Claude-Code-Workflow

作者 catlog22

JSON-driven multi-agent cadence-team development framework with intelligent CLI orchestration (Gemini/Qwen/Codex), context-first architecture, and automated workflow execution

2,138
Stars
164
Forks
TypeScript
语言
2026/8/23
添加时间

⚠️ 第三方软件声明

本 Skill 为第三方开源软件,独立托管于 GitHub。SkillTip 仅为信息目录,不控制或维护底层仓库。所显示的安全检查为自动化且范围有限,安装前请自行审查源码。

阅读服务条款

安装

添加到你的 Claude Code skills 目录:

# Add to your Claude Code skills
git clone https://github.com/catlog22/Claude-Code-Workflow

快速入门

使用 Claude-Code-Workflow 等 Skills 的指南。

安全报告

已验证

上次扫描:—

{
  "status": "PASSED",
  "issues": []
}

README.md

[!IMPORTANT]

This project has evolved into Maestro Flow

Claude Code Workflow is now archived. All active development continues at:

https://github.com/catlog22/maestro-flow

npm install -g maestro-flow

Maestro Flow includes everything from CCW plus: Knowledge Graph, adaptive lifecycle engine (Ralph), hook system, team collaboration, and more.



Quick Start Guide CLI Tools Architecture


✨ Key Features

🎯 Skill-based Workflows

From lite-plan (lightweight) to brainstorm (multi-role analysis)

🔄 Multi-CLI Orchestration

Gemini, Qwen, Codex, Claude - auto-select or manual

⚡ Team Architecture v2

Role-based agents with inner loop execution

🔧 Queue Scheduler

Background queue execution service

📦 Session Lifecycle

start/resume/complete/sync workflow sessions

🖥️ Terminal Dashboard

Multi-terminal grid with execution monitor

🎨 Orchestrator Editor

Template-based workflow visual editing

💬 A2UI

Agent-to-User interactive interface

📖 New? See Workflow Guide for complete workflow documentation.


🚀 Quick Start

Install CCW

npm install -g claude-code-workflow
ccw install -m Global

Codex Configuration (Required for .codex/skills/)

If you use Codex CLI with the .codex/skills/ workflow skills, add these required features to your ~/.codex/config.toml:

[features]
default_mode_request_user_input = true   # Enable request_user_input tool for interactive confirmations
multi_agent = true                       # Enable multi-agent coordination (spawn_agent, wait, etc.)
multi_agent_v2 = true                    # Enable v4 agent API (fork_context, task_name, send_message, assign_task, list_agents)
enable_fanout = true                     # Enable spawn_agents_on_csv for parallel wave execution

These features are required for workflow skills to function properly. Without them, interactive confirmation gates (request_user_input), subagent orchestration, and CSV-driven parallel execution will not work.

Workflow Skills vs Commands

CCW uses two types of invocations:

TypeFormatExamples
SkillsTrigger phrase (no slash)workflow-lite-plan, brainstorm, workflow-plan
CommandsSlash command/ccw, /workflow/session:start, /issue/new

Choose Your Workflow Skill

Skill TriggerUse Case
workflow-lite-planLightweight planning, single-module features (hands off to lite-execute)
workflow-multi-cli-planMulti-CLI collaborative analysis
workflow-planFull planning with session persistence
workflow-tdd-planTest-driven development
workflow-test-fixTest generation and fix cycles
brainstormMulti-role brainstorming analysis

Workflow Examples

# Skill triggers (no slash - just describe what you want)
workflow-lite-plan "Add JWT authentication"
workflow-plan "Implement payment gateway integration"
workflow-execute

# Brainstorming
brainstorm "Design real-time collaboration system"

# Slash commands for session management
/workflow/session:start
/workflow/session:resume
/workflow/session:complete

🛠️ CLI Tool Installation

CLIDescriptionOfficial Docs
GeminiGoogle AI analysisgoogle-gemini/gemini-cli
CodexOpenAI autonomous codingopenai/codex
OpenCodeOpen-source multi-modelopencode-ai/opencode
QwenAlibaba Qwen-CodeQwenLM/Qwen

🎭 Semantic CLI Invocation


Users can semantically specify CLI tools in prompts - the system automatically invokes the corresponding CLI.

