catlog22 d9fcdad949 refactor(workflow): migrate to sessions/ subdirectory structure
Refactor workflow directory structure to improve clarity and robustness by introducing dedicated sessions/ subdirectory for active sessions.

## Directory Structure Changes

### Before (Old Structure)
```
.workflow/
├── .active-WFS-session-1    # Marker files (fragile)
├── WFS-session-1/           # Active sessions mixed with config
├── WFS-session-2/
├── project.json
└── .archives/               # Archived sessions
```

### After (New Structure)
```
.workflow/
├── project.json             # Project metadata
├── sessions/                # [NEW] All active sessions
│   └── WFS-session-1/
└── archives/                # Archived sessions (removed dot prefix)
```

## Key Improvements

1. **Physical Isolation**: Active sessions now in dedicated sessions/ subdirectory
2. **No Marker Files**: Removed fragile .active-* marker file mechanism
3. **Directory-Based State**: Session state determined by directory location
   - In sessions/ = active
   - In archives/ = archived
4. **Simpler Discovery**: `ls .workflow/sessions/` instead of `find .workflow/ -name ".active-*"`
5. **Cleaner Root**: .workflow/ root now only contains project.json, sessions/, archives/

## Path Transformations

| Old Pattern | New Pattern |
|-------------|-------------|
| `find .workflow/ -name ".active-*"` | `find .workflow/sessions/ -name "WFS-*" -type d` |
| `.workflow/WFS-[slug]/` | `.workflow/sessions/WFS-[slug]/` |
| `.workflow/.archives/` | `.workflow/archives/` |
| `touch .workflow/.active-*` | *Removed* |
| `rm .workflow/.active-*` | *Removed* |

## Modified Commands

### session/start.md
- Update session creation path to .workflow/sessions/WFS-*/
- Remove .active-* marker file creation
- Update session discovery to use directory listing
- Updated all 3 modes: Discovery, Auto, Force New

### session/complete.md
- Update session move from sessions/ to archives/
- Remove .active-* marker file deletion
- Update manifest path to archives/manifest.json
- Update agent prompts with new paths

### status.md
- Update session discovery to find .workflow/sessions/
- Update all session file path references
- Update archive query examples

### execute.md
- Update session discovery logic
- Update all task file paths to include sessions/ prefix
- Update context package paths
- Update error handling documentation

## Benefits

- **Robustness**: Eliminates marker file state inconsistency risk
- **Clarity**: Clear separation between active and archived sessions
- **Simplicity**: Session discovery is straightforward directory listing
- **Alignment**: Closer to OpenSpec's three-layer structure (specs/changes/archive)

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-18 11:34:52 +08:00

🚀 Claude Code Workflow (CCW)

Version License Platform

Languages: English | 中文


Claude Code Workflow (CCW) transforms AI development from simple prompt chaining into a robust, context-first orchestration system. It solves execution uncertainty and error accumulation through structured planning, deterministic execution, and intelligent multi-model orchestration.

🎉 Version 5.8.1: Lite-Plan Workflow & CLI Tools Enhancement

Core Improvements:

  • Lite-Plan Workflow (/workflow:lite-plan) - Lightweight interactive planning with intelligent automation
    • Three-Dimensional Multi-Select Confirmation: Task approval + Execution method + Code review tool
    • Smart Code Exploration: Auto-detects when codebase context is needed (use -e flag to force)
    • Parallel Task Execution: Identifies independent tasks for concurrent execution
    • Flexible Execution: Choose between Agent (@code-developer) or CLI (Gemini/Qwen/Codex)
    • Optional Post-Review: Built-in code quality analysis with your choice of AI tool
  • CLI Tools Optimization - Simplified command syntax with auto-model-selection
    • Removed -m parameter requirement for Gemini, Qwen, and Codex (auto-selects best model)
    • Clearer command structure and improved documentation
  • 🔄 Execution Workflow Enhancement - Streamlined phases with lazy loading strategy
  • 🎨 CLI Explore Agent - Improved visibility with yellow color scheme

See CHANGELOG.md for full details.

📚 New to CCW? Check out the Getting Started Guide for a beginner-friendly 5-minute tutorial!


