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 andrew-yangy/gru-ai/.claude ./rig-gru-ai # inspect, then merge into .claude/ 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 andrew-yangy/gru-ai/.claude/skills/brainstorm .claude/skills/brainstorm $ npx degit andrew-yangy/gru-ai/.claude/skills/code-review-excellence .claude/skills/code-review-excellence $ npx degit andrew-yangy/gru-ai/.claude/skills/directive .claude/skills/directive $ npx degit andrew-yangy/gru-ai/.claude/skills/frontend-design .claude/skills/frontend-design $ npx degit andrew-yangy/gru-ai/.claude/skills/gruai-agents .claude/skills/gruai-agents $ npx degit andrew-yangy/gru-ai/.claude/skills/gruai-config .claude/skills/gruai-config $ npx degit andrew-yangy/gru-ai/.claude/skills/healthcheck .claude/skills/healthcheck $ npx degit andrew-yangy/gru-ai/.claude/skills/report .claude/skills/report $ npx degit andrew-yangy/gru-ai/.claude/skills/scout .claude/skills/scout $ npx degit andrew-yangy/gru-ai/.claude/skills/seo-audit .claude/skills/seo-audit $ npx degit andrew-yangy/gru-ai/.claude/skills/smoke-test .claude/skills/smoke-test $ npx degit andrew-yangy/gru-ai/.claude/skills/walkthrough .claude/skills/walkthrough $ npx degit andrew-yangy/gru-ai/.claude/skills/webapp-testing .claude/skills/webapp-testing
$ curl -fsSL --create-dirs -o .claude/agents/casey-data.md https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/agents/casey-data.md $ curl -fsSL --create-dirs -o .claude/agents/devon-fullstack.md https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/agents/devon-fullstack.md $ curl -fsSL --create-dirs -o .claude/agents/jordan-backend.md https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/agents/jordan-backend.md $ curl -fsSL --create-dirs -o .claude/agents/marcus-cpo.md https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/agents/marcus-cpo.md $ curl -fsSL --create-dirs -o .claude/agents/morgan-coo.md https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/agents/morgan-coo.md $ curl -fsSL --create-dirs -o .claude/agents/priya-cmo.md https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/agents/priya-cmo.md $ curl -fsSL --create-dirs -o .claude/agents/quinn-design.md https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/agents/quinn-design.md $ curl -fsSL --create-dirs -o .claude/agents/riley-frontend.md https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/agents/riley-frontend.md $ curl -fsSL --create-dirs -o .claude/agents/sam-qa.md https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/agents/sam-qa.md $ curl -fsSL --create-dirs -o .claude/agents/sarah-cto.md https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/agents/sarah-cto.md $ curl -fsSL --create-dirs -o .claude/agents/taylor-content.md https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/agents/taylor-content.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 (13)
brainstormcode-review-excellencedirectivefrontend-designgruai-agentsgruai-confighealthcheckreportscoutseo-auditsmoke-testwalkthroughwebapp-testing
Subagents (11)
| casey model: inherit | | |
| devon model: inherit | | |
| jordan model: inherit | | |
| marcus model: inherit | | |
| morgan model: inherit | | |
| priya model: inherit | | |
| quinn model: inherit | | |
| riley model: inherit | | |
| sam model: inherit | | |
| sarah model: inherit | | |
| taylor model: inherit | | |
Similar rigs
Zigzag968/claude-code-lgtmgate
An LGTM you can trust: a complete pipeline running several issues at once, each in its own git worktree, through a scripted five-agent flow that self-recovers or escalates to you, on the way to a mergeable PR.
Orchestrator 1.9k tok ·
nateberkopec/dotfiles
yup we're doin the thing
YOLO Cowboy 958 tok ·
alexanderop/dotfiles
macOS dotfiles - zsh, git, VSCode, Ghostty, Homebrew
Skill Collector 1.1k tok ·
LeastBit/Claude_skills_zh-CN
Anthropics/skills中文学习版本 来自：https://github.com/anthropics/skills
Skill Collector 608 tok ·