Basic Invocation

User PromptSystem Action
"Use Gemini to analyze the auth module"Auto-invoke gemini CLI for analysis
"Let Codex review this code"Auto-invoke codex CLI for review
"Ask Qwen about performance optimization"Auto-invoke qwen CLI for consultation

Multi-CLI Orchestration

PatternUser Prompt Example
Collaborative"Use Gemini and Codex to collaboratively analyze security vulnerabilities"
Parallel"Have Gemini, Codex, and Qwen analyze the architecture in parallel"
Iterative"Use Gemini to diagnose, then Codex to fix, iterate until resolved"
Pipeline"Gemini designs the solution, Codex implements, Claude reviews"

🔍 ACE Tool Configuration

ACE (Augment Context Engine) provides powerful semantic code search.


📚 CodexLens Local Search

⚠️ In Development: CodexLens is under iterative optimization. Some features may be unstable.

Search ModeDescription
FTSFull-text search, based on SQLite FTS5
SemanticSemantic search, using local embedding models
HybridHybrid search, combining FTS + Semantic + Reranking

💻 CCW CLI Commands

🌟 Recommended Commands

CommandDescriptionWhen to Use
/ccwAuto workflow orchestrator - analyzes intent, selects workflow, executes✅ General tasks, auto workflow selection
/ccw-coordinatorSmart orchestrator - recommends command chains, allows manual adjustment🔧 Complex multi-step workflows

Quick Examples:

# /ccw - Auto workflow selection
/ccw "Add user authentication"
/ccw "Fix memory leak in WebSocket"
/ccw "Implement with TDD"

# /ccw-coordinator - Manual chain orchestration
/ccw-coordinator "Implement OAuth2 system"

Session Management Commands

/workflow:session:start     # Start new workflow session
/workflow:session:resume    # Resume paused session
/workflow:session:list      # List all sessions
/workflow:session:sync      # Sync session work
/workflow:session:complete  # Complete session

Issue Workflow Commands

/issue/new       # Create new issue
/issue/plan      # Plan issue resolution
/issue/queue     # Form execution queue
/issue/execute   # Execute issue queue

Other CLI Commands

ccw install           # Install workflow files
ccw view              # Open dashboard
ccw cli -p "..."      # Execute CLI tools (Gemini/Qwen/Codex)
ccw upgrade -a        # Upgrade all installations

🏗️ Architecture

┌─────────────────────────────────────────────────────────────────┐
│                     Workflow Skills                              │
│  📝 workflow-lite-plan / workflow-multi-cli-plan (lightweight)  │
│  📊 workflow-plan / workflow-tdd-plan (session-based)           │
│  🧪 workflow-test-fix / workflow-test-fix         │
│  🧠 brainstorm (multi-role analysis)                            │
└─────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────┐
│                   Team Architecture v2                          │
│  🤖 team-worker agents with role-spec based execution           │
│  🔄 Inner loop framework for sequential task processing         │
│  📢 Message bus protocol with team coordination                 │
│  🧠 Wisdom accumulation (learnings/decisions/conventions)       │
└─────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────┐
│                   Queue Scheduler Service                       │
│  ⚙️ Background execution service with API endpoints             │
│  📊 Queue management and unified CLI execution settings         │
└─────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────┐
│                   Terminal Dashboard & Orchestrator             │
│  🖥️ Multi-terminal grid with execution monitor                  │
│  🎨 Template-based workflow editor with slash commands          │
│  📡 Real-time agent communication via A2UI                      │
└─────────────────────────────────────────────────────────────────┘

📦 Project Structure

Claude-Code-Workflow/
├── .claude/
│   ├── agents/          # 22 specialized agents (team-worker, cli-discuss, etc.)
│   ├── commands/        # Slash commands (5 categories)
│   │   ├── ccw.md       # Main orchestrator
│   │   ├── ccw-coordinator.md
│   │   ├── cli/         # CLI commands (cli-init, codex-review)
│   │   ├── issue/       # Issue management (plan, execute, queue)
│   │   ├── memory/      # Memory commands (prepare, style-skill-memory)
│   │   └── workflow/    # Workflow commands (session, ui-design, etc.)
│   └── skills/          # 37 modular skills
│       ├── workflow-lite-plan/
│       ├── workflow-plan/
│       ├── workflow-tdd-plan/
│       ├── workflow-test-fix/
│       ├── brainstorm/
│       ├── team-*/      # Team coordination skills
│       └── ...
├── ccw/
│   ├── src/             # TypeScript source code
│   │   ├── commands/    # CLI command implementations
│   │   ├── core/        # Core services (a2ui, auth, hooks, routes)
│   │   ├── mcp-server/  # MCP server implementation
│   │   └── tools/       # Tool implementations
│   └── frontend/        # React frontend (Terminal Dashboard, Orchestrator)
├── codex-lens/          # Local semantic code search engine
└── docs/                # Documentation

