism for continuity between subtasks.
+
+**Input**: User description or task ID (automatically loads from `.task/[ID].json` if applicable)
+**Reference**: @~/.claude/workflows/intelligent-tools-strategy.md for Codex details
+
+## Core Workflow
+
+```
+Task Input → Decompose into Subtasks → TodoWrite Tracking →
+For Each Subtask:
+  1. Execute with Codex
+  2. [Optional] Git verification
+  3. Mark complete in TodoWrite
+  4. Resume next subtask with `codex resume --last`
+→ Final Summary
+```
+
+## Parameters
+
+- `<input>` (Required): Task description or task ID (e.g., "implement auth" or "IMPL-001")
+  - If input matches task ID format, loads from `.task/[ID].json`
+  - Otherwise, uses input as task description
+- `--verify-git` (Optional): Verify git status after each subtask completion
+
+## Execution Flow
+
+### Phase 1: Input Processing & Decomposition
+
+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**:
+   - Analyze task complexity and scope
+   - Break down into 3-8 subtasks
+   - Create TodoWrite tracker with all subtasks
+   - Display decomposition for user review
+
+**Decomposition Criteria**:
+- Each subtask: 5-15 minutes completable
+- Clear, testable outcomes
+- Explicit dependencies
+- Focused file scope (1-5 files per subtask)
+
+### Phase 2: Sequential Execution
+
+**For First Subtask**:
+```bash
+# Initial execution (no resume needed)
+codex -C [dir] --full-auto exec "
+PURPOSE: [task goal]
+TASK: [subtask 1 description]
+CONTEXT: @{relevant_files} @{CLAUDE.md}
+EXPECTED: [specific deliverables]
+RULES: [constraints]
+Subtask 1 of N: [subtask title]
+" --skip-git-repo-check -s danger-full-access
+```
+
+**For Subsequent Subtasks** (using resume --last):
+```bash
+# Resume previous session for context continuity
+codex exec "
+CONTINUE TO NEXT SUBTASK:
+Subtask N of M: [subtask title]
+
+PURPOSE: [continuation goal]
+TASK: [subtask N description]
+CONTEXT: Previous work completed, now focus on @{new_relevant_files}
+EXPECTED: [specific deliverables]
+RULES: Build on previous subtask, maintain consistency
+" resume --last --skip-git-repo-check -s danger-full-access
+```
+
+### Phase 3: Verification (if --verify-git enabled)
+
+After each subtask completion:
+```bash
+# Check git status
+git status --short
+
+# Verify expected changes
+git diff --stat
+
+# Optional: Check for untracked files that should be committed
+git ls-files --others --exclude-standard
+```
+
+**Verification Checks**:
+- Files modified match subtask scope
+- No unexpected changes in unrelated files
+- No merge conflicts or errors
+- Code compiles/runs (if applicable)
+
+### Phase 4: TodoWrite Tracking
+
+**Initial Setup**:
+```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
+    { content: "Final verification and summary", status: "pending", activeForm: "Verifying and summarizing" }
+  ]
+})
+```
+
+**After Each Subtask**:
+```javascript
+TodoWrite({
+  todos: [
+    { content: "Subtask 1: [description]", status: "completed", activeForm: "Executing subtask 1" },
+    { content: "Subtask 2: [description]", status: "in_progress", activeForm: "Executing subtask 2" },
+    // ... update status
+  ]
+})
+```
+
+## 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
+
+**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
+
+**Image Support**:
+```bash
+# First subtask with design reference
+codex -C [dir] -i design.png --full-auto exec "..." --skip-git-repo-check -s danger-full-access
+
+# Resume for next subtask (image context preserved)
+codex exec "CONTINUE TO NEXT SUBTASK: ..." resume --last --skip-git-repo-check -s danger-full-access
+```
+
+## Error Handling
+
+**Subtask Failure**:
+1. Mark subtask as blocked in TodoWrite
+2. Report error details to user
+3. Pause execution for manual intervention
+4. User can choose to:
+   - Retry current subtask
+   - Continue to next subtask
+   - Abort entire task
+
+**Git Verification Failure** (if --verify-git):
+1. Show unexpected changes
+2. Pause execution
+3. Request user decision:
+   - Continue anyway
+   - Rollback and retry
+   - Manual fix
+
+**Codex Session Lost**:
+1. Detect if `codex exec "..." resume --last` fails
+2. Attempt retry with fresh session
+3. Report to user if manual intervention needed
+
+## Output Format
+
+**During Execution**:
+```
+📋 Task Decomposition:
+  1. [Subtask 1 description]
+  2. [Subtask 2 description]
+  ...
+
+▶️  Executing Subtask 1/N: [title]
+  Codex session started...
+  [Codex output]
+  ✅ Subtask 1 completed
+
+🔍 Git Verification:
+  M  src/file1.ts
+  A  src/file2.ts
+  ✅ Changes verified
+
+▶️  Executing Subtask 2/N: [title]
+  Resuming Codex session...
+  [Codex output]
+  ✅ Subtask 2 completed
+...
+
+✅ All Subtasks Completed
+📊 Summary: [file references, changes, next steps]
+```
+
+**Final Summary**:
+```markdown
+# Task Execution Summary: [Task Description]
+
+## Subtasks Completed
+1. ✅ [Subtask 1]: [files modified]
+2. ✅ [Subtask 2]: [files modified]
+...
+
+## Files Modified
+- src/file1.ts:10-50 - [changes]
+- src/file2.ts - [changes]
+
+## Git Status
+- N files modified
+- M files added
+- No conflicts
+
+## Next Steps
+- [Suggested follow-up actions]
+```
+
+## Examples
+
+**Example 1: Simple Task**
+```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
+```
+
+**Example 2: With Git Verification**
+```bash
+/cli:codex-execute --verify-git "refactor API layer to use dependency injection"
+
+# After each subtask, verifies:
+# - Only expected files modified
+# - No breaking changes in unrelated code
+# - Tests still pass
+```
+
+**Example 3: With Task ID**
+```bash
+/cli:codex-execute IMPL-001
+
+# Loads task from .task/IMPL-001.json
+# Decomposes based on task requirements
+```
+
+## Best Practices
+
+1. **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. **Context Continuity**: Let `codex resume --last` maintain context
+5. **Recovery Points**: TodoWrite provides clear progress tracking
+6. **Image References**: Attach design files for UI tasks
+
+## Input Processing
+
+**Automatic Detection**:
+- Input matches task ID pattern → Load from `.task/[ID].json`
+- Otherwise → Use as task description
+
+**Task JSON Structure** (when loading from file):
+```json
+{
+  "task_id": "IMPL-001",
+  "title": "Implement user authentication",
+  "description": "Create JWT-based auth system",
+  "acceptance_criteria": [...],
+  "scope": {...},
+  "brainstorming_refs": [...]
+}
+```
+
+**Save Results**:
+- Execution log: `.chat/codex-execute-[timestamp].md` (if workflow active)
+- Summary: `.summaries/[TASK-ID]-summary.md` (if task ID provided)
+- TodoWrite tracking embedded in session
+
+## Notes
+
+**vs. `/cli:execute`**:
+- `/cli:execute`: Single-shot execution with Gemini/Qwen/Codex
+- `/cli:codex-execute`: Multi-stage Codex execution with automatic task decomposition and resume mechanism
+
+**Input Flexibility**: Accepts both freeform descriptions and task IDs (auto-detects and loads JSON)
+
+**Context Window**: `codex exec "..." resume --last` maintains conversation history, ensuring consistency across subtasks without redundant context injection.
--- a/.claude/commands/cli/execute.md
+++ b/.claude/commands/cli/execute.md
@@ -14,222 +14,98 @@ model: sonnet

 # CLI Execute Command (/cli:execute)

-## Overview
+## Purpose

-**⚡ YOLO-enabled execution**: Auto-approves all confirmations for streamlined implementation workflow.
-
-**Purpose**: Execute implementation tasks using intelligent context inference and CLI tools with full permissions.
+Execute implementation tasks with YOLO permissions (auto-approves all confirmations).

 **Supported Tools**: codex, gemini (default), qwen
+**Reference**: @~/.claude/workflows/intelligent-tools-strategy.md for complete tool details

-**Core Guidelines**: @~/.claude/workflows/intelligent-tools-strategy.md
+## YOLO Permissions

-## 🚨 YOLO Permissions
+Auto-approves: file pattern inference, execution, file modifications, summary generation

-**All confirmations auto-approved by default:**
- ✅ File pattern inference confirmation
- ✅ Gemini execution confirmation
- ✅ File modification confirmation
- ✅ Implementation summary generation
+## Enhancement Integration

-## 🎯 Enhancement Integration
+**When `--enhance` flag present** (Description Mode only): Execute `/enhance-prompt "[description]"` first, then use enhanced output (INTENT/CONTEXT/ACTION) for execution.

-**When `--enhance` flag present** (for Description Mode only):
-```bash
-# Step 1: Enhance the description
-SlashCommand(command="/enhance-prompt \"[description]\"")
-
-# Step 2: Use enhanced output for execution
-# Enhanced output provides:
-# - INTENT: Clear technical goal
-# - CONTEXT: Session memory + codebase patterns
-# - ACTION: Specific implementation steps
-# - ATTENTION: Critical constraints
-```
-
-**Example**:
-```bash
-# User: /gemini:execute --enhance "fix login"
-
-# Step 1: Enhance
-/enhance-prompt "fix login"
-# Returns:
-# INTENT: Debug authentication failure in login flow
-# CONTEXT: JWT auth in src/auth/, known token expiry issue
-# ACTION: Fix token validation → update refresh logic → test flow
-# ATTENTION: Preserve existing session management
-
-# Step 2: Execute with enhanced context
-gemini --all-files -p "@{src/auth/**/*} @{CLAUDE.md}
-Implementation: Debug authentication failure in login flow
-Focus: Token validation, refresh logic, test flow
-Constraints: Preserve existing session management"
-```
-
-**Note**: `--enhance` only applies to Description Mode. Task ID Mode uses task JSON directly.
+**Note**: Task ID Mode uses task JSON directly (no enhancement).

 ## Execution Modes

-### 1. Description Mode (supports --enhance)
-**Input**: Natural language description
-```bash
-/gemini:execute "implement JWT authentication with middleware"
-/gemini:execute --enhance "implement JWT authentication with middleware"
-```
-**Process**: [Optional: Enhance] → Keyword analysis → Pattern inference → Context collection → Execution
+**1. Description Mode** (supports `--enhance`):
+- Input: Natural language description
+- Process: [Optional: Enhance] → Keyword analysis → Pattern inference → Execute

-### 2. Task ID Mode (no --enhance)
-**Input**: Workflow task identifier
-```bash
-/gemini:execute IMPL-001
-```
-**Process**: Task JSON parsing → Scope analysis → Context integration → Execution
+**2. Task ID Mode** (no `--enhance`):
+- Input: Workflow task identifier (e.g., `IMPL-001`)
+- Process: Task JSON parsing → Scope analysis → Execute

-## Context Inference Logic
+## Context Inference

-**Auto-selects relevant files based on:**
+Auto-selects files based on:
 - **Keywords**: "auth" → `@{**/*auth*,**/*user*}`
 - **Technology**: "React" → `@{src/**/*.{jsx,tsx}}`
 - **Task Type**: "api" → `@{**/api/**/*,**/routes/**/*}`
- **Always includes**: `@{CLAUDE.md,**/*CLAUDE.md}`
+- **Always**: `@{CLAUDE.md,**/*CLAUDE.md}`

-## Command Options
+## Options

-| Option | Purpose |
-|--------|---------|
-| `--debug` | Verbose execution logging |
-| `--save-session` | Save complete execution session to workflow |
+- `--debug`: Verbose logging
+- `--save-session`: Save execution to workflow session

 ## Workflow Integration

-### Session Management
-⚠️ **Auto-detects active session**: Checks `.workflow/.active-*` marker file
+**Session Management**: Auto-detects `.workflow/.active-*` marker
+- **Active**: Save to `.workflow/WFS-[id]/.chat/execute-[timestamp].md`
+- **None**: Create new session

-**Session storage:**
- **Active session exists**: Saves to `.workflow/WFS-[topic]/.chat/execute-[timestamp].md`
- **No active session**: Creates new session directory
+**Task Integration**: Load from `.task/[TASK-ID].json`, update status, generate summary

-### Task Integration
+## Command Template
+
+**Gemini/Qwen** (with YOLO approval):
 ```bash
-# Execute specific workflow task
-/gemini:execute IMPL-001
-
-# Loads from: .task/IMPL-001.json
-# Uses: task context, brainstorming refs, scope definitions
-# Updates: workflow status, generates summary
-```
-
-## Execution Templates
-
-**Core Guidelines**: @~/.claude/workflows/intelligent-tools-strategy.md
-
-### Permission Requirements
-
-**Gemini Write Access** (when file modifications needed):
- Add `--approval-mode yolo` flag for auto-approval
- Required for: file creation, modification, deletion
-
-### User Description Template
-```bash
-cd [target-directory] && ~/.claude/scripts/gemini-wrapper --approval-mode yolo -p "
-PURPOSE: [clear implementation goal from description]
-TASK: [specific implementation task]
-CONTEXT: @{inferred_patterns} @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Implementation code with file:line locations, test cases, integration guidance
-RULES: [template reference if applicable] | [constraints]
+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]
 "
 ```

