taoq-ai/wuwei
无为 WUWEI: a Claude Code plugin that runs a chartered agent team through your day, with guards that make the safe path the default one.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit taoq-ai/wuwei/agents ./rig-wuwei/agents $ npx degit taoq-ai/wuwei/skills ./rig-wuwei/skills $ npx degit taoq-ai/wuwei/hooks ./rig-wuwei/hooks
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit taoq-ai/wuwei/.agents/skills/speckit-analyze .claude/skills/speckit-analyze $ npx degit taoq-ai/wuwei/.agents/skills/speckit-checklist .claude/skills/speckit-checklist $ npx degit taoq-ai/wuwei/.agents/skills/speckit-clarify .claude/skills/speckit-clarify $ npx degit taoq-ai/wuwei/.agents/skills/speckit-constitution .claude/skills/speckit-constitution $ npx degit taoq-ai/wuwei/.agents/skills/speckit-converge .claude/skills/speckit-converge $ npx degit taoq-ai/wuwei/.agents/skills/speckit-implement .claude/skills/speckit-implement $ npx degit taoq-ai/wuwei/.agents/skills/speckit-plan .claude/skills/speckit-plan $ npx degit taoq-ai/wuwei/.agents/skills/speckit-specify .claude/skills/speckit-specify $ npx degit taoq-ai/wuwei/.agents/skills/speckit-tasks .claude/skills/speckit-tasks $ npx degit taoq-ai/wuwei/.agents/skills/speckit-taskstoissues .claude/skills/speckit-taskstoissues $ npx degit taoq-ai/wuwei/skills/wuwei-consolidate .claude/skills/wuwei-consolidate $ npx degit taoq-ai/wuwei/skills/wuwei-plan .claude/skills/wuwei-plan $ npx degit taoq-ai/wuwei/skills/wuwei-report .claude/skills/wuwei-report $ npx degit taoq-ai/wuwei/skills/wuwei-retro .claude/skills/wuwei-retro
$ curl -fsSL --create-dirs -o .claude/agents/builder.md https://raw.githubusercontent.com/taoq-ai/wuwei/main/agents/builder.md $ curl -fsSL --create-dirs -o .claude/agents/lead.md https://raw.githubusercontent.com/taoq-ai/wuwei/main/agents/lead.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/taoq-ai/wuwei/main/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/sentinel-arch.md https://raw.githubusercontent.com/taoq-ai/wuwei/main/agents/sentinel-arch.md $ curl -fsSL --create-dirs -o .claude/agents/sentinel-goal.md https://raw.githubusercontent.com/taoq-ai/wuwei/main/agents/sentinel-goal.md $ curl -fsSL --create-dirs -o .claude/agents/sentinel-quality.md https://raw.githubusercontent.com/taoq-ai/wuwei/main/agents/sentinel-quality.md $ curl -fsSL --create-dirs -o .claude/agents/sentinel-security.md https://raw.githubusercontent.com/taoq-ai/wuwei/main/agents/sentinel-security.md $ curl -fsSL --create-dirs -o .claude/agents/shepherd.md https://raw.githubusercontent.com/taoq-ai/wuwei/main/agents/shepherd.md $ curl -fsSL --create-dirs -o .claude/agents/steward.md https://raw.githubusercontent.com/taoq-ai/wuwei/main/agents/steward.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (14)
speckit-analyzespeckit-checklistspeckit-clarifyspeckit-constitutionspeckit-convergespeckit-implementspeckit-planspeckit-specifyspeckit-tasksspeckit-taskstoissueswuwei-consolidatewuwei-planwuwei-reportwuwei-retro
Subagents (9)
| builder | Follow the builder charter for assigned WUWEI work. |
| lead | Follow the lead charter for assigned WUWEI work. |
| planner | Follow the planner charter for assigned WUWEI work. |
| sentinel-arch | Follow the sentinel arch charter for assigned WUWEI work. |
| sentinel-goal | Follow the sentinel goal charter for assigned WUWEI work. |
| sentinel-quality | Follow the sentinel quality charter for assigned WUWEI work. |
| sentinel-security | Follow the sentinel security charter for assigned WUWEI work. |
| shepherd | Follow the shepherd charter for assigned WUWEI work. |
| steward | Follow the steward charter for assigned WUWEI work. |
Similar rigs
darshan-panchal1/wtenv
Give each git worktree its own ports, env file, database, and docker-compose project. Built for running parallel coding agents.
Skill Collector 813 tok ·
nowo-tech/ClaudePhpSetup
Interactive CLI that generates customized Claude Code markdown files (CLAUDE.md, commands, agents) for PHP projects. Abandoned — no longer maintained.
Skill Collector 3.2k tok ·
tlgimenes/doce
doce — a fully local, zero-config AI coding agent for macOS. No account, no API key, no cloud.
Skill Collector 449 tok ·
moinsen-dev/speckit-xref
Keep the code on the spec: a Claude Code mod and a GitHub Spec Kit extension for requirement-to-code traceability and drift checks
Skill Collector 482 tok ·