leosimini/keelokit
Stop agents from calling buggy code "done": a Claude Code plugin where separate agents test, review and try to break every story, and each bug leaves a check. By Leopoldo Simini.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit leosimini/keelokit/.claude ./rig-keelokit # 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 leosimini/keelokit/skills/build-story .claude/skills/build-story $ npx degit leosimini/keelokit/skills/check-bugbash .claude/skills/check-bugbash $ npx degit leosimini/keelokit/skills/check-health .claude/skills/check-health $ npx degit leosimini/keelokit/skills/check-security .claude/skills/check-security $ npx degit leosimini/keelokit/skills/harness-upgrade .claude/skills/harness-upgrade $ npx degit leosimini/keelokit/skills/keelokit .claude/skills/keelokit $ npx degit leosimini/keelokit/skills/plan-backlog .claude/skills/plan-backlog $ npx degit leosimini/keelokit/skills/plan-intake .claude/skills/plan-intake $ npx degit leosimini/keelokit/skills/project-adopt .claude/skills/project-adopt $ npx degit leosimini/keelokit/skills/project-dashboard .claude/skills/project-dashboard $ npx degit leosimini/keelokit/skills/project-new .claude/skills/project-new $ npx degit leosimini/keelokit/skills/project-report .claude/skills/project-report $ npx degit leosimini/keelokit/skills/run-local .claude/skills/run-local $ npx degit leosimini/keelokit/skills/ship-release .claude/skills/ship-release $ npx degit leosimini/keelokit/skills/ship-setup .claude/skills/ship-setup
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 (15)
Similar rigs
shaeX1994/ai-project-template
Multi-agent AI config template — one .ai/ source tree syncs rules to Claude Code, Cursor, Copilot, Codex, Gemini, Windsurf, DeepSeek and Grok.
Pragmatist 3.3k tok ·
ecodelearn/template-claude-code-open
Multi-agent coding template — persistent memory, spec-driven workflow, skills and security hooks for Claude Code, Cursor, Windsurf, GitHub Copilot and any AGENTS.md-reading tool. No dependencies.
Pragmatist 1.4k tok ·
zionge2k/claude-dotfiles
Claude Code personal dotfiles (macOS + Arch Linux)
YOLO Cowboy 5.3k tok ·
obra/superpowers
An agentic skills framework & software development methodology that works.
Skill Collector 3.0k tok ·