-**Example**:
+**Codex**:
 ```bash
-cd . && ~/.claude/scripts/gemini-wrapper --approval-mode yolo -p "
-PURPOSE: Implement JWT authentication with middleware
-TASK: Create authentication system with token validation
-CONTEXT: @{**/*auth*,**/*middleware*} @{CLAUDE.md}
-EXPECTED: Auth service, middleware, tests with file modifications
-RULES: Follow existing auth patterns | Security best practices
-"
+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
 ```

-### Task ID Template
-```bash
-cd [task-directory] && ~/.claude/scripts/gemini-wrapper --approval-mode yolo -p "
-PURPOSE: [task_title]
-TASK: Execute [task-id] implementation
-CONTEXT: @{task_files} @{brainstorming_refs} @{CLAUDE.md,**/*CLAUDE.md}
-EXPECTED: Complete implementation following acceptance criteria
-RULES: $(cat [task_template]) | Task type: [task_type], Scope: [task_scope]
-"
-```
+## Examples

-**Example**:
 ```bash
-cd .workflow/WFS-123 && ~/.claude/scripts/gemini-wrapper --approval-mode yolo -p "
-PURPOSE: Implement user profile editing
-TASK: Execute IMPL-001 implementation
-CONTEXT: @{src/user/**/*} @{.brainstorming/product-owner/analysis.md} @{CLAUDE.md}
-EXPECTED: Profile edit API, UI components, validation, tests
-RULES: $(cat ~/.claude/workflows/cli-templates/prompts/development/feature.txt) | Type: feature, Scope: user module
-"
+/cli:execute "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
 ```

 ## Auto-Generated Outputs

-### 1. Implementation Summary
-**Location**: `.summaries/[TASK-ID]-summary.md` or auto-generated ID
+- **Summary**: `.summaries/[TASK-ID]-summary.md`
+- **Session**: `.chat/execute-[timestamp].md`

-```markdown
-# Task Summary: [Task-ID] [Description]
+## Notes

-## Implementation
- **Files Modified**: [file:line references]
- **Features Added**: [specific functionality]
- **Context Used**: [inferred patterns]
-
-## Integration
- [Links to workflow documents]
-```
-
-### 2. Execution Session
-**Location**: `.chat/execute-[timestamp].md`
-
-```markdown
-# Execution Session: [Timestamp]
-
-## Input
-[User description or Task ID]
-
-## Context Inference
-[File patterns used with rationale]
-
-## Implementation Results
-[Generated code and modifications]
-
-## Status Updates
-[Workflow integration updates]
-```
-
-## Error Handling
-
- **Task ID not found**: Lists available tasks
- **Pattern inference failure**: Uses generic `src/**/*` pattern
- **Execution failure**: Attempts fallback with simplified context
- **File modification errors**: Reports specific file/permission issues
-
-## Performance Features
-
- **Smart caching**: Frequently used pattern mappings
- **Progressive inference**: Precise → broad pattern fallback
- **Parallel execution**: When multiple contexts needed
- **Directory optimization**: Switches to optimal execution path
-
-## Integration Workflow
-
-**Typical sequence:**
-1. `workflow:plan` → Creates tasks
-2. `/gemini:execute IMPL-001` → Executes with YOLO permissions
-3. Auto-updates workflow status and generates summaries
-4. `workflow:review` → Final validation
-
-**vs. `/gemini:analyze`**: Execute performs analysis **and implementation**, analyze is read-only.
+**vs. `/cli:analyze`**: Execute performs implementation, analyze is read-only.

--- a/.claude/commands/version.md
+++ b/.claude/commands/version.md
@@ -0,0 +1,261 @@
+---
+name: version
+description: Display version information and check for updates
+usage: /version
+examples:
+  - /version
+allowed-tools: Bash(*)
+---
+
+# Version Command (/version)
+
+## Purpose
+Display local and global installation versions, check for the latest updates from GitHub, and provide upgrade recommendations.
+
+## Execution Flow
+1. **Local Version Check**: Read version information from `./.claude/version.json` if it exists.
+2. **Global Version Check**: Read version information from `~/.claude/version.json` if it exists.
+3. **Fetch Remote Versions**: Use GitHub API to get the latest stable release tag and the latest commit hash from the main branch.
+4. **Compare & Suggest**: Compare installed versions with the latest remote versions and provide upgrade suggestions if applicable.
+
+## Step 1: Check Local Version
+
+### Check if local version.json exists
+```bash
+bash(test -f ./.claude/version.json && echo "found" || echo "not_found")
+```
+
+### Read local version (if exists)
+```bash
+bash(cat ./.claude/version.json)
+```
+
+### Extract version with jq (preferred)
+```bash
+bash(cat ./.claude/version.json | grep -o '"version": *"[^"]*"' | cut -d'"' -f4)
+```
+
+### Extract installation date
+```bash
+bash(cat ./.claude/version.json | grep -o '"installation_date_utc": *"[^"]*"' | cut -d'"' -f4)
+```
+
+**Output Format**:
+```
+Local Version: 3.2.1
+Installed: 2025-10-03T12:00:00Z
+```
+
+## Step 2: Check Global Version
+
+### Check if global version.json exists
+```bash
+bash(test -f ~/.claude/version.json && echo "found" || echo "not_found")
+```
+
+### Read global version
+```bash
+bash(cat ~/.claude/version.json)
+```
+
+### Extract version
+```bash
+bash(cat ~/.claude/version.json | grep -o '"version": *"[^"]*"' | cut -d'"' -f4)
+```
+
+### Extract installation date
+```bash
+bash(cat ~/.claude/version.json | grep -o '"installation_date_utc": *"[^"]*"' | cut -d'"' -f4)
+```
+
+**Output Format**:
+```
+Global Version: 3.2.1
+Installed: 2025-10-03T12:00:00Z
+```
+
+## Step 3: Fetch Latest Stable Release
+
+### Call GitHub API for latest release (with timeout)
+```bash
+bash(curl -fsSL "https://api.github.com/repos/catlog22/Claude-Code-Workflow/releases/latest" 2>/dev/null, timeout: 30000)
+```
+
+### Extract tag name (version)
+```bash
+bash(curl -fsSL "https://api.github.com/repos/catlog22/Claude-Code-Workflow/releases/latest" 2>/dev/null | grep -o '"tag_name": *"[^"]*"' | head -1 | cut -d'"' -f4, timeout: 30000)
+```
+
+### Extract release name
+```bash
+bash(curl -fsSL "https://api.github.com/repos/catlog22/Claude-Code-Workflow/releases/latest" 2>/dev/null | grep -o '"name": *"[^"]*"' | head -1 | cut -d'"' -f4, timeout: 30000)
+```
+
+### Extract published date
+```bash
+bash(curl -fsSL "https://api.github.com/repos/catlog22/Claude-Code-Workflow/releases/latest" 2>/dev/null | grep -o '"published_at": *"[^"]*"' | cut -d'"' -f4, timeout: 30000)
+```
+
+**Output Format**:
+```
+Latest Stable: v3.2.2
+Release: v3.2.2: Independent Test-Gen Workflow with Cross-Session Context
+Published: 2025-10-03T04:10:08Z
+```
+
+## Step 4: Fetch Latest Main Branch
+
+### Call GitHub API for latest commit on main (with timeout)
+```bash
+bash(curl -fsSL "https://api.github.com/repos/catlog22/Claude-Code-Workflow/commits/main" 2>/dev/null, timeout: 30000)
+```
+
+### Extract commit SHA (short)
+```bash
+bash(curl -fsSL "https://api.github.com/repos/catlog22/Claude-Code-Workflow/commits/main" 2>/dev/null | grep -o '"sha": *"[^"]*"' | head -1 | cut -d'"' -f4 | cut -c1-7, timeout: 30000)
+```
+
+### Extract commit message (first line only)
+```bash
+bash(curl -fsSL "https://api.github.com/repos/catlog22/Claude-Code-Workflow/commits/main" 2>/dev/null | grep '"message":' | cut -d'"' -f4 | cut -d'\' -f1, timeout: 30000)
+```
+
+### Extract commit date
+```bash
+bash(curl -fsSL "https://api.github.com/repos/catlog22/Claude-Code-Workflow/commits/main" 2>/dev/null | grep -o '"date": *"[^"]*"' | head -1 | cut -d'"' -f4, timeout: 30000)
+```
+
+**Output Format**:
+```
+Latest Dev: a03415b
+Message: feat: Add version tracking and upgrade check system
+Date: 2025-10-03T04:46:44Z
+```
+
+## Step 5: Compare Versions and Suggest Upgrade
+
+### Normalize versions (remove 'v' prefix)
+```bash
+bash(echo "v3.2.1" | sed 's/^v//')
+```
+
+### Compare two versions
+```bash
+bash(printf "%s\n%s" "3.2.1" "3.2.2" | sort -V | tail -n 1)
+```
+
+### Check if versions are equal
+```bash
+# If equal: Up to date
+# If remote newer: Upgrade available
+# If local newer: Development version
+```
+
+**Output Scenarios**:
+
+**Scenario 1: Up to date**
+```
+✅ You are on the latest stable version (3.2.1)
+```
+
+**Scenario 2: Upgrade available**
+```
+⬆️ A newer stable version is available: v3.2.2
+Your version: 3.2.1
+
+To upgrade:
+PowerShell: iex (iwr -useb https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.ps1)
+Bash: bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.sh)
+```
+
+**Scenario 3: Development version**
+```
+✨ You are running a development version (3.3.0-dev)
+This is newer than the latest stable release (v3.2.2)
+```
+
+## Simple Bash Commands
+
+### Basic Operations
+```bash
+# Check local version file
+bash(test -f ./.claude/version.json && cat ./.claude/version.json)
+
+# Check global version file
+bash(test -f ~/.claude/version.json && cat ~/.claude/version.json)
+
+# Extract version from JSON
+bash(cat version.json | grep -o '"version": *"[^"]*"' | cut -d'"' -f4)
+
+# Extract date from JSON
+bash(cat version.json | grep -o '"installation_date_utc": *"[^"]*"' | cut -d'"' -f4)
+
+# Fetch latest release (with timeout)
+bash(curl -fsSL "https://api.github.com/repos/catlog22/Claude-Code-Workflow/releases/latest" 2>/dev/null, timeout: 30000)
+
+# Extract tag name
+bash(curl -fsSL "https://api.github.com/repos/catlog22/Claude-Code-Workflow/releases/latest" 2>/dev/null | grep -o '"tag_name": *"[^"]*"' | cut -d'"' -f4, timeout: 30000)
+
+# Extract release name
+bash(curl -fsSL "https://api.github.com/repos/catlog22/Claude-Code-Workflow/releases/latest" 2>/dev/null | grep -o '"name": *"[^"]*"' | head -1 | cut -d'"' -f4, timeout: 30000)
+
+# Fetch latest commit (with timeout)
+bash(curl -fsSL "https://api.github.com/repos/catlog22/Claude-Code-Workflow/commits/main" 2>/dev/null, timeout: 30000)
+
+# Extract commit SHA
+bash(curl -fsSL "https://api.github.com/repos/catlog22/Claude-Code-Workflow/commits/main" 2>/dev/null | grep -o '"sha": *"[^"]*"' | head -1 | cut -d'"' -f4 | cut -c1-7, timeout: 30000)
+
+# Extract commit message (first line)
+bash(curl -fsSL "https://api.github.com/repos/catlog22/Claude-Code-Workflow/commits/main" 2>/dev/null | grep '"message":' | cut -d'"' -f4 | cut -d'\' -f1, timeout: 30000)
+
+# Compare versions
+bash(printf "%s\n%s" "3.2.1" "3.2.2" | sort -V | tail -n 1)
+
+# Remove 'v' prefix
+bash(echo "v3.2.1" | sed 's/^v//')
+```
+
+## Error Handling
+
+### No installation found
+```
+WARNING: Claude Code Workflow not installed
+Install using:
+PowerShell: iex (iwr -useb https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.ps1)
+```
+
+### Network error
+```
+ERROR: Could not fetch latest version from GitHub
+Check your network connection
+```
+
+### Invalid version.json
+```
+ERROR: version.json is invalid or corrupted
+```
+
+## Design Notes
+
+- Uses simple, direct bash commands instead of complex functions
+- Each step is independent and can be executed separately
+- Fallback to grep/sed for JSON parsing (no jq dependency required)
+- Network calls use curl with error suppression and 30-second timeout
+- Version comparison uses `sort -V` for accurate semantic versioning
+- Use `/commits/main` API instead of `/branches/main` for more reliable commit info
+- Extract first line of commit message using `cut -d'\' -f1` to handle JSON escape sequences
+
+## API Endpoints
+
+### GitHub API Used
+- **Latest Release**: `https://api.github.com/repos/catlog22/Claude-Code-Workflow/releases/latest`
+  - Fields: `tag_name`, `name`, `published_at`
+- **Latest Commit**: `https://api.github.com/repos/catlog22/Claude-Code-Workflow/commits/main`
+  - Fields: `sha`, `commit.message`, `commit.author.date`
+
+### Timeout Configuration
+All network calls should use `timeout: 30000` (30 seconds) to handle slow connections.
+
+## Related Commands
+- `/cli:cli-init` - Initialize CLI configurations
+- `/workflow:session:list` - List workflow sessions
--- a/.claude/commands/workflow/plan.md
+++ b/.claude/commands/workflow/plan.md
@@ -15,13 +15,22 @@ allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)

 ## Coordinator Role

-**This command is a pure orchestrator**: Execute 4 slash commands in sequence, parse their outputs, pass context between them, and ensure complete execution.
+**This command is a pure orchestrator**: Execute 4 slash commands in sequence, parse their outputs, pass context between them, and ensure complete execution through **automatic continuation**.