Core Concepts

CCW is built on a set of core principles that differentiate it from traditional AI development approaches:

  • Context-First Architecture: Pre-defined context gathering eliminates execution uncertainty by ensuring agents have the correct information before implementation.
  • JSON-First State Management: Task states live in .task/IMPL-*.json files as the single source of truth, enabling programmatic orchestration without state drift.
  • Autonomous Multi-Phase Orchestration: Commands chain specialized sub-commands and agents to automate complex workflows with zero user intervention.
  • Multi-Model Strategy: Leverages the unique strengths of different AI models (Gemini for analysis, Codex for implementation) for superior results.
  • Hierarchical Memory System: A 4-layer documentation system provides context at the appropriate level of abstraction, preventing information overload.
  • Specialized Role-Based Agents: A suite of agents (@code-developer, @test-fix-agent, etc.) mirrors a real software team to handle diverse tasks.

⚙️ Installation

For detailed installation instructions, please refer to the INSTALL.md guide.

🚀 Quick One-Line Installation

Windows (PowerShell):

Invoke-Expression (Invoke-WebRequest -Uri "https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.ps1" -UseBasicParsing).Content

Linux/macOS (Bash/Zsh):

bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.sh)

Verify Installation

After installation, open Claude Code and check if the workflow commands are available by running:

/workflow:session:list

If the slash commands (e.g., /workflow:*) are recognized, the installation was successful.


🛠️ Command Reference

CCW provides a rich set of commands for managing workflows, tasks, and interacting with AI tools. For a complete list and detailed descriptions of all available commands, please see the COMMAND_REFERENCE.md file.

For a detailed technical specification of every command, see the COMMAND_SPEC.md.


💡 Need Help? Use the Interactive Command Guide

CCW includes a built-in command-guide skill to help you discover and use commands effectively:

  • CCW-help - Get interactive help and command recommendations
  • CCW-issue - Report bugs or request features with guided templates

The command guide provides:

  • 🔍 Smart Command Search - Find commands by keyword, category, or use-case
  • 🤖 Next-Step Recommendations - Get suggestions for what to do after any command
  • 📖 Detailed Documentation - View parameters, examples, and best practices
  • 🎓 Beginner Onboarding - Learn the top 14 essential commands with a guided learning path
  • 📝 Issue Reporting - Generate standardized bug reports and feature requests

Example Usage:

User: "CCW-help"
→ Interactive menu with command search, recommendations, and documentation

User: "What's next after /workflow:plan?"
→ Recommends /workflow:execute, /workflow:action-plan-verify, with workflow patterns

User: "CCW-issue"
→ Guided template generation for bugs, features, or questions

🚀 Getting Started

The best way to get started is to follow the 5-minute tutorial in the Getting Started Guide.

Here is a quick example of a common development workflow:

Lightweight interactive workflow with in-memory planning and immediate execution:

# Basic usage with auto-detection
/workflow:lite-plan "Add JWT authentication to user login"

# Force code exploration
/workflow:lite-plan -e "Refactor logging module for better performance"

# Preset CLI tool
/workflow:lite-plan --tool codex "Add unit tests for auth service"

Interactive Flow:

  1. Phase 1: Automatic task analysis and smart code exploration (if needed)
  2. Phase 2: Answer clarification questions (if any)
  3. Phase 3: Review generated plan with task breakdown
  4. Phase 4: Three-dimensional confirmation:
    • Confirm/Modify/Cancel task
    • 🔧 Choose execution: Agent / Provide Plan / CLI (Gemini/Qwen/Codex)
    • 🔍 Optional code review: No / Claude / Gemini / Qwen / Codex
  5. Phase 5: Watch real-time execution with live task tracking

Option 2: Full Workflow (Comprehensive Planning)

Traditional multi-phase workflow for complex projects:

  1. Create a Plan (automatically starts a session):
    /workflow:plan "Implement JWT-based user login and registration"
    
  2. Execute the Plan:
    /workflow:execute
    
  3. Check Status (optional):
    /workflow:status
    

🤝 Contributing & Support

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.

Description
JSON-driven multi-agent development framework with intelligent CLI orchestration (Gemini/Qwen/Codex), context-first architecture, and automated workflow execution
Readme MIT 33 MiB
Languages
TypeScript 38.2%
Python 24.2%
HTML 16.3%
JavaScript 15.2%
CSS 4.5%
Other 1.6%