KbWen/agentic-os
Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and
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 KbWen/agentic-os/.claude ./rig-agentic-os # 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 KbWen/agentic-os/.agents/skills/api-design .claude/skills/api-design $ npx degit KbWen/agentic-os/.agents/skills/auth-security .claude/skills/auth-security $ npx degit KbWen/agentic-os/.agents/skills/database-design .claude/skills/database-design $ npx degit KbWen/agentic-os/.agents/skills/dispatching-parallel-agents .claude/skills/dispatching-parallel-agents $ npx degit KbWen/agentic-os/.agents/skills/doc-lookup .claude/skills/doc-lookup $ npx degit KbWen/agentic-os/.agents/skills/frontend-patterns .claude/skills/frontend-patterns $ npx degit KbWen/agentic-os/.agents/skills/karpathy-principles .claude/skills/karpathy-principles $ npx degit KbWen/agentic-os/.agents/skills/production-readiness .claude/skills/production-readiness $ npx degit KbWen/agentic-os/.agents/skills/red-team-adversarial .claude/skills/red-team-adversarial $ npx degit KbWen/agentic-os/.agents/skills/subagent-driven-development .claude/skills/subagent-driven-development $ npx degit KbWen/agentic-os/.agents/skills/systematic-debugging .claude/skills/systematic-debugging $ npx degit KbWen/agentic-os/.agents/skills/test-driven-development .claude/skills/test-driven-development $ npx degit KbWen/agentic-os/.agents/skills/using-git-worktrees .claude/skills/using-git-worktrees $ npx degit KbWen/agentic-os/.agents/skills/verification-before-completion .claude/skills/verification-before-completion
$ curl -fsSL --create-dirs -o .claude/agents/acx-handoff.md https://raw.githubusercontent.com/KbWen/agentic-os/main/.claude/agents/acx-handoff.md $ curl -fsSL --create-dirs -o .claude/agents/acx-implementer.md https://raw.githubusercontent.com/KbWen/agentic-os/main/.claude/agents/acx-implementer.md $ curl -fsSL --create-dirs -o .claude/agents/acx-reviewer.md https://raw.githubusercontent.com/KbWen/agentic-os/main/.claude/agents/acx-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/acx-shipper.md https://raw.githubusercontent.com/KbWen/agentic-os/main/.claude/agents/acx-shipper.md $ curl -fsSL --create-dirs -o .claude/agents/acx-tester.md https://raw.githubusercontent.com/KbWen/agentic-os/main/.claude/agents/acx-tester.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 (14)
api-designauth-securitydatabase-designdispatching-parallel-agentsdoc-lookupfrontend-patternskarpathy-principlesproduction-readinessred-team-adversarialsubagent-driven-developmentsystematic-debuggingtest-driven-developmentusing-git-worktreesverification-before-completion
Subagents (5)
| acx-handoff model: sonnet | AgentCortex /handoff phase executor. Use when delegating handoff work that must produce a resumable state summary with full Work Log archival per agentic-os governance. |
| acx-implementer model: sonnet | AgentCortex /implement phase executor. Use when delegating implementation work that must follow agentic-os gates, evidence requirements, and skill injection. |
| acx-reviewer model: opus | AgentCortex /review phase executor. Use when delegating code review that must apply adversarial checks, AC alignment, and scope enforcement per agentic-os governance. |
| acx-shipper model: sonnet | AgentCortex /ship phase executor. Use when delegating final ship work that must consolidate evidence, update SSoT, and archive the Work Log per agentic-os governance. |
| acx-tester model: sonnet | AgentCortex /test phase executor. Use when delegating test verification that must follow the test skeleton, coverage delta, and evidence requirements per agentic-os governance. |
Slash commands (30)
/adr/app-init/ask-local/ask-openrouter/audit/bootstrap/brainstorm/claude-cli/codex-cli/decide/execute-plan/govern-audit/govern-docs/handoff/help/hotfix/implement/plan/research/retro/review/ship/spec-intake/spec/sync-docs/test-classify/test-skeleton/test/worktree-first/write-plan
Similar rigs
RichardBray/dotfiles
My personal configuration files and settings
Skill Collector 671 tok ·
emanuelnicenboim/dotfiles
Personal dotfiles - Claude Code skills & config
Skill Collector 671 tok ·
obra/superpowers
An agentic skills framework & software development methodology that works.
Skill Collector 3.0k tok ·
sodiumjoe/dotfiles
dotfiles
Skill Collector 1.1k tok ·