-**Execution Flow**:
-1. Initialize TodoWrite → Execute Phase 1 → Parse output → Update TodoWrite
-2. Execute Phase 2 with Phase 1 data → Parse output → Update TodoWrite
-3. Execute Phase 3 with Phase 2 data → Parse output → Update TodoWrite
-4. Execute Phase 4 with Phase 3 validation → Update TodoWrite → Return summary
+**Execution Model - Auto-Continue Workflow**:
+
+Each phase executes and returns to user, then **automatically continues** to next phase:
+
+1. **User triggers**: `/workflow:plan "task"`
+2. **Phase 1 executes** → Returns to user with results
+3. **Auto-continue to Phase 2** → Returns to user with results
+4. **Auto-continue to Phase 3** → Returns to user with results
+5. **Auto-continue to Phase 4** → Returns final summary
+
+**Auto-Continue Mechanism**:
+- Read TodoList to determine current phase status
+- Execute next pending phase based on TodoList state
+- No external state files needed - TodoList tracks progress

 **Execution Modes**:
 - **Manual Mode** (default): Use `/workflow:tools:task-generate`
@@ -32,9 +41,8 @@ allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*)
 1. **Start Immediately**: First action is TodoWrite initialization, second action is Phase 1 command execution
 2. **No Preliminary Analysis**: Do not read files, analyze structure, or gather context before Phase 1
 3. **Parse Every Output**: Extract required data from each command's output for next phase
-4. **Sequential Execution**: Each phase depends on previous phase's output
-5. **Complete All Phases**: Do not return to user until Phase 4 completes
-6. **Track Progress**: Update TodoWrite after every phase completion
+4. **Auto-Continue via TodoList**: Check TodoList status to execute next pending phase automatically
+5. **Track Progress**: Update TodoWrite after every phase completion

 ## 4-Phase Execution

@@ -64,6 +72,8 @@ CONTEXT: Existing user database schema, REST API endpoints

 **TodoWrite**: Mark phase 1 completed, phase 2 in_progress

+**After Phase 1**: Return to user showing Phase 1 results, then auto-continue to Phase 2
+
 ---

 ### Phase 2: Context Gathering
@@ -83,6 +93,8 @@ CONTEXT: Existing user database schema, REST API endpoints

 **TodoWrite**: Mark phase 2 completed, phase 3 in_progress

+**After Phase 2**: Return to user showing Phase 2 results, then auto-continue to Phase 3
+
 ---

 ### Phase 3: Intelligent Analysis
@@ -99,6 +111,8 @@ CONTEXT: Existing user database schema, REST API endpoints

 **TodoWrite**: Mark phase 3 completed, phase 4 in_progress

+**After Phase 3**: Return to user showing Phase 3 results, then auto-continue to Phase 4
+
 ---

 ### Phase 4: Task Generation
@@ -227,23 +241,23 @@ Return summary to user

 - **Parsing Failure**: If output parsing fails, retry command once, then report error
 - **Validation Failure**: If validation fails, report which file/data is missing
- **Command Failure**: Keep phase `in_progress`, report error to user, do not proceed
+- **Command Failure**: Keep phase `in_progress`, report error to user, do not proceed to next phase

 ## Coordinator Checklist

 ✅ **Pre-Phase**: Convert user input to structured format (GOAL/SCOPE/CONTEXT)
 ✅ Initialize TodoWrite before any command
 ✅ Execute Phase 1 immediately with structured description
-✅ Parse session ID from Phase 1 output
+✅ Parse session ID from Phase 1 output, store in memory
 ✅ Pass session ID and structured description to Phase 2 command
-✅ Parse context path from Phase 2 output
+✅ Parse context path from Phase 2 output, store in memory
 ✅ Pass session ID and context path to Phase 3 command
 ✅ Verify ANALYSIS_RESULTS.md after Phase 3
 ✅ Select correct Phase 4 command based on --agent flag
 ✅ Pass session ID to Phase 4 command
 ✅ Verify all Phase 4 outputs
 ✅ Update TodoWrite after each phase
-✅ Return summary only after Phase 4 completes
+✅ After each phase, automatically continue to next phase based on TodoList status

 ## Structure Template Reference

--- a/.claude/scripts/update_module_claude.sh
+++ b/.claude/scripts/update_module_claude.sh
@@ -40,22 +40,22 @@ update_module_claude() {
    if [ "$module_path" = "." ]; then
        # Root directory
        layer="Layer 1 (Root)"
-        template_path="$HOME/.claude/workflows/cli-templates/prompts/dms/claude-layer1-root.txt"
+        template_path="$HOME/.claude/workflows/cli-templates/prompts/memory/claude-layer1-root.txt"
        analysis_strategy="--all-files"
    elif [[ "$clean_path" =~ ^[^/]+$ ]]; then
        # Top-level directories (e.g., .claude, src, tests)
        layer="Layer 2 (Domain)"
-        template_path="$HOME/.claude/workflows/cli-templates/prompts/dms/claude-layer2-domain.txt"
+        template_path="$HOME/.claude/workflows/cli-templates/prompts/memory/claude-layer2-domain.txt"
        analysis_strategy="@{*/CLAUDE.md}"
    elif [[ "$clean_path" =~ ^[^/]+/[^/]+$ ]]; then
        # Second-level directories (e.g., .claude/scripts, src/components)
        layer="Layer 3 (Module)"
-        template_path="$HOME/.claude/workflows/cli-templates/prompts/dms/claude-layer3-module.txt"
+        template_path="$HOME/.claude/workflows/cli-templates/prompts/memory/claude-layer3-module.txt"
        analysis_strategy="@{*/CLAUDE.md}"
    else
        # Deeper directories (e.g., .claude/workflows/cli-templates/prompts)
        layer="Layer 4 (Sub-Module)"
-        template_path="$HOME/.claude/workflows/cli-templates/prompts/dms/claude-layer4-submodule.txt"
+        template_path="$HOME/.claude/workflows/cli-templates/prompts/memory/claude-layer4-submodule.txt"
        analysis_strategy="--all-files"
    fi
    
--- a/.claude/version.json
+++ b/.claude/version.json
@@ -0,0 +1,7 @@
+{
+  "version": "3.3.0",
+  "installation_mode": "Local",
+  "installation_path": "D:\\Claude_dms3\\.claude",
+  "source_branch": "main",
+  "installation_date_utc": "2025-10-04T00:00:00Z"
+}
--- a/.claude/workflows/cli-templates/prompts/memory/claude-layer1-root.txt
+++ b/.claude/workflows/cli-templates/prompts/memory/claude-layer1-root.txt
--- a/.claude/workflows/cli-templates/prompts/memory/claude-layer2-domain.txt
+++ b/.claude/workflows/cli-templates/prompts/memory/claude-layer2-domain.txt
--- a/.claude/workflows/cli-templates/prompts/memory/claude-layer3-module.txt
+++ b/.claude/workflows/cli-templates/prompts/memory/claude-layer3-module.txt
--- a/.claude/workflows/cli-templates/prompts/memory/claude-layer4-submodule.txt
+++ b/.claude/workflows/cli-templates/prompts/memory/claude-layer4-submodule.txt
--- a/.claude/workflows/cli-templates/prompts/memory/hierarchy-analysis.txt
+++ b/.claude/workflows/cli-templates/prompts/memory/hierarchy-analysis.txt
@@ -1,4 +1,4 @@
-Analyze project structure for DMS hierarchy optimization:
+Analyze project structure for memory hierarchy optimization:

 ## Required Analysis:
 1. Assess project complexity and file organization patterns
--- a/.claude/workflows/intelligent-tools-strategy.md
+++ b/.claude/workflows/intelligent-tools-strategy.md
@@ -18,6 +18,7 @@ type: strategic-guideline
 - **Default to tools** - Use specialized tools for most coding tasks, no matter how small
 - **Lower barriers** - Engage tools immediately when encountering any complexity
 - **Context optimization** - Based on user intent, determine whether to use `-C [directory]` parameter for focused analysis to reduce irrelevant context import
+- **⚠️ Write operation protection** - For local codebase write/modify operations, require EXPLICIT user confirmation unless user provides clear instructions containing MODE=write or MODE=auto

 ### Quick Decision Rules
 1. **Exploring/Understanding?** → Start with Gemini
@@ -33,15 +34,19 @@ type: strategic-guideline
 - **Override When Needed**: Specify custom timeout for longer operations

 ### Permission Framework
- **Gemini/Qwen Write Access**: Use `--approval-mode yolo` when tools need to create/modify files
- **Codex Write Access**: Always use `-s danger-full-access` and `--skip-git-repo-check` for development and file operations
- **Auto-approval Protocol**: Enable automatic tool approvals for autonomous workflow execution
+- **⚠️ 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

 ## 🎯 Universal Command Template

 ### Standard Format (REQUIRED)
 ```bash
-# Gemini Analysis (全权限)
+# Gemini Analysis (read/write capable)
 cd [directory] && ~/.claude/scripts/gemini-wrapper -p "
 PURPOSE: [clear analysis goal]
 TASK: [specific analysis task]
@@ -51,7 +56,7 @@ EXPECTED: [expected output]
 RULES: [template reference and constraints]
 "

-# Qwen Architecture Analysis (仅分析)
+# Qwen Architecture Analysis (read-only analysis)
 cd [directory] && ~/.claude/scripts/qwen-wrapper -p "
 PURPOSE: [clear architecture goal]
 TASK: [specific analysis task]
@@ -84,16 +89,18 @@ RULES: [template reference and constraints]

 The MODE field controls execution behavior and file permissions:

-**For Gemini** (全权限，可读写):
- `analysis` (default) - 分析 + 可生成文档
- `write` - 创建/修改文件（自动启用 --approval-mode yolo）
+**For Gemini**:
+- `analysis` (default) - Read-only analysis and documentation generation
+- `write` - ⚠️ Create/modify codebase files (requires explicit specification, auto-enables --approval-mode yolo)

-**For Qwen** (仅分析):
- `analysis` (default) - 仅架构分析，不生成代码
+**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` (default) - 自主开发，全文件操作
- `write` - 测试生成和文件修改
+- `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
 Tools execute in current working directory:
@@ -235,26 +242,34 @@ For every development task:

 ## 🎯 Key Features

-### Gemini (全权限)
+### Gemini
 - **Command**: `~/.claude/scripts/gemini-wrapper`
 - **Strengths**: Large context window, pattern recognition
 - **Best For**: Analysis, documentation generation, code exploration
- **Permissions**: 可读写，MODE=write 时自动启用 --approval-mode yolo
- **Default MODE**: `analysis`
+- **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 (仅分析)
+### Qwen
 - **Command**: `~/.claude/scripts/qwen-wrapper`
 - **Strengths**: Architecture analysis, pattern recognition
 - **Best For**: System design analysis, architectural review
- **Permissions**: 仅分析，不生成代码
- **Default MODE**: `analysis`
+- **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
- **Required**: `-s danger-full-access` and `--skip-git-repo-check` for development
- **Default MODE**: `auto`
+- **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: `@{**/*}`
--- a/.codex/AGENTS.md
+++ b/.codex/AGENTS.md
@@ -6,6 +6,8 @@

 ## Prompt Structure

+### Single-Task Format
+
 **Receive prompts in this format**:

