English | 中文

Autonomous coding, evolved.

93 skills, 21 hooks, 35 agents, a safety guardian, and a correction learning loop — all working together so Claude codes better, catches its own mistakes, and can run unattended overnight while you sleep.

If this saves you time, a star helps others find it. Something broken? Open an issue.

Blog post: Building Clade — motivation, design decisions, and lessons learned.

1. Install
2. MCP Server
3. What It Does
4. Skills
5. Hooks
6. Supported Languages
7. Documentation
8. Repo Structure
9. Contributing
10. License

git clone https://github.com/shenxingy/clade.git
cd clade && ./install.sh

Installs skills, hooks, agents, scripts, and safety guardian. Start a new Claude Code session to activate.

Requires: jq. Platform: Linux and macOS.

If you just want the skills in Cursor, Windsurf, Claude Desktop, or any MCP client:

pip install clade-mcp

See MCP Server below for configuration.

The MCP server exposes all 94 Clade skills as callable tools via the Model Context Protocol. Works with any MCP-compatible client.

Claude Desktop / Claude Code:

{
  "mcpServers": {
    "clade": { "command": "uvx", "args": ["clade-mcp"] }
  }
}

Cursor / Windsurf:

{
  "mcpServers": {
    "clade": { "command": "clade-mcp" }
  }
}

Prerequisite: Claude Code CLI must be installed — skills execute via claude -p.

See How It Works for the full hook reference (21 hooks).

See When to Use What for detailed usage guidance.

Auto-detected — hooks and agents adapt to your project:

All checks are opt-in by detection — if the tool isn't installed, the hook silently skips.

Keep ~/.claude/ in sync across machines — memory, corrections, skills, hooks, and scripts.

~/.claude/scripts/sync-setup.sh            # auto-detect NFS or GitHub
~/.claude/scripts/sync-setup.sh --github   # explicit GitHub backend

Fully automatic once configured. See Configuration for details.

clade/
├── install.sh               # One-command deployment
├── uninstall.sh             # Clean removal
├── mcp-package/             # PyPI package (clade-mcp)
├── orchestrator/            # FastAPI web UI + worker pool + task queue
│   ├── server.py            # App, routes, WebSocket
│   ├── worker.py            # WorkerPool, SwarmManager
│   ├── task_queue.py        # SQLite-backed task CRUD
│   ├── mcp_server.py        # MCP server (local dev version)
│   └── web/                 # Single-page dashboard
├── configs/
│   ├── skills/              # 93 skill definitions (SKILL.md + prompt.md)
│   ├── hooks/               # 21 event hooks + lib/
│   ├── agents/              # 35 agent definitions
│   └── scripts/             # 27 shell + Python utilities
├── adapters/openclaw/       # OpenClaw integration (mobile monitoring)
├── templates/               # Settings, CLAUDE.md, corrections templates
└── docs/                    # Guides and research

Monitor and control overnight loops from your phone via OpenClaw.

See adapters/openclaw/README.md for setup.

Contributions welcome — code, docs, issue triage, bug reports. See CONTRIBUTING.md.

1. Loop on non-code tasks (research/docs) fails silently — workers produce no diff, loop reports failure
2. Workers inherit parent env — project-specific env vars leak into worker shells; sanitize before overnight runs
3. Context budget is per-session — multi-day runs may exhaust context; use /handoff + /pickup

MIT