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
-eflag 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
-mparameter 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!
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-*.jsonfiles 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.
For detailed installation instructions, please refer to the INSTALL.md guide.
Windows (PowerShell):
Invoke-Expression (Invoke-WebRequest -Uri "https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.ps1" -UseBasicParsing).ContentLinux/macOS (Bash/Zsh):
bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.sh)After installation, open Claude Code and check if the workflow commands are available by running:
/workflow:session:listIf the slash commands (e.g., /workflow:*) are recognized, the installation was successful.
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.
CCW includes a built-in command-guide skill to help you discover and use commands effectively:
CCW-help- Get interactive help and command recommendationsCCW-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
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:
- Phase 1: Automatic task analysis and smart code exploration (if needed)
- Phase 2: Answer clarification questions (if any)
- Phase 3: Review generated plan with task breakdown
- 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
- Phase 5: Watch real-time execution with live task tracking
Traditional multi-phase workflow for complex projects:
- Create a Plan (automatically starts a session):
/workflow:plan "Implement JWT-based user login and registration" - Execute the Plan:
/workflow:execute
- Check Status (optional):
/workflow:status
- Repository: GitHub - Claude-Code-Workflow
- Issues: Report bugs or request features on GitHub Issues.
- Discussions: Join the Community Forum.
This project is licensed under the MIT License. See the LICENSE file for details.