 ```
@@ -17,11 +19,37 @@ EXPECTED: [deliverables]
 RULES: [constraints and templates]
 ```

+### Multi-Task Format (Subtask Execution)
+
+**First subtask** (creates new session):
+```
+PURPOSE: [overall goal]
+TASK: [subtask 1 description]
+MODE: auto
+CONTEXT: [file patterns]
+EXPECTED: [subtask deliverables]
+RULES: [constraints]
+Subtask 1 of N: [subtask title]
+```
+
+**Subsequent subtasks** (continues via `resume --last`):
+```
+CONTINUE TO NEXT SUBTASK:
+Subtask N of M: [subtask title]
+
+PURPOSE: [continuation goal]
+TASK: [subtask N description]
+CONTEXT: Previous work completed, now focus on [new files]
+EXPECTED: [subtask deliverables]
+RULES: Build on previous subtask, maintain consistency
+```
+
 ## Execution Requirements

 ### ALWAYS

- **Parse all six fields** - Understand PURPOSE, TASK, MODE, CONTEXT, EXPECTED, RULES
+- **Parse all fields** - Understand PURPOSE, TASK, MODE, CONTEXT, EXPECTED, RULES
+- **Detect subtask format** - Check for "Subtask N of M" or "CONTINUE TO NEXT SUBTASK"
 - **Follow MODE strictly** - Respect execution boundaries
 - **Study CONTEXT files** - Find 3+ similar patterns before implementing
 - **Apply RULES** - Follow templates and constraints exactly
@@ -29,6 +57,7 @@ RULES: [constraints and templates]
 - **Commit incrementally** - Small, working commits
 - **Match project style** - Follow existing patterns exactly
 - **Validate EXPECTED** - Ensure all deliverables are met
+- **Report context** (subtasks) - Summarize key info for next subtask

 ### NEVER

@@ -49,7 +78,7 @@ RULES: [constraints and templates]
 - Run tests and builds
 - Commit code incrementally

-**Execute**:
+**Execute (Single Task)**:
 1. Parse PURPOSE and TASK
 2. Analyze CONTEXT files - find 3+ similar patterns
 3. Plan implementation approach
@@ -60,7 +89,17 @@ RULES: [constraints and templates]
 8. Validate all EXPECTED deliverables
 9. Report results

-**Use For**: Feature implementation, bug fixes, refactoring
+**Execute (Multi-Task/Subtask)**:
+1. **First subtask**: Follow single-task flow above
+2. **Subsequent subtasks** (via `resume --last`):
+   - Recall context from previous subtask(s)
+   - Build on previous work (don't repeat)
+   - Maintain consistency with previous decisions
+   - Focus on current subtask scope only
+   - Test integration with previous subtasks
+   - Report subtask completion status
+
+**Use For**: Feature implementation, bug fixes, refactoring, multi-step tasks

 ### MODE: write

@@ -119,7 +158,7 @@ RULES: [constraints and templates]

 ## Progress Reporting

-### During Execution
+### During Execution (Single Task)

 ```
 [1/5] Analyzing existing code patterns...
@@ -129,7 +168,17 @@ RULES: [constraints and templates]
 [5/5] Running validation...
 ```

-### On Success
+### During Execution (Subtask)
+
+```
+[Subtask N/M: Subtask Title]
+[1/4] Recalling context from previous subtasks...
+[2/4] Implementing current subtask...
+[3/4] Testing integration with previous work...
+[4/4] Validating subtask completion...
+```
+
+### On Success (Single Task)

 ```
 ✅ Task completed
@@ -146,6 +195,26 @@ Validation:
 Next Steps: [recommendations]
 ```

+### On Success (Subtask)
+
+```
+✅ Subtask N/M completed
+
+Changes:
+- Created: [files]
+- Modified: [files]
+
+Integration:
+✅ Compatible with previous subtasks
+✅ Tests: [count] passing
+✅ Build: Success
+
+Context for next subtask:
+- [Key decisions made]
+- [Files created/modified]
+- [Patterns established]
+```
+
 ### On Partial Completion

 ```
@@ -178,6 +247,60 @@ Recommendation: [next steps]
 - Graceful degradation
 - Don't expose sensitive info

+## Multi-Step Task Execution
+
+### Context Continuity via Resume
+
+When executing subtasks via `codex exec "..." resume --last`:
+
+**Advantages**:
+- Session memory preserves previous decisions
+- Maintains implementation style consistency
+- Avoids redundant context re-injection
+- Enables incremental testing and validation
+
+**Best Practices**:
+1. **First subtask**: Establish patterns and architecture
+2. **Subsequent subtasks**: Build on established patterns
+3. **Test integration**: After each subtask, verify compatibility
+4. **Report context**: Summarize key decisions for next subtask
+5. **Maintain scope**: Focus only on current subtask goals
+
+### Subtask Coordination
+
+**DO**:
+- Remember decisions from previous subtasks
+- Reuse patterns established earlier
+- Test integration with previous work
+- Report what's ready for next subtask
+
+**DON'T**:
+- Re-implement what previous subtasks completed
+- Change patterns established earlier (unless explicitly requested)
+- Skip testing integration points
+- Assume next subtask's requirements
+
+### Example Flow
+
+```
+Subtask 1: Create data models
+→ Establishes: Schema patterns, validation approach
+→ Delivers: Models with tests
+→ Context for next: Model structure, validation rules
+
+Subtask 2: Implement API endpoints (resume --last)
+→ Recalls: Model structure from subtask 1
+→ Builds on: Uses established models
+→ Delivers: API with integration tests
+→ Context for next: API patterns, error handling
+
+Subtask 3: Add authentication (resume --last)
+→ Recalls: API patterns from subtask 2
+→ Integrates: Auth middleware into existing endpoints
+→ Delivers: Secured API
+→ Final validation: Full integration test
+```
+
 ## Philosophy

 - **Incremental progress over big bangs** - Small, testable changes
@@ -186,6 +309,7 @@ Recommendation: [next steps]
 - **Clear intent over clever code** - Boring, obvious solutions
 - **Simple over complex** - Avoid over-engineering
 - **Follow existing style** - Match project patterns exactly
+- **Context continuity** - Leverage resume for multi-step consistency

 ## Execution Checklist

@@ -211,5 +335,6 @@ Recommendation: [next steps]

 ---

-**Version**: 2.0.0
-**Last Updated**: 2025-10-02
+**Version**: 2.1.0
+**Last Updated**: 2025-10-04
+**Changes**: Added multi-step task execution support with resume mechanism
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -5,6 +5,241 @@ 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).

+## [3.3.0] - 2025-10-04
+
+### 🚀 CLI Tool Enhancements & Codex Multi-Step Execution
+
+This release streamlines CLI tool documentation and introduces automated multi-step task execution with Codex.
+
+#### Added
+
+**New Command: `/cli:codex-execute`**:
+- **Purpose**: Automated task decomposition and sequential execution with Codex
+- **Features**:
+  - Automatic task breakdown into 3-8 manageable subtasks
+  - Sequential execution using `codex exec "..." resume --last` mechanism
+  - TodoWrite progress tracking for each subtask
+  - Optional Git verification after each subtask (`--verify-git` flag)
+  - Supports both freeform descriptions and workflow task IDs
+  - Automatic detection and loading of task JSON files
+  - Context continuity across subtasks via resume mechanism
+  - Integration with workflow system (optional)
+
+**Codex Resume Mechanism**:
+- **First Subtask**: Creates new Codex session with `codex exec`
+- **Subsequent Subtasks**: Continues with `codex exec "..." resume --last`
+- **Benefits**:
+  - Session memory preserves previous decisions
+  - Maintains implementation style consistency
+  - Avoids redundant context re-injection
+  - Enables incremental testing and validation
+
+**Enhanced Codex Agent Configuration** (`.codex/AGENTS.md`):
+- Added multi-task prompt format (Single-Task & Multi-Task)
+- Enhanced MODE: auto with subtask execution flow
+- New "Multi-Step Task Execution" section with:
+  - Context continuity best practices
+  - Subtask coordination guidelines
+  - Example 3-subtask workflow demonstration
+- Updated progress reporting for subtasks
+- Version 2.1.0 with multi-step task execution support
+
+#### Changed
+
+**CLI Documentation Optimization**:
+- **Streamlined Documentation**: Reduced redundancy by referencing `intelligent-tools-strategy.md`
+- **Updated Commands**:
+  - `/cli:analyze` - Simplified from ~200 to ~78 lines
+  - `/cli:chat` - Simplified from ~161 to ~92 lines
+  - `/cli:execute` - Simplified from ~235 to ~111 lines
+- **Unified Command Templates**:
+  - Separated Gemini/Qwen (uses `-p` parameter) from Codex (uses `exec` command)
+  - Added Codex `-i` parameter documentation for image attachment
+  - Consistent template structure across all CLI commands
+
+**Intelligent Tools Strategy Updates**:
+- Enhanced Codex session management documentation
+- Added `codex exec "..." resume --last` syntax explanation
+- Documented multi-task execution pattern
+- Clarified image attachment workflow with resume
+
+**Command Template Improvements**:
+- **Gemini/Qwen**: `cd [dir] && ~/.claude/scripts/[tool]-wrapper -p "..."`
+- **Codex**: `codex -C [dir] --full-auto exec "..." --skip-git-repo-check -s danger-full-access`
+- **Codex with Resume**: `codex exec "..." resume --last --skip-git-repo-check -s danger-full-access`
+- **Image Support**: `codex -C [dir] -i image.png --full-auto exec "..."`
+
+#### Technical Details
+
+**Multi-Step Execution Flow**:
+```
+Input → Parse (Description/Task ID) → Decompose into Subtasks → TodoWrite Tracking →
+For Each Subtask:
+  1. Execute with Codex (first: exec, subsequent: exec resume --last)
+  2. [Optional] Git verification
+  3. Mark complete in TodoWrite
+→ Final Summary
+```
+
+**Subtask Decomposition Criteria**:
+- Each subtask: 5-15 minutes completable
+- Clear, testable outcomes
+- Explicit dependencies
+- Focused file scope (1-5 files per subtask)
+
+**Error Handling**:
+- Subtask failure: Pause for user intervention
+- Git verification failure: Request user decision
+- Codex session lost: Attempt retry with fresh session
+
+**Integration Features**:
+- Automatic task ID detection (e.g., `IMPL-001`, `TASK-123`)
+- JSON task loading from `.task/[ID].json`
+- Execution logging to `.chat/codex-execute-[timestamp].md`
+- Summary generation to `.summaries/[TASK-ID]-summary.md`
+
+#### Benefits
+
+**Developer Experience**:
+- 🚀 Automated task breakdown reduces planning overhead
+- 📊 Clear progress tracking with TodoWrite integration
+- 🔄 Context continuity improves code consistency
+- ✅ Optional Git verification ensures code quality
+- 🎯 Focused subtask execution reduces complexity
+
+**Code Quality**:
+- 🧪 Incremental testing after each subtask
+- 🔍 Git verification catches unexpected changes
+- 📝 Comprehensive execution logs for audit trail
+- 🎨 Image attachment support for UI/design tasks
+
+**Documentation**:
+- 📚 Reduced documentation redundancy by ~60%
+- 🔗 Clear references to master documentation
+- ✨ Consistent command structure across all CLI tools
+- 📖 Better separation of concerns (strategy vs. command docs)
+
+---
+
+## [3.2.3] - 2025-10-03
+
+### ✨ Version Management System
+
+This release introduces a comprehensive version management and upgrade notification system.
+
+#### Added
+
+**New Command: `/version`**:
+- **Purpose**: Display version information and check for updates from GitHub
+- **Features**:
+  - Shows local and global installation versions
+  - Fetches latest stable release from GitHub API
+  - Displays latest development commit from main branch
+  - Compares installed versions with remote versions
+  - Provides upgrade recommendations with installation commands
+  - Supports both stable and development version tracking
+
+**Version Information Display**:
+- **Local Version**: Shows project-specific installation (if exists)
+- **Global Version**: Shows `~/.claude` installation with tracking mode
+- **Latest Stable**: Displays latest release tag, name, and publish date
+- **Latest Dev**: Shows latest commit hash, message, and date
+- **Status Assessment**: Automatic version comparison and upgrade suggestions
+
+**Version Tracking Files**:
+- **`.claude/version.json`**: Local project version tracking
+- **`~/.claude/version.json`**: Global installation version tracking
+- **Fields**:
+  - `version`: Version number or "latest" for main branch tracking
+  - `installation_mode`: "Local" or "Global"
+  - `installation_path`: Installation directory
+  - `source_branch`: Source branch (usually "main")
+  - `installation_date_utc`: ISO 8601 timestamp
+
+**GitHub API Integration**:
+- **Latest Release**: `https://api.github.com/repos/catlog22/Claude-Code-Workflow/releases/latest`
+  - Extracts: `tag_name`, `name`, `published_at`
+- **Latest Commit**: `https://api.github.com/repos/catlog22/Claude-Code-Workflow/commits/main`
+  - Extracts: `sha`, `commit.message`, `commit.author.date`
+- **Timeout**: 30-second timeout for slow connections
+- **Error Handling**: Graceful fallback for network errors
+
+**Command Output Scenarios**:
+
+1. **Up to date**:
+   ```
+   ✅ You are on the latest stable version (3.2.3)
+   ```
+
+2. **Upgrade available**:
+   ```
+   ⬆️ A newer stable version is available: v3.2.3
+   Your version: 3.2.2
+
+   To upgrade:
+   PowerShell: iex (iwr -useb https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.ps1)
+   Bash: bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.sh)
+   ```
+
+3. **Development version**:
+   ```
+   ✨ You are running a development version (3.3.0-dev)
+   This is newer than the latest stable release (v3.2.3)
+   ```
+
+#### Changed
+
+**Documentation Updates**:
+- Added `/version` command reference to README.md
+- Added version management documentation to README_CN.md
+- Created comprehensive `.claude/commands/version.md` implementation guide
+- Updated command tables with version management examples
+
+**Installation Scripts Enhancement**:
+- Installation scripts now create `version.json` files automatically
+- Track installation mode (local vs global)
+- Record installation timestamp
+- Support version tracking for both stable and development installations
+
+#### Technical Details
+
+**Implementation**:
+- Uses simple bash commands (no jq dependency required)
+- Fallback to grep/sed for JSON parsing
+- Network calls with curl and error suppression
+- Version comparison using `sort -V` for semantic versioning
+- Cross-platform compatible (Windows Git Bash, Linux, macOS)
+
+**Command Structure**:
+```bash
+/version                    # Display version and check for updates
+```
+
+**No parameters required** - command automatically:
+1. Checks local version file (`./.claude/version.json`)
+2. Checks global version file (`~/.claude/version.json`)
+3. Fetches latest release from GitHub
+4. Fetches latest commit from main branch
+5. Compares versions and provides recommendations
+
+#### Benefits
+
+**User Experience**:
+- 🔍 Quick version check with single command
+- 📊 Comprehensive version information display
+- 🔄 Automatic upgrade notifications
+- 📈 Development version tracking support
+- 🌐 GitHub API integration for latest updates
+
+**DevOps**:
+- 📁 Version tracking in both local and global installations
+- 🕐 Installation timestamp for audit trails
+- 🔀 Support for both stable and development branches
+- ⚡ Fast execution with 30-second network timeout
+- 🛡️ Graceful error handling for offline scenarios
+
+---
+
 ## [3.2.0] - 2025-10-02