🎼 Team Cadence Control (Beat Model)

The v2 team architecture introduces an event-driven beat model for efficient orchestration:

Beat Cycle (single beat)
======================================================================
  Event                   Coordinator              Workers
----------------------------------------------------------------------
  callback/resume --> +- handleCallback -+
                      |  mark completed   |
                      |  check pipeline   |
                      +- handleSpawnNext -+
                      |  find ready tasks |
                      |  spawn workers ---+--> [team-worker A] Phase 1-5
                      |  (parallel OK)  --+--> [team-worker B] Phase 1-5
                      +- STOP (idle) -----+         |
                                                     |
  callback <-----------------------------------------+
  (next beat)              SendMessage + TaskUpdate(completed)
======================================================================

Key Benefits:

  • 🎯 Event-driven: Coordinator only wakes when needed (callback/resume)
  • Fast-advance: Simple successors spawn directly without coordinator roundtrip
  • 🔄 Dynamic pipelines: Generated per-task from dependency graph
  • 📊 Parallel execution: Independent tasks run concurrently

🖥️ Frontend Highlights

Terminal Dashboard

Multi-terminal grid layout with real-time execution monitoring.

Features:

  • 🖥️ Multi-terminal grid with resizable panes
  • 📊 Execution monitor with agent list
  • 📁 File sidebar for project navigation
  • 🎯 Session grouping by project tags
  • 🌙 Fullscreen/immersive mode

Orchestrator Editor

Visual workflow template editor with drag-drop.

Features:

  • 🎨 React Flow-based visual editing
  • 📦 Template library with pre-built workflows
  • 🔧 Property panel for node configuration
  • ⚡ Slash command integration

🙏 Acknowledgments

  • Impeccable — Design audit methodology, OKLCH color system, anti-AI-slop detection patterns, editorial typography standards, motion/animation token architecture, and vanilla JS interaction patterns. The UI team skills (team-ui-polish, team-interactive-craft, team-motion-design, team-visual-a11y, team-uidesign, team-ux-improve) draw heavily from Impeccable's design knowledge.

  • gstack — Systematic debugging methodology, security audit frameworks, and release pipeline patterns. The skills investigate (Iron Law debugging), security-audit (OWASP Top 10 + STRIDE), and ship (gated release pipeline) are inspired by gstack's workflow designs.


🤝 Contributing

GitHub Issues

📄 License

MIT License - see LICENSE


💬 Community

Join the CCW WeChat group to discuss tips and share experiences with other developers!

CCW WeChat Group

Scan to join the WeChat group (if the QR code has expired, please open an Issue for the latest one)


☕ Buy Me a Coffee

Your support is the greatest motivation for updates!

WeChat Appreciation QR Code

"您的支持是更新的最大动力"


🔗 Links

LINUX DO

常见问题

What is Claude-Code-Workflow?

Claude-Code-Workflow is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by catlog22. JSON-driven multi-agent cadence-team development framework with intelligent CLI orchestration (Gemini/Qwen/Codex), context-first architecture, and automated workflow execution. It has 2,138 GitHub stars.

Is Claude-Code-Workflow safe to use?

Claude-Code-Workflow returned warnings in SkillsLLM's automated security scan. It has no critical vulnerabilities, but review the flagged issues in the Security Report section before adding it to your workflow.

How do I install Claude-Code-Workflow?

Clone the repository with "git clone https://github.com/catlog22/Claude-Code-Workflow" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is Claude-Code-Workflow written in?

Claude-Code-Workflow is primarily written in TypeScript. It is open-source under catlog22 on GitHub, so you can review or fork the full source.

Are there alternatives to Claude-Code-Workflow?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Claude-Code-Workflow against similar tools.

评论 (0)

暂无评论,成为第一个分享想法的人!

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,03119,897Shell
AI 智能体
查看详情

开发者还喜欢

基于喜欢此 Skill 的开发者投票和收藏

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情