peterquiel/claude-ape-setup
A structured workflow framework for Claude Code. Separates planning from execution, uses markdown files as communication artifacts, and puts human review at the center of every decision.
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 peterquiel/claude-ape-setup/.claude ./rig-claude-ape-setup # 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 peterquiel/claude-ape-setup/.claude/skills/database-schema .claude/skills/database-schema $ npx degit peterquiel/claude-ape-setup/.claude/skills/domain-model .claude/skills/domain-model $ npx degit peterquiel/claude-ape-setup/.claude/skills/testing .claude/skills/testing
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/peterquiel/claude-ape-setup/main/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/code-scout.md https://raw.githubusercontent.com/peterquiel/claude-ape-setup/main/.claude/agents/code-scout.md $ curl -fsSL --create-dirs -o .claude/agents/implementation-expert.md https://raw.githubusercontent.com/peterquiel/claude-ape-setup/main/.claude/agents/implementation-expert.md $ curl -fsSL --create-dirs -o .claude/agents/openapi-implementation-planner.md https://raw.githubusercontent.com/peterquiel/claude-ape-setup/main/.claude/agents/openapi-implementation-planner.md $ curl -fsSL --create-dirs -o .claude/agents/post-implementation-reviewer.md https://raw.githubusercontent.com/peterquiel/claude-ape-setup/main/.claude/agents/post-implementation-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/qs-engineer.md https://raw.githubusercontent.com/peterquiel/claude-ape-setup/main/.claude/agents/qs-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/software-architect.md https://raw.githubusercontent.com/peterquiel/claude-ape-setup/main/.claude/agents/software-architect.md $ curl -fsSL --create-dirs -o .claude/agents/technical-documentation-agent.md https://raw.githubusercontent.com/peterquiel/claude-ape-setup/main/.claude/agents/technical-documentation-agent.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 (3)
Subagents (8)
| code-reviewer model: opus | | |
| code-scout model: opus | | |
| implementation-expert model: opus | | |
| openapi-implementation-planner model: opus | | |
| post-implementation-reviewer model: opus | | |
| qs-engineer model: opus | | |
| software-architect model: opus | | |
| technical-documentation-agent model: opus | | |
Slash commands (8)
/analyze/execute/improve-doc/init-ape/log/optimize-agent-or-skill/plan/review-changes
Similar rigs
javivelasco/dotfiles
🏡
Minimalist 804 tok ·
AizenvoltPrime/claude-setup
—
Pragmatist 1.2k tok ·
IvanKuzyshyn/dotfiles
Dotfiles optimized for speed, coffee, and questionable life choices. 😜
Pragmatist 3.0k tok ·
HGInsights/claude-code-setup
Production-tested Claude Code harness configuration: hooks, skills, subagents, and automated review loops
Pragmatist 1.9k tok ·