 ### 🔄 Test-Fix Workflow & Agent Architecture Simplification
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -19,11 +19,14 @@ For all CLI tool usage, command syntax, and integration guidelines:

 ### Core Beliefs

+- **Pursue good taste** - Eliminate edge cases to make code logic natural and elegant
+- **Embrace extreme simplicity** - Complexity is the root of all evil
+- **Be pragmatic** - Code must solve real-world problems, not hypothetical ones
+- **Data structures first** - Bad programmers worry about code; good programmers worry about data structures
+- **Never break backward compatibility** - Existing functionality is sacred and inviolable
 - **Incremental progress over big bangs** - Small changes that compile and pass tests
 - **Learning from existing code** - Study and plan before implementing
- **Pragmatic over dogmatic** - Adapt to project reality
 - **Clear intent over clever code** - Be boring and obvious
- **Simple solutions over complex architectures** - Avoid over-engineering and premature optimization
 - **Follow existing code style** - Match import patterns, naming conventions, and formatting of existing codebase

 ### Simplicity Means
--- a/INSTALL.md
+++ b/INSTALL.md
@@ -186,7 +186,7 @@ cd Dmsflow
 .\Install-Claude.ps1 -Global

 # 4. Start using Claude Code with Agent workflows!
-# Use /workflow commands and DMS system for development
+# Use /workflow commands and memory system for development
 ```

 ## Verification
@@ -207,7 +207,7 @@ After installation, verify:
   - Check that global `.claude` directory is recognized
   - Verify workflow commands and DMS commands are available
   - Test `/workflow` commands for agent coordination
-   - Test `/dmsflow version` to check version information
+   - Test `/workflow version` to check version information

 ## Troubleshooting

--- a/INSTALL_CN.md
+++ b/INSTALL_CN.md
@@ -162,7 +162,7 @@ cd Dmsflow
 .\Install-Claude.ps1 -Global

 # 4. 开始使用 Claude Code Agent 工作流！
-# 使用 /workflow 命令和 DMS 系统进行开发
+# 使用 /workflow 命令和内存系统进行开发
 ```

 ## 验证
@@ -181,9 +181,9 @@ cd Dmsflow
 2. **测试 Claude Code：**
   - 在项目中打开 Claude Code
   - 检查全局 `.claude` 目录是否被识别
-   - 验证工作流命令和 DMS 命令是否可用
+   - 验证工作流命令和内存命令是否可用
   - 测试 `/workflow` 命令的 Agent 协调功能
-   - 测试 `/dmsflow version` 检查版本信息
+   - 测试 `/workflow version` 检查版本信息

 ## 故障排除

--- a/Install-Claude.ps1
+++ b/Install-Claude.ps1
@@ -59,7 +59,11 @@ param(

    [switch]$BackupAll,

-    [switch]$NoBackup
+    [switch]$NoBackup,
+
+    [string]$SourceVersion = "",
+
+    [string]$SourceBranch = ""
 )

 # Set encoding for proper Unicode support
@@ -622,6 +626,37 @@ function Merge-DirectoryContents {
    return $true
 }

+function Create-VersionJson {
+    param(
+        [string]$TargetClaudeDir,
+        [string]$InstallationMode
+    )
+
+    # Determine version from source or default
+    $versionNumber = if ($SourceVersion) { $SourceVersion } else { $Version }
+    $sourceBranch = if ($SourceBranch) { $SourceBranch } else { "unknown" }
+
+    # Create version.json content
+    $versionInfo = @{
+        version = $versionNumber
+        installation_mode = $InstallationMode
+        installation_path = $TargetClaudeDir
+        installation_date_utc = (Get-Date).ToUniversalTime().ToString("yyyy-MM-ddTHH:mm:ssZ")
+        source_branch = $sourceBranch
+    }
+
+    $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
+        return $true
+    } catch {
+        Write-ColorOutput "WARNING: Failed to create version.json: $($_.Exception.Message)" $ColorWarning
+        return $false
+    }
+}
+
 function Install-Global {
    Write-ColorOutput "Installing Claude Code Workflow System globally..." $ColorInfo

@@ -682,6 +717,10 @@ function Install-Global {
    Write-ColorOutput "Merging .gemini directory contents..." $ColorInfo
    $geminiMerged = Merge-DirectoryContents -Source $sourceGeminiDir -Destination $globalGeminiDir -Description ".gemini directory contents" -BackupFolder $backupFolder

+    # Create version.json in global .claude directory
+    Write-ColorOutput "Creating version.json..." $ColorInfo
+    Create-VersionJson -TargetClaudeDir $globalClaudeDir -InstallationMode "Global"
+
    if ($backupFolder -and (Test-Path $backupFolder)) {
        $backupFiles = Get-ChildItem $backupFolder -Recurse -File -ErrorAction SilentlyContinue
        if (-not $backupFiles -or ($backupFiles | Measure-Object).Count -eq 0) {
@@ -819,6 +858,14 @@ 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

+    # Create version.json in local .claude directory
+    Write-ColorOutput "Creating version.json in local directory..." $ColorInfo
+    Create-VersionJson -TargetClaudeDir $localClaudeDir -InstallationMode "Path"
+
+    # Also create version.json in global .claude directory
+    Write-ColorOutput "Creating version.json in global directory..." $ColorInfo
+    Create-VersionJson -TargetClaudeDir $globalClaudeDir -InstallationMode "Global"
+
    if ($backupFolder -and (Test-Path $backupFolder)) {
        $backupFiles = Get-ChildItem $backupFolder -Recurse -File -ErrorAction SilentlyContinue
        if (-not $backupFiles -or ($backupFiles | Measure-Object).Count -eq 0) {
--- a/Install-Claude.sh
+++ b/Install-Claude.sh
@@ -87,8 +87,8 @@ function show_header() {

 function test_prerequisites() {
    # Test bash version
-    if [ "${BASH_VERSINFO[0]}" -lt 4 ]; then
-        write_color "ERROR: Bash 4.0 or higher is required" "$COLOR_ERROR"
+    if [ "${BASH_VERSINFO[0]}" -lt 2 ]; then
+        write_color "ERROR: Bash 2.0 or higher is required" "$COLOR_ERROR"
        write_color "Current version: ${BASH_VERSION}" "$COLOR_ERROR"
        return 1
    fi
--- a/README.md
+++ b/README.md
@@ -2,7 +2,7 @@

 <div align="center">

-[![Version](https://img.shields.io/badge/version-v3.2.1-blue.svg)](https://github.com/catlog22/Claude-Code-Workflow/releases)
+[![Version](https://img.shields.io/badge/version-v3.3.0-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)
@@ -15,13 +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: v3.2.0** - Simplified agent architecture with "Tests Are the Review" philosophy. See [CHANGELOG.md](CHANGELOG.md) for details.
+> **🎉 Latest: v3.3.0** - CLI tool enhancements & Codex multi-step execution. See [CHANGELOG.md](CHANGELOG.md) for details.
 >
-> **What's New in v3.2.0**:
-> - 🔄 Simplified from 3 agents to 2 core agents (`@code-developer`, `@test-fix-agent`)
-> - ✅ "Tests Are the Review" - Passing tests = approved code
-> - 🧪 Enhanced test-fix workflow with automatic execution and fixing
-> - 📦 Interactive installation with version selection menu
+> **What's New in v3.3.0**:
+> - 🚀 New `/cli:codex-execute` command for automated multi-step task execution
+> - 🔄 Codex resume mechanism (`codex exec "..." resume --last`) for context continuity
+> - 📋 TodoWrite progress tracking for subtask execution
+> - 📚 Streamlined CLI documentation (60% reduction in redundancy)
+> - 🔧 Enhanced Codex agent configuration for multi-task workflows
+> - ✅ Optional Git verification after each subtask completion

 ---

@@ -94,17 +96,51 @@ Select version to install (1-3, default: 1):

 > 💡 **Pro Tip**: The installer automatically detects and displays the latest version numbers and release dates from GitHub. Just press Enter to select the recommended stable release.

+### **📦 Local Installation (Install-Claude.ps1)**
+
+For local installation without network access, use the bundled PowerShell installer:
+
+**Installation Modes:**
+```powershell
+# Interactive mode with prompts (recommended)
+.\Install-Claude.ps1
+
+# Quick install with automatic backup
+.\Install-Claude.ps1 -Force -BackupAll
+
+# Non-interactive install
+.\Install-Claude.ps1 -NonInteractive -Force
+```
+
+**Installation Options:**
+
+| Mode | Description | Installs To |
+|------|-------------|-------------|
+| **Global** | System-wide installation (default) | `~/.claude/`, `~/.codex/`, `~/.gemini/` |
+| **Path** | Custom directory + global hybrid | Local: `agents/`, `commands/`<br>Global: `workflows/`, `scripts/` |
+
+**Backup Behavior:**
+- **Default**: Automatic backup enabled (`-BackupAll`)
+- **Disable**: Use `-NoBackup` flag (⚠️ overwrites without backup)
+- **Backup location**: `claude-backup-{timestamp}/` in installation directory
+
+**⚠️ Important Warnings:**
+- `-Force -BackupAll`: Silent file overwrite (with backup)
+- `-NoBackup -Force`: Permanent file overwrite (no recovery)
+- Global mode modifies user profile directories
+
 ### **✅ Verify Installation**
 After installation, run the following command to ensure CCW is working:
 ```bash
 /workflow:session:list
 ```

-> **📝 Important Notes:**
+> **📝 Installation Notes:**
 > - The installer will automatically install/update `.codex/` and `.gemini/` directories
 > - **Global mode**: Installs to `~/.codex` and `~/.gemini`
 > - **Path mode**: Installs to your specified directory (e.g., `project/.codex`, `project/.gemini`)
-> - Existing files will be backed up automatically before installation
+> - **Backup**: Existing files are backed up by default to `claude-backup-{timestamp}/`
+> - **Safety**: Use interactive mode for first-time installation to review changes

 ---

@@ -142,9 +178,9 @@ After installation, run the following command to ensure CCW is working:

