mhlaghari/stuntman
Claude doesn't do its own stunts. Plan with Claude, execute with a near-free model, review with Claude — a delegation harness for Claude Code.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ npx degit mhlaghari/stuntman/skills ./rig-stuntman/skills $ npx degit mhlaghari/stuntman/hooks ./rig-stuntman/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 mhlaghari/stuntman/skills/delegate .claude/skills/delegate $ npx degit mhlaghari/stuntman/skills/dispatch .claude/skills/dispatch $ npx degit mhlaghari/stuntman/skills/floor .claude/skills/floor $ npx degit mhlaghari/stuntman/skills/handoff .claude/skills/handoff $ npx degit mhlaghari/stuntman/skills/launch .claude/skills/launch $ npx degit mhlaghari/stuntman/skills/relay .claude/skills/relay $ npx degit mhlaghari/stuntman/skills/scaffold .claude/skills/scaffold $ npx degit mhlaghari/stuntman/skills/usages .claude/skills/usages $ npx degit mhlaghari/stuntman/skills/wiki .claude/skills/wiki
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (9)
Similar rigs
epilande/ccmux
🔮 Run all your AI coding agents in tmux: jump to the one that needs you, spawn them into worktrees, and hand work between them
Pragmatist 6.3k tok · · Q20
jaharris87/agentic-dev-framework
Multi-agent adversarial dev workflow templates: Claude Code (builder) + Codex (reviewers) + GitHub Actions (orchestrator)
Pragmatist 5.0k tok · · Q15
raj-rangani/kiasi
Make your Claude Code weekly limit last longer. Fixed local rules keep noisy tool output out of every step; your own dashboard shows the days it bought back. No model calls, no network.
Pragmatist 158 tok · · Q0
bassimeledath/dispatch
A Claude Code skill that 10x's your effective context window by dispatching tasks to background AI workers.
Minimalist 720 tok · · Q0