fainir/agent-harness
Skills, rules and hooks that turn Claude Code, Codex or any AGENTS.md agent into a product team, CEO or portfolio manager: size the job, finish it, verify it, ask the owner one action at a time, improve itself.
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 fainir/agent-harness/skills ./rig-agent-harness/skills $ npx degit fainir/agent-harness/hooks ./rig-agent-harness/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 fainir/agent-harness/skills/hire .claude/skills/hire $ npx degit fainir/agent-harness/skills/learn .claude/skills/learn $ npx degit fainir/agent-harness/skills/owner-actions .claude/skills/owner-actions $ npx degit fainir/agent-harness/skills/portfolio .claude/skills/portfolio $ npx degit fainir/agent-harness/skills/product-spec .claude/skills/product-spec $ npx degit fainir/agent-harness/skills/production-ready .claude/skills/production-ready $ npx degit fainir/agent-harness/skills/qa-flows .claude/skills/qa-flows $ npx degit fainir/agent-harness/skills/release-gates .claude/skills/release-gates $ npx degit fainir/agent-harness/skills/run-company .claude/skills/run-company $ npx degit fainir/agent-harness/skills/ship .claude/skills/ship $ npx degit fainir/agent-harness/skills/ux-ui-review .claude/skills/ux-ui-review $ npx degit fainir/agent-harness/skills/workspace .claude/skills/workspace
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 (12)
Similar rigs
blauwtje/exo
Claude Code plugin with four stages and hooks that refuse risky commands.
Pragmatist 1.4k tok · · Q0
laaielichter/Threesmith
Checks the three.js code your coding agent writes: version-pinned review, headless page checks, safe fixes and 3D models from code. MCP server, CLI and Claude Code plugin.
Pragmatist 4.7k tok · · Q0
vishalguptax/agent-engineering-kit
Make AI coding agents ship clean code: rules, sub-agents, skills and hooks for Claude Code, Codex, Cursor, Copilot, Gemini CLI and 13 more, with a safe installer.
Orchestrator 2.3k tok · · Q20
markfulton/ai-employees
Open source AI Employees. 8 scheduled business roles, 60 routines, on Claude Code and 10 other harnesses. They drive your browser the way you do and improve every run. You own the files.
Pragmatist 3.7k tok · · Q3