 **Phase 4: Testing & Quality Assurance**
 ```bash
-# Generate comprehensive test suite (standard workflow)
-/workflow:test-gen
-/workflow:execute
+# Generate independent test-fix workflow (v3.2.2+)
+/workflow:test-gen WFS-auth  # Creates WFS-test-auth session
+/workflow:execute            # Runs test validation

 # OR verify TDD compliance (TDD workflow)
 /workflow:tdd-verify
@@ -217,7 +253,7 @@ After installation, run the following command to ensure CCW is working:
 | `/workflow:tdd-plan` | Create a Test-Driven Development workflow with Red-Green-Refactor cycles. |
 | `/workflow:execute` | Execute the current workflow plan autonomously. |
 | `/workflow:status` | Display the current status of the workflow. |
-| `/workflow:test-gen` | Automatically generate a test plan from the implementation. |
+| `/workflow:test-gen` | Create independent test-fix workflow for validating completed implementation. |
 | `/workflow:tdd-verify` | Verify TDD compliance and generate quality report. |
 | `/workflow:review` | **Optional** manual review (only use when explicitly needed - passing tests = approved code). |

@@ -228,6 +264,7 @@ After installation, run the following command to ensure CCW is working:
 | `/task:*` | Manage individual tasks (`create`, `breakdown`, `execute`, `replan`). |
 | `/update-memory-full` | Re-index the entire project documentation. |
 | `/update-memory-related` | Update documentation related to recent changes. |
+| `/version` | Display version information and check for updates from GitHub. |

 ---

@@ -275,7 +312,7 @@ Configure Gemini CLI for optimal integration:
 ```json
 // ~/.gemini/settings.json
 {
-  "contextFileName": "CLAUDE.md"
+  "contextFileName": ["CLAUDE.md", "GEMINI.md"]
 }
 ```

@@ -306,7 +343,7 @@ MCP (Model Context Protocol) tools provide advanced codebase analysis. **Complet

 | MCP Server | Purpose | Installation Guide |
 |------------|---------|-------------------|
-| **Exa MCP** | External API patterns & best practices | [Install Guide](https://github.com/exa-labs/exa-mcp-server) |
+| **Exa MCP** | External API patterns & best practices | [Install Guide](https://smithery.ai/server/exa) |
 | **Code Index MCP** | Advanced internal code search | [Install Guide](https://github.com/johnhuang316/code-index-mcp) |

 #### Benefits When Enabled
--- a/README_CN.md
+++ b/README_CN.md
@@ -2,7 +2,7 @@

 <div align="center">

-[![Version](https://img.shields.io/badge/version-v3.2.1-blue.svg)](https://github.com/catlog22/Claude-Code-Workflow/releases)
+[![Version](https://img.shields.io/badge/version-v3.3.0-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)
@@ -15,13 +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: v3.2.0** - 采用"测试即审查"理念简化智能体架构。详见 [CHANGELOG.md](CHANGELOG.md)。
+> **🎉 最新版本: v3.3.0** - CLI 工具增强与 Codex 多步骤执行。详见 [CHANGELOG.md](CHANGELOG.md)。
 >
-> **v3.2.0 版本新特性**:
-> - 🔄 从 3 个智能体简化为 2 个核心智能体（`@code-developer`、`@test-fix-agent`）
-> - ✅ "测试即审查" - 测试通过 = 代码批准
-> - 🧪 增强的测试修复工作流，支持自动执行和修复
-> - 📦 交互式安装，包含版本选择菜单
+> **v3.3.0 版本新特性**:
+> - 🚀 新增 `/cli:codex-execute` 命令，实现自动化多步骤任务执行
+> - 🔄 Codex resume 机制（`codex exec "..." resume --last`），保持上下文连续性
+> - 📋 TodoWrite 进度跟踪，监控子任务执行状态
+> - 📚 精简 CLI 文档（减少 60% 冗余内容）
+> - 🔧 增强 Codex 智能体配置，支持多任务工作流
+> - ✅ 可选的 Git 验证，每个子任务完成后检查代码变更

 ---

@@ -94,17 +96,51 @@ bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflo

 > 💡 **提示**：安装程序会自动从 GitHub 检测并显示最新的版本号和发布日期。只需按 Enter 键即可选择推荐的稳定版本。

+### **📦 本地安装 (Install-Claude.ps1)**
+
+无需网络访问时，使用内置的 PowerShell 安装脚本：
+
+**安装模式：**
+```powershell
+# 交互式安装（推荐）
+.\Install-Claude.ps1
+
+# 快速安装（自动备份）
+.\Install-Claude.ps1 -Force -BackupAll
+
+# 非交互式安装
+.\Install-Claude.ps1 -NonInteractive -Force
+```
+
+**安装选项：**
+
+| 模式 | 描述 | 安装位置 |
+|------|------|----------|
+| **Global** | 系统级安装（默认） | `~/.claude/`、`~/.codex/`、`~/.gemini/` |
+| **Path** | 自定义目录 + 全局混合 | 本地：`agents/`、`commands/`<br>全局：`workflows/`、`scripts/` |
+
+**备份行为：**
+- **默认**：自动备份启用（`-BackupAll`）
+- **禁用**：使用 `-NoBackup` 标志（⚠️ 无备份覆盖）
+- **备份位置**：安装目录中的 `claude-backup-{timestamp}/`
+
+**⚠️ 重要警告：**
+- `-Force -BackupAll`：静默文件覆盖（带备份）
+- `-NoBackup -Force`：永久文件覆盖（无法恢复）
+- Global 模式会修改用户配置目录
+
 ### **✅ 验证安装**
 安装后，运行以下命令以确保 CCW 正常工作：
 ```bash
 /workflow:session:list
 ```

-> **📝 重要说明：**
+> **📝 安装说明：**
 > - 安装程序将自动安装/更新 `.codex/` 和 `.gemini/` 目录
 > - **全局模式**：安装到 `~/.codex` 和 `~/.gemini`
 > - **路径模式**：安装到指定目录（例如 `project/.codex`、`project/.gemini`）
-> - 安装前会自动备份现有文件
+> - **备份**：默认自动备份现有文件到 `claude-backup-{timestamp}/`
+> - **安全**：首次安装建议使用交互式模式以审查更改

 ---

@@ -142,15 +178,12 @@ bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflo

 **阶段 4：测试与质量保证**
 ```bash
-# 生成全面测试套件（标准工作流）
-/workflow:test-gen
-/workflow:execute
+# 生成独立测试修复工作流（v3.2.2+）
+/workflow:test-gen WFS-auth  # 创建 WFS-test-auth 会话
+/workflow:execute            # 运行测试验证

