catlog22 d82bf5a823 fix: Preserve user intent in test workflow session creation
- Add Step 1.0 to test-gen.md to load source session task_description
- Add Step 1.0 to test-fix-gen.md (Session Mode) to load original user intent
- Include originalTaskDescription in session creation to enable semantic CLI selection
- Fixes data flow gap identified by Gemini review: user's CLI tool preferences
  (e.g., "use Codex for fixes") now propagate through test workflow sessions

This ensures semantic CLI tool selection works correctly in derivative test sessions
by preserving the original user's task description from the source session.

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-29 17:06:13 +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 powerful, context-first orchestration system. It solves execution uncertainty and error accumulation through structured planning, deterministic execution, and intelligent multi-model orchestration.

🎉 Version 5.9.6: Review Cycle Enhancement & Dashboard Automation

Core Improvements:

  • Enhanced Review Dashboard: The review-cycle dashboard now supports real-time progress tracking and advanced filtering for better visibility into code reviews.
  • 🎯 New Fix-Tracking Dashboard: Introduced a new, independent fix-dashboard.html to monitor the progress of bug fixes with rich data integration.
  • 🚀 lite-fix Workflow: Added a new lite-fix command for intelligent, streamlined bug diagnosis and resolution.
  • 🛠️ lite-plan Optimization: Significantly optimized the lite-plan workflow with cost-aware parallel execution, better complexity analysis, and robust context protection.
  • 🧠 Intelligent Test Cycles: Improved the test-cycle-execute command with smart iteration strategies and a universal @test-fix-agent for more effective testing.

See CHANGELOG.md for complete 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 distinguish it from traditional AI development approaches:

  • Context-First Architecture: Eliminates uncertainty during execution through pre-defined context gathering, ensuring agents have the right information before implementation.
  • JSON-First State Management: Task state is fully stored in .task/IMPL-*.json files as the single source of truth, enabling programmatic orchestration without state drift.
  • Autonomous Multi-Stage Orchestration: Commands chain-invoke specialized sub-commands and agents to automate complex workflows with zero user intervention.
  • Multi-Model Strategy: Leverages the unique strengths of different AI models (e.g., Gemini for analysis, Codex for implementation) for superior results.
  • Layered Memory System: A 4-tier documentation system that provides context at the appropriate abstraction level, preventing information overload.
  • Specialized Role-Based Agents: A suite of agents (@code-developer, @test-fix-agent, etc.) that emulate a real software team for diverse tasks.

⚙️ Installation

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

🚀 One-Click Quick Install

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 verify that workflow commands are available by running:

/workflow:session:list

If 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 interactions with AI tools. For a complete list and detailed descriptions of all available commands, please refer to the COMMAND_REFERENCE.md file.

For detailed technical specifications of each command, see 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 using 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 arguments, examples, and best practices
  • 🎓 Beginner Onboarding - Learn the 14 core commands through guided learning paths
  • 📝 Issue Reporting - Generate standardized bug reports and feature requests

Usage Examples:

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

User: "What should I do after /workflow:plan?"
→ Recommends /workflow:execute, /workflow:action-plan-verify with workflow patterns

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

🚀 Quick Start

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

Here's 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"

# Basic usage
/workflow:lite-plan "Add unit tests for authentication 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 and task breakdown
  4. Phase 4: Three-dimensional confirmation:
    • Confirm/Modify/Cancel task
    • 🔧 Choose execution: Agent / Provide Plan Only / CLI (Gemini/Qwen/Codex)
    • 🔍 Optional code review: No / Claude / Gemini / Qwen / Codex
  5. Phase 5: Watch live execution and task tracking

Intelligent bug diagnosis and fix workflow with adaptive severity assessment:

# Standard bug fix (auto-adapts based on severity)
/workflow:lite-fix "User avatar upload fails with 413 error"

# Production hotfix mode
/workflow:lite-fix --hotfix "Payment gateway 5xx errors"

Workflow Features:

  • Phase 1: Intelligent root cause diagnosis with adaptive search
  • Phase 2: Automatic impact assessment and risk scoring
  • Phase 3: Fix strategy generation based on complexity
  • Phase 4: Risk-aware verification planning
  • Phase 5: User confirmation with execution selection
  • Phase 6: Execution dispatch with complete artifact tracking

Session Artifacts (saved to .workflow/.lite-fix/{bug-slug}-{timestamp}/):

  • diagnosis.json - Root cause analysis and reproduction steps
  • impact.json - Risk score, severity, and workflow adaptations
  • fix-plan.json - Fix strategy and implementation tasks
  • task.json - Enhanced Task JSON with complete context
  • followup.json - Auto-generated follow-up tasks (hotfix mode only)

Option 3: Full Workflow (📋 Comprehensive Planning)

Traditional multi-stage workflow for complex projects:

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

📚 Documentation

CCW provides comprehensive documentation to help you get started quickly and master advanced features:

📖 Getting Started

🏗️ Architecture & Design

📋 Command Reference

🤝 Contributing


🤝 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%