 # 或验证 TDD 合规性（TDD 工作流）
 /workflow:tdd-verify
-
-# 可选：手动审查（仅在明确需要时使用）
-# /workflow:review  # 测试通过 = 代码已批准
 ```

 ### 简单任务快速入门
@@ -220,7 +253,7 @@ bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflo
 | `/workflow:tdd-plan` | 创建测试驱动开发工作流，包含 Red-Green-Refactor 循环。 |
 | `/workflow:execute` | 自主执行当前的工作流计划。 |
 | `/workflow:status` | 显示工作流的当前状态。 |
-| `/workflow:test-gen` | 从实现中自动生成测试计划。 |
+| `/workflow:test-gen` | 创建独立测试修复工作流，用于验证已完成的实现。 |
 | `/workflow:tdd-verify` | 验证 TDD 合规性并生成质量报告。 |
 | `/workflow:review` | **可选** 手动审查（仅在明确需要时使用，测试通过即代表代码已批准）。 |

@@ -231,6 +264,7 @@ bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflo
 | `/task:*` | 管理单个任务（`create`, `breakdown`, `execute`, `replan`）。 |
 | `/update-memory-full` | 重新索引整个项目文档。 |
 | `/update-memory-related` | 更新与最近更改相关的文档。 |
+| `/version` | 显示版本信息并检查 GitHub 更新。 |

 ---

@@ -278,7 +312,7 @@ npm install -g @google/gemini-cli @openai/codex @qwen-code/qwen-code
 ```json
 // ~/.gemini/settings.json
 {
-  "contextFileName": "CLAUDE.md"
+  "contextFileName": ["CLAUDE.md", "GEMINI.md"]
 }
 ```

@@ -309,7 +343,7 @@ MCP (模型上下文协议) 工具提供高级代码库分析。**完全可选**

 | MCP 服务器 | 用途 | 安装指南 |
 |------------|------|---------|
-| **Exa MCP** | 外部 API 模式和最佳实践 | [安装指南](https://github.com/exa-labs/exa-mcp-server) |
+| **Exa MCP** | 外部 API 模式和最佳实践 | [安装指南](https://smithery.ai/server/exahttps://smithery.ai/server/exa) |
 | **Code Index MCP** | 高级内部代码搜索 | [安装指南](https://github.com/johnhuang316/code-index-mcp) |

 #### 启用后的好处
--- a/RELEASE_NOTES_v2.0.md
+++ b/RELEASE_NOTES_v2.0.md
@@ -1,264 +0,0 @@
-# 🚀 Claude Code Workflow (CCW) v2.0.0 Release Notes
-
-**Release Date**: September 28, 2025
-**Release Type**: Major Version Release
-**Repository**: https://github.com/catlog22/Claude-Code-Workflow
-
---
-
-## 📋 Overview
-
-Claude Code Workflow v2.0 represents a **major architectural evolution** with significant enhancements to the multi-agent automation framework. This release introduces a comprehensive four-layer architecture, enhanced workflow lifecycle management, and intelligent tech stack detection.
-
-> **🎯 Upgrade Recommendation**: This is a **breaking change release** with significant architectural improvements. Review the breaking changes section before upgrading.
-
---
-
-## 🌟 Major Features & Enhancements
-
-### 🏗️ **Four-Layer Architecture (NEW)**
-
-CCW now operates through four distinct architectural layers with defined responsibilities and data contracts:
-
-| Layer | Components | Data Flow | Integration Points |
-|-------|------------|-----------|-------------------|
-| **🖥️ Interface Layer** | CLI Commands, Gemini/Codex/Qwen Wrappers | User input → Commands → Agents | External CLI tools, approval modes |
-| **📋 Session Layer** | `.active-[session]` markers, `workflow-session.json` | Session state → Task discovery | Atomic session switching |
-| **📊 Task/Data Layer** | `.task/impl-*.json`, hierarchy management | Task definitions → Agent execution | JSON-first model, generated views |
-| **🤖 Orchestration Layer** | Multi-agent coordination, dependency resolution | Agent outputs → Task updates | Intelligent execution flow |
-
-### 🔄 **Enhanced Workflow Lifecycle**
-
-Complete development lifecycle with quality gates at each phase:
-
-1. **💡 Brainstorm Phase** - Multi-perspective conceptual planning with role-based analysis
-2. **📋 Plan Phase** - Structured implementation planning with task decomposition
-3. **✅ Verify Phase** - Pre-execution validation using Gemini (strategic) + Codex (technical)
-4. **⚡ Execute Phase** - Autonomous implementation with multi-agent orchestration
-5. **🧪 Test Phase** - Automated test workflow generation with comprehensive coverage
-6. **🔍 Review Phase** - Quality assurance and completion validation
-
-### 🧪 **Automated Test Generation**
-
-Comprehensive test workflow creation:
- **Implementation Analysis**: Scans completed IMPL-* tasks for test requirements
- **Multi-layered Testing**: Unit, Integration, E2E, Performance, Security tests
- **Agent Assignment**: Specialized test agents for different test types
- **Dependency Mapping**: Test execution follows implementation dependency chains
-
-### ✅ **Plan Verification System**
-
-Dual-engine validation before execution:
- **Gemini Strategic Analysis**: High-level feasibility and architectural soundness
- **Codex Technical Analysis**: Implementation details and technical feasibility
- **Cross-Validation**: Identifies conflicts between strategic vision and technical constraints
- **Improvement Suggestions**: Actionable recommendations before implementation begins
-
-### 🧠 **Smart Tech Stack Detection**
-
-Intelligent task-based loading of technology guidelines:
- **Automatic Detection**: Only loads tech stacks for development and code review tasks
- **Multi-Language Support**: TypeScript, React, Python, Java, Go, JavaScript
- **Performance Optimized**: Skips detection for non-relevant tasks
- **Context-Aware**: Applies appropriate tech stack principles to development work
-
-### 🔮 **Qwen CLI Integration**
-
-Full integration of Qwen CLI for architecture analysis and code generation:
- **Architecture Analysis**: System design patterns and code quality assessment
- **Code Generation**: Implementation scaffolding and component creation
- **Intelligent Modes**: Auto template selection and precise architectural planning
-
---
-
-## 📊 New Commands & Capabilities
-
-### **Issue Management Commands**
- `➕ /workflow:issue:create` - Create new project issues with priority and type
- `📋 /workflow:issue:list` - List and filter issues by status and assignment
- `📝 /workflow:issue:update` - Update existing issue status and assignments
- `✅ /workflow:issue:close` - Close completed issues with resolution reasons
-
-### **Enhanced Workflow Commands**
- `✅ /workflow:plan-verify` - Pre-execution validation using dual analysis
- `🧪 /workflow:test-gen` - Generate comprehensive test workflows
- `🎨 /workflow:brainstorm:artifacts` - Generate structured planning documents
- `🔍 /workflow:plan-deep` - Deep technical planning with Gemini analysis
-
-### **Qwen CLI Commands**
- `🔍 /qwen:analyze` - Architecture analysis and code quality assessment
- `💬 /qwen:chat` - Direct Qwen interaction for design discussions
- `⚡ /qwen:execute` - Intelligent implementation with YOLO permissions
- `🚀 /qwen:mode:auto` - Auto template selection and execution
- `🐛 /qwen:mode:bug-index` - Bug analysis and fix suggestions
- `📋 /qwen:mode:plan` - Architecture planning and analysis
-
---
-
-## 🔧 Technical Improvements
-
-### **Script & Tool Enhancements**
- **gemini-wrapper**: Improved token management and path handling
- **qwen-wrapper**: Streamlined execution and simplified interface
- **Cross-Platform**: Enhanced Windows path compatibility with proper quoting
- **Directory Navigation**: Intelligent context optimization for focused analysis
-
-### **Agent Improvements**
- **Flow Control**: Enhanced sequential execution with context accumulation
- **Context Assessment**: Smart tech stack loading for relevant tasks only
- **Error Handling**: Improved per-step error strategies
- **Variable Passing**: Context transfer between execution steps
-
-### **Documentation Overhaul**
- **Unified Structure**: Aligned English and Chinese documentation
- **Command Standardization**: Consistent syntax across all commands
- **Architecture Clarity**: Clear data flow and integration point descriptions
- **Version Synchronization**: Both language versions now reflect v2.0 features
-
---
-
-## 📈 Performance & Compatibility
-
-### **Performance Metrics**
-| Metric | Performance | Details |
-|--------|-------------|---------|
-| 🔄 **Session Switching** | <10ms | Atomic marker file operations |
-| 📊 **JSON Queries** | <1ms | Direct JSON access, no parsing overhead |
-| 📝 **Doc Updates** | <30s | Medium projects, intelligent targeting |
-| 🔍 **Context Loading** | <5s | Complex codebases with caching |
-| ⚡ **Task Execution** | 10min timeout | Complex operations with error handling |
-
-### **System Requirements**
- **🖥️ OS**: Windows 10+, Ubuntu 18.04+, macOS 10.15+
- **📦 Dependencies**: Git, Node.js (Gemini), Python 3.8+ (Codex)
- **💾 Storage**: ~50MB core + variable project data
- **🧠 Memory**: 512MB minimum, 2GB recommended
-
-### **Integration Requirements**
- **🔍 Gemini CLI**: Required for analysis and strategic planning workflows
- **🤖 Codex CLI**: Required for autonomous development and bug fixing
- **🔮 Qwen CLI**: Required for architecture analysis and code generation
- **📂 Git Repository**: Required for change tracking and version control
-
---
-
-## ⚠️ Breaking Changes
-
-### **Removed Components**
- **Python CLI Backend**: All `pycli` references and related scripts removed
- **Deprecated Scripts**: `install_pycli.sh`, `pycli`, `pycli.conf`, `tech-stack-loader.sh`
- **Legacy Commands**: Old path reading scripts and unused Python tools
-
-### **Command Syntax Changes**
- **Session Commands**: `/workflow:session list` → `/workflow:session:list`
- **File Naming**: Standardized to lowercase `.task/impl-*.json`
- **Session Markers**: Unified format `.active-[session]`
-
-### **Architecture Changes**
- **Data Model**: Migrated to JSON-first architecture
- **Session Management**: Atomic marker-based system
- **Task Structure**: Standardized hierarchy and status management
-
-### **Configuration Updates**
-Required Gemini CLI configuration:
-```json
-{
-  "contextFileName": "CLAUDE.md"
-}
-```
-
---
-
-## 🚀 Migration Guide
-
-### **From v1.x to v2.0**
-
-1. **Update Configuration**:
-   ```bash
-   # Update Gemini CLI settings
-   echo '{"contextFileName": "CLAUDE.md"}' > ~/.gemini/settings.json
-   ```
-
-2. **Clean Legacy Files**:
-   ```bash
-   # Remove old Python CLI references
-   rm -f .claude/scripts/pycli*
-   rm -f .claude/scripts/install_pycli.sh
-   ```
-
-3. **Update Command Usage**:
-   ```bash
-   # Old syntax
-   /workflow:session list
-
-   # New syntax
-   /workflow:session:list
-   ```
-
-4. **Verify Installation**:
-   ```bash
-   /workflow:session:list
-   ```
-
---
-
-## 📚 Documentation & Resources
-
-### **Updated Documentation**
- **README.md**: Complete v2.0 feature documentation
- **README_CN.md**: Chinese documentation with v2.0 alignment
- **Architecture Guides**: Four-layer system documentation
- **Command Reference**: Comprehensive CLI command tables
-
-### **Quick Start**
-```bash
-# Install CCW v2.0
-Invoke-Expression (Invoke-WebRequest -Uri "https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.ps1" -UseBasicParsing).Content
-
-# Verify installation
-/workflow:session:list
-
-# Start first workflow
-/workflow:session:start "My First Project"
-```
-
---
-
-## 🤝 Contributing & Support
-
-### **Development**
- **GitHub**: https://github.com/catlog22/Claude-Code-Workflow
- **Issues**: https://github.com/catlog22/Claude-Code-Workflow/issues
- **Discussions**: https://github.com/catlog22/Claude-Code-Workflow/discussions
-
-### **Community**
- **Documentation**: [Project Wiki](https://github.com/catlog22/Claude-Code-Workflow/wiki)
- **Changelog**: [Release History](CHANGELOG.md)
- **License**: MIT License
-
---
-
-## 🙏 Acknowledgments
-
-Special thanks to the community for feedback and contributions that made v2.0 possible. This release represents a significant step forward in automated development workflow capabilities.
-
---
-
-**🚀 Claude Code Workflow v2.0**
-
-*Professional software development workflow automation through intelligent multi-agent coordination and autonomous execution capabilities.*
-
---
-
-## 📝 Commit History Summary
-
-This release includes 15+ commits spanning major architectural improvements:
-
- **5d08c53**: Smart tech stack detection for agents
- **b956943**: Workflow architecture documentation updates
- **8baca52**: README v2.0 alignment and four-layer architecture
- **0756682**: Python CLI cleanup and modernization
- **be4db94**: Concept evaluation framework addition
- **817f51c**: Qwen CLI integration and task commands
-
-For complete commit history, see: [GitHub Commits](https://github.com/catlog22/Claude-Code-Workflow/commits/main)
--- a/RELEASE_NOTES_v3.2.1.md
+++ b/RELEASE_NOTES_v3.2.1.md
@@ -1,142 +0,0 @@
-# 🔧 Claude Code Workflow (CCW) v3.2.1 Release Notes
-
-**Release Date**: October 2, 2025
-**Release Type**: Patch Release - Documentation Fix
-**Repository**: https://github.com/catlog22/Claude-Code-Workflow
-
---
-
-## 📋 Overview
-
-CCW v3.2.1 is a critical documentation fix release that corrects `workflow-session.json` path references throughout the brainstorming workflow documentation. This ensures consistency with the architecture specification defined in `workflow-architecture.md`.
-
---
-
-## 🐛 Bug Fixes
-
-### **Documentation Path Corrections**
-
-**Issue**: Documentation incorrectly referenced `workflow-session.json` inside the `.brainstorming/` subdirectory
-
-**Impact**:
- Confusing path references in 9 brainstorming role documentation files
- Inconsistency with architectural specifications
- Potential runtime errors when commands attempt to read session metadata
-
-**Fixed Files** (9 total):
-1. ✅ `data-architect.md`
-2. ✅ `product-manager.md`
-3. ✅ `product-owner.md`
-4. ✅ `scrum-master.md`
-5. ✅ `subject-matter-expert.md`
-6. ✅ `ui-designer.md`
-7. ✅ `ux-expert.md`
-8. ✅ `auto-parallel.md`
-9. ✅ `artifacts.md`
-
-**Corrections Applied**:
- ❌ **Incorrect**: `.workflow/WFS-{session}/.brainstorming/workflow-session.json`
- ✅ **Correct**: `.workflow/WFS-{session}/workflow-session.json`
-
---
-
-## 📐 Architecture Alignment
-
-### Confirmed Standard Structure
-```
-.workflow/WFS-[topic-slug]/
-├── workflow-session.json        # ✅ Session metadata (root level)
-├── .brainstorming/              # Brainstorming artifacts subdirectory
-│   └── topic-framework.md
-├── IMPL_PLAN.md
-├── TODO_LIST.md
-└── .task/
-    └── IMPL-*.json
-```
-
-### Key Points
- `workflow-session.json` is **always at session root level**
- `.brainstorming/` directory contains **only** framework and analysis files
- No session metadata files inside subdirectories
-
---
-
-## 📊 Changes Summary
-
-| Category | Files Changed | Lines Modified |
-|----------|--------------|----------------|
-| Documentation Fixes | 9 | 19 insertions, 18 deletions |
-| Path Corrections | 8 role files | 2 corrections per file |
-| Structure Clarifications | 1 artifacts file | Added architectural note |
-
---
-
-## ✅ Verification
-
-**Pre-Release Checks**:
- ✅ No incorrect `.brainstorming/workflow-session.json` references
- ✅ No legacy `session.json` references
- ✅ All brainstorming roles use correct paths
- ✅ Architecture consistency verified with Gemini analysis
-
---
-
-## 🔄 Upgrade Instructions
-
-### For Existing Users
-
-**No action required** - This is a documentation-only fix.
-
-1. Pull the latest changes:
-   ```bash
-   git pull origin main
-   ```
-
-2. Review updated documentation:
-   - `.claude/commands/workflow/brainstorm/*.md`
-
-### For New Users
-
-Simply clone the repository with the correct documentation:
-```bash
-git clone https://github.com/catlog22/Claude-Code-Workflow.git
-```
-
---
-
-## 📚 Related Documentation
-
- **Architecture Reference**: `.claude/workflows/workflow-architecture.md`
- **Brainstorming Commands**: `.claude/commands/workflow/brainstorm/`
- **Session Management**: `.claude/commands/workflow/session/`
-
---
-
-## 🙏 Acknowledgments
-
-Special thanks to the analysis tools used in this fix:
- **Gemini CLI**: Path verification and consistency checking
- **Codex**: Initial codebase analysis
- **Claude Code**: Documentation review and corrections
-
---
-
-## 🔗 Links
-
- **Full Changelog**: [v3.2.0...v3.2.1](https://github.com/catlog22/Claude-Code-Workflow/compare/v3.2.0...v3.2.1)
- **Issues Fixed**: Documentation consistency issue
- **Previous Release**: [v3.2.0 Release Notes](RELEASE_NOTES_v3.2.0.md)
-
---
-
-## 📝 Notes
-
- This is a **non-breaking change** - existing workflows will continue to function
- Documentation now correctly reflects the implemented architecture
- No code changes were necessary - this was purely a documentation correction
-
---
-
-**Contributors**: Claude Code Development Team
-**License**: MIT
-**Support**: [GitHub Issues](https://github.com/catlog22/Claude-Code-Workflow/issues)
--- a/RELEASE_NOTES_v3.2.3.md
+++ b/RELEASE_NOTES_v3.2.3.md
@@ -0,0 +1,252 @@
+# v3.2.3 - Version Management System
+
+## 🎉 Release Date
+2025-10-03
+
+## ✨ Overview
+
+This release introduces a comprehensive version management and upgrade notification system, making it easy to track your Claude Code Workflow installation and stay up-to-date with the latest releases.
+
+## 🆕 New Features
+
+### `/version` Command
+
+A powerful new command that provides complete version information and automatic update checking:
+
+**Features:**
+- 📊 **Version Display**: Shows both local and global installation versions
+- 🌐 **GitHub Integration**: Fetches latest stable release and development commits
+- 🔄 **Smart Comparison**: Automatically compares installed version with latest available
+- 💡 **Upgrade Recommendations**: Provides installation commands for easy upgrading
+- ⚡ **Fast Execution**: 30-second timeout for network calls, graceful offline handling
+
+**Usage:**
+```bash
+/version
+```
+
+**Example Output:**
+```
+Installation Status:
+- Local: No project-specific installation
+- Global: ✅ Installed at ~/.claude
+  - Version: v3.2.3
+  - Installed: 2025-10-03T05:01:34Z
+
+Latest Releases:
+- Stable: v3.2.3 (2025-10-03T04:10:08Z)
+  - v3.2.3: Version Management System
+- Latest Commit: c5c36a2 (2025-10-03T05:00:06Z)
+  - fix: Optimize version command API calls and data extraction
+
+Status: ✅ You are on the latest stable version (3.2.3)
+```
+
+### Version Tracking System
+
+**Version Files:**
+- `.claude/version.json` - Local project installation tracking
+- `~/.claude/version.json` - Global installation tracking
+
+**Tracked Information:**
+```json
+{
+  "version": "v3.2.3",
+  "installation_mode": "Global",
+  "installation_path": "C:\\Users\\username\\.claude",
+  "source_branch": "main",
+  "installation_date_utc": "2025-10-03T05:01:34Z"
+}
+```
+
+### GitHub API Integration
+
+**Endpoints Used:**
+- **Latest Release**: `https://api.github.com/repos/catlog22/Claude-Code-Workflow/releases/latest`
+  - Extracts: tag_name, release name, published date
+- **Latest Commit**: `https://api.github.com/repos/catlog22/Claude-Code-Workflow/commits/main`
+  - Extracts: commit SHA, message, author date
+
+**Network Handling:**
+- 30-second timeout for slow connections
+- Graceful error handling for offline scenarios
+- No external dependencies (uses curl and grep/sed)
+
+## 🔄 What's Changed
+
+### Documentation Updates
+
+**Updated Files:**
+- ✅ `CHANGELOG.md` - Added comprehensive v3.2.3 release notes
+- ✅ `README.md` - Updated version badge to v3.2.3, added `/version` command
+- ✅ `README_CN.md` - Updated version badge and command reference (Chinese)
+- ✅ `.claude/commands/version.md` - Complete implementation guide
+
+**Version References:**
+- All version badges updated from v3.2.2 to v3.2.3
+- "What's New" sections updated with v3.2.3 features
+- Command reference tables include `/version` command
+
+### Installation Scripts Enhancement
+
+**Future Enhancement** (for next release):
+- Installation scripts will automatically create `version.json` files
+- Track installation mode (local vs global)
+- Record installation timestamp
+- Support version tracking for both stable and development installations
+
+## 📋 Version Comparison Scenarios
+
+### Scenario 1: Up to Date
+```
+✅ You are on the latest stable version (3.2.3)
+```
+
+### Scenario 2: Upgrade Available
+```
+⬆️ A newer stable version is available: v3.2.4
+Your version: 3.2.3
+
+To upgrade:
+PowerShell: iex (iwr -useb https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.ps1)
+Bash: bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.sh)
+```
+
+### Scenario 3: Development Version
+```
+✨ You are running a development version (3.3.0-dev)
+This is newer than the latest stable release (v3.2.3)
+```
+
+## 🛠️ Technical Details
+
+### Implementation Highlights
+
+**Simple Bash Commands:**
+- No jq dependency required (uses grep/sed for JSON parsing)
+- Cross-platform compatible (Windows Git Bash, Linux, macOS)
+- Version comparison using `sort -V` for semantic versioning
+- Direct API access using curl with error suppression
+
+**Command Structure:**
+```bash
+# Check local version
+test -f ./.claude/version.json && cat ./.claude/version.json
+
+# Check global version
+test -f ~/.claude/version.json && cat ~/.claude/version.json
+
+# Fetch latest release (with timeout)
+curl -fsSL "https://api.github.com/repos/catlog22/Claude-Code-Workflow/releases/latest" 2>/dev/null
+
+# Extract version
+grep -o '"tag_name": *"[^"]*"' | cut -d'"' -f4
+
+# Compare versions
+printf "%s\n%s" "3.2.2" "3.2.3" | sort -V | tail -n 1
+```
+
+## 📊 Benefits
+
+### User Experience
+- 🔍 **Quick version check** with single command
+- 📊 **Comprehensive information** display (local, global, stable, dev)
+- 🔄 **Automatic upgrade notifications** when new versions available
+- 📈 **Development version tracking** for cutting-edge features
+- 🌐 **GitHub integration** for latest updates
+
+### DevOps
+- 📁 **Version tracking** in both local and global installations
+- 🕐 **Installation timestamp** for audit trails
+- 🔀 **Support for both stable and development** branches
+- ⚡ **Fast execution** with 30-second network timeout
+- 🛡️ **Graceful error handling** for offline scenarios
+
+## 🔗 Related Commands
+
+- `/cli:cli-init` - Initialize CLI tool configurations
+- `/workflow:session:list` - List workflow sessions
+- `/update-memory-full` - Update project documentation
+
+## 📦 Installation
+
+### Fresh Installation
+
+**Windows (PowerShell):**
+```powershell
+iex (iwr -useb https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.ps1)
+```
+
+**Linux/macOS (Bash):**
+```bash
+bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.sh)
+```
+
+### Upgrade from v3.2.2
+
+Use the same installation commands above. The installer will automatically:
+1. Detect your existing installation
+2. Back up current files (if using `-BackupAll`)
+3. Update to v3.2.3
+4. Create/update `version.json` files
+
+## 🐛 Bug Fixes
+
+- Fixed commit message extraction to handle JSON escape sequences
+- Improved API endpoint from `/branches/main` to `/commits/main` for reliable commit info
+- Added 30-second timeout to all network calls for slow connections
+- Enhanced release name and published date extraction
+
+## 📚 Documentation
+
+### New Documentation
+- `.claude/commands/version.md` - Complete command implementation guide
+  - API endpoints and usage
+  - Timeout configuration
+  - Error handling scenarios
+  - Simple bash command examples
+
+### Updated Documentation
+- `CHANGELOG.md` - v3.2.3 release notes
+- `README.md` - Version badge and command reference
+- `README_CN.md` - Chinese version updates
+
+## 🙏 Credits
+
+This release includes contributions and improvements based on:
+- GitHub API integration for version detection
+- Cross-platform bash command compatibility
+- User feedback on installation and upgrade processes
+
+## 📝 Notes
+
+- **Backward Compatible**: All existing commands and workflows continue to work
+- **No Breaking Changes**: This is a minor release with new features only
+- **Optional Feature**: `/version` command is entirely optional, existing workflows unaffected
+
+## 🚀 What's Next
+
+**Planned for v3.2.4:**
+- Enhanced installation script to auto-create version.json
+- Version tracking in all installation modes
+- Automatic version detection during installation
+
+**Future Enhancements:**
+- Auto-update functionality (opt-in)
+- Version comparison in workflow sessions
+- Release notes display in CLI
+
+---
+
+**Full Changelog**: [v3.2.2...v3.2.3](https://github.com/catlog22/Claude-Code-Workflow/compare/v3.2.2...v3.2.3)
+
+**Installation:**
+```bash
+# One-line install (recommended)
+bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.sh)
+
+# Or use specific version tag
+git clone -b v3.2.3 https://github.com/catlog22/Claude-Code-Workflow.git
+```
+
+🤖 Generated with [Claude Code](https://claude.com/claude-code)
--- a/install-remote.ps1
+++ b/install-remote.ps1
@@ -258,23 +258,25 @@ function Extract-Repository {

 function Invoke-LocalInstaller {
    param(
-        [string]$RepoDir
+        [string]$RepoDir,
+        [string]$VersionInfo = "",
+        [string]$BranchInfo = ""
    )
-    
+
    $installerPath = Join-Path $RepoDir "Install-Claude.ps1"
-    
+
    if (-not (Test-Path $installerPath)) {
        Write-ColorOutput "ERROR: Install-Claude.ps1 not found" $ColorError
        return $false
    }
-    
+
    Write-ColorOutput "Running local installer..." $ColorInfo
    Write-Host ""
-    
+
    # Build parameters for local installer
    $params = @{}
    if ($Global) { $params["InstallMode"] = "Global" }
-    if ($Directory) { 
+    if ($Directory) {
        $params["InstallMode"] = "Custom"
        $params["TargetPath"] = $Directory
    }
@@ -282,11 +284,15 @@ function Invoke-LocalInstaller {
    if ($NoBackup) { $params["NoBackup"] = $NoBackup }
    if ($NonInteractive) { $params["NonInteractive"] = $NonInteractive }
    if ($BackupAll) { $params["BackupAll"] = $BackupAll }
-    
+
+    # Pass version and branch information
+    if ($VersionInfo) { $params["SourceVersion"] = $VersionInfo }
+    if ($BranchInfo) { $params["SourceBranch"] = $BranchInfo }
+
    try {
        # Change to repo directory and run installer
        Push-Location $RepoDir
-        
+
        if ($params.Count -gt 0) {
            $paramList = ($params.GetEnumerator() | ForEach-Object { "-$($_.Key) $($_.Value)" }) -join " "
            Write-ColorOutput "Executing: & `"$installerPath`" $paramList" $ColorInfo
@@ -295,7 +301,7 @@ function Invoke-LocalInstaller {
            Write-ColorOutput "Executing: & `"$installerPath`"" $ColorInfo
            & $installerPath
        }
-        
+
        Pop-Location
        return $true
    } catch {
@@ -542,26 +548,32 @@ function Main {
    # Create temp directory
    $tempDir = Get-TempDirectory
    Write-ColorOutput "Temporary directory: $tempDir" $ColorInfo
-    
+
    try {
        # Download repository
        $zipPath = Download-Repository -TempDir $tempDir -Version $Version -Branch $Branch -Tag $Tag
        if (-not $zipPath) {
            throw "Download failed"
        }
-        
+
        # Extract repository
        $repoDir = Extract-Repository $zipPath $tempDir
        if (-not $repoDir) {
            throw "Extraction failed"
        }
-        
-        # Run local installer
-        $success = Invoke-LocalInstaller $repoDir
+
+        # Determine version and branch information to pass
+        $versionToPass = if ($Tag) { $Tag } else { "latest" }
+        $branchToPass = if ($Version -eq "branch") { $Branch } elseif ($Version -eq "latest") { "main" } elseif ($Tag) { $Tag } else { "main" }
+
+        Write-ColorOutput "Version info: $versionToPass (branch: $branchToPass)" $ColorInfo
+
+        # Run local installer with version information
+        $success = Invoke-LocalInstaller -RepoDir $repoDir -VersionInfo $versionToPass -BranchInfo $branchToPass
        if (-not $success) {
            throw "Installation script failed"
        }
-        
+
        Write-Host ""
        Write-ColorOutput "Remote installation completed successfully!" $ColorSuccess
        
--- a/install-remote.sh
+++ b/install-remote.sh
@@ -43,8 +43,8 @@ function show_header() {

 function test_prerequisites() {
    # Test bash version
-    if [ "${BASH_VERSINFO[0]}" -lt 4 ]; then
-        write_color "ERROR: Bash 4.0 or higher is required" "$COLOR_ERROR"
+    if [ "${BASH_VERSINFO[0]}" -lt 2 ]; then
+        write_color "ERROR: Bash 2.0 or higher is required" "$COLOR_ERROR"
        write_color "Current version: ${BASH_VERSION}" "$COLOR_ERROR"
        return 1
    fi
Author	SHA1	Message	Date
catlog22	3a78dac919	release: v3.3.0 - CLI Tool Enhancements & Codex Multi-Step Execution ✨ Features: - New /cli:codex-execute command for automated multi-step task execution - Codex resume mechanism (codex exec "..." resume --last) for context continuity - TodoWrite progress tracking for subtask execution - Optional Git verification after each subtask (--verify-git flag) - Automatic task JSON detection and loading - Enhanced Codex agent configuration (.codex/AGENTS.md v2.1.0) 📚 Documentation: - Streamlined CLI documentation (60% reduction in redundancy) - Updated /cli:analyze, /cli:chat, /cli:execute commands - Enhanced intelligent-tools-strategy.md with Codex resume patterns - Unified command templates for Gemini/Qwen vs Codex - Added Codex -i parameter documentation for image attachment 🔧 Technical: - Multi-task prompt format (Single-Task & Multi-Task) - Subtask coordination guidelines and best practices - Enhanced MODE: auto with subtask execution flow - Progress reporting for multi-step workflows 📦 Updates: - Version bumped to 3.3.0 in README.md, README_CN.md - Created .claude/version.json for version tracking - Comprehensive CHANGELOG.md entry with all changes 🤖 Generated with Claude Code (https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-04 00:51:34 +08:00
catlog22	4b578285ea	refactor: Enhance tool write protection and lower Bash requirement - Add explicit write operation protection in intelligent-tools-strategy - Require MODE=write or MODE=auto for local codebase modifications - Default all tools to read-only analysis mode - Convert all Chinese text to English for consistency - Lower Bash version requirement from 4.0 to 2.0 in Install-Claude.sh - Align with install-remote.sh requirements - Improve compatibility with older systems 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-04 00:09:17 +08:00
catlog22	5c66e268ec	fix: Clarify auto-continue workflow execution model in plan command - Replace sequential execution model with explicit auto-continue pattern - Document that each phase returns to user before auto-continuing - Use TodoList state for progress tracking (no external state files) - Store parsed data (sessionId, contextPath) in memory between phases - Clarify error handling keeps phase in_progress without proceeding 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-03 23:56:09 +08:00
catlog22	de4914f046	fix: Lower Bash version requirement from 4.0 to 2.0 Based on Gemini analysis, all script features (double brackets, local keyword, BASH_VERSINFO array) are supported in Bash 2.0+. This change improves compatibility with older systems while maintaining full functionality. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-03 21:23:23 +08:00
catlog22	00d1be60cb	refactor: Rename DMS directory to memory and update references - Renamed .claude/workflows/cli-templates/prompts/dms/ to memory/ - Updated all path references in update_module_claude.sh - Updated terminology in INSTALL.md and INSTALL_CN.md - Changed DMS system references to memory system 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-03 13:46:44 +08:00
catlog22	f549dfcc9b	release: v3.2.3 - Version Management System Add comprehensive version management and upgrade notification system: New Features: - Add /version command for checking installed versions - GitHub API integration for latest release detection - Automatic upgrade notifications and recommendations - Version tracking in both local and global installations - Quick version check with comprehensive status display Documentation Updates: - Update CHANGELOG.md with v3.2.3 release notes - Update README.md version badge to v3.2.3 - Update README_CN.md with Chinese version documentation - Add RELEASE_NOTES_v3.2.3.md with detailed release information - Add /version command to command reference tables Cleanup: - Remove old release notes (RELEASE_NOTES_v2.0.md, RELEASE_NOTES_v3.2.1.md) Version Files: - Update ~/.claude/version.json to v3.2.3 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-03 13:09:37 +08:00
catlog22	c5c36a23ea	fix: Optimize version command API calls and data extraction - Change API endpoint from /branches/main to /commits/main for reliable commit info - Add 30-second timeout to all network calls for slow connections - Extract release name and published date from latest release - Extract commit message (first line only) using improved parsing - Add commit date extraction from main branch - Update documentation with API endpoints and timeout configuration - Fix commit message extraction to handle JSON escape sequences 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-03 13:00:06 +08:00
catlog22	a03415bfeb	feat: Add version tracking and upgrade check system - Add /version command to check installed and latest versions - Create version.json metadata file during installation - Pass version and branch info from install-remote.ps1 to Install-Claude.ps1 - Support version comparison and upgrade recommendations - Track installation mode (Global/Path) and source branch 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-03 12:46:44 +08:00
catlog22	06772c675e	docs: Enhance core coding principles with engineering best practices Integrated five fundamental engineering principles at the start of Core Beliefs: - Good taste: eliminate edge cases for elegant logic - Extreme simplicity: complexity as root cause of issues - Pragmatism: solve real problems, not hypothetical ones - Data structures first: prioritize data design over code - Backward compatibility: preserve existing functionality These principles complement existing guidelines while emphasizing foundational software engineering wisdom. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-03 12:24:29 +08:00
catlog22	8c062f3611	docs: Update README files for v3.2.2 release Update both English and Chinese README files to reflect v3.2.2 changes: Version Updates: - Bump version badge from v3.2.1 to v3.2.2 - Update "What's New" section with v3.2.2 features Key Documentation Changes: - Independent test session architecture (WFS-test-[source]) - Automatic cross-session context gathering via metadata - Integrated concept-enhanced analysis (Gemini + Codex parallel) - Reuses IMPL-*.json format with meta.type="test-fix" - 4-phase workflow: session → context → analysis → task generation Command Reference Updates: - Updated /workflow:test-gen description to reflect independent workflow creation - Updated Phase 4 examples to show new usage: /workflow:test-gen WFS-auth Changes in Both Files: - README.md: English version updated - README_CN.md: Chinese version updated with matching content 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-03 12:07:35 +08:00