anujg21/claude-engineering-os
A repository template that gives Claude Code a working engineering method: phased workflow, path-scoped standards, independent review agents, and hooks that block dangerous commands.
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 anujg21/claude-engineering-os/agents ./rig-claude-engineering-os/agents $ npx degit anujg21/claude-engineering-os/skills ./rig-claude-engineering-os/skills $ npx degit anujg21/claude-engineering-os/hooks ./rig-claude-engineering-os/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 anujg21/claude-engineering-os/skills/adopt .claude/skills/adopt $ npx degit anujg21/claude-engineering-os/skills/adr .claude/skills/adr $ npx degit anujg21/claude-engineering-os/skills/architecture .claude/skills/architecture $ npx degit anujg21/claude-engineering-os/skills/design .claude/skills/design $ npx degit anujg21/claude-engineering-os/skills/discovery .claude/skills/discovery $ npx degit anujg21/claude-engineering-os/skills/guide .claude/skills/guide $ npx degit anujg21/claude-engineering-os/skills/implement .claude/skills/implement $ npx degit anujg21/claude-engineering-os/skills/operate .claude/skills/operate $ npx degit anujg21/claude-engineering-os/skills/performance-review .claude/skills/performance-review $ npx degit anujg21/claude-engineering-os/skills/plan .claude/skills/plan $ npx degit anujg21/claude-engineering-os/skills/production-readiness .claude/skills/production-readiness $ npx degit anujg21/claude-engineering-os/skills/project-state .claude/skills/project-state $ npx degit anujg21/claude-engineering-os/skills/release .claude/skills/release $ npx degit anujg21/claude-engineering-os/skills/review .claude/skills/review $ npx degit anujg21/claude-engineering-os/skills/security-review .claude/skills/security-review
$ curl -fsSL --create-dirs -o .claude/agents/architecture-reviewer.md https://raw.githubusercontent.com/anujg21/claude-engineering-os/main/agents/architecture-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/anujg21/claude-engineering-os/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/production-readiness-reviewer.md https://raw.githubusercontent.com/anujg21/claude-engineering-os/main/agents/production-readiness-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/anujg21/claude-engineering-os/main/agents/security-reviewer.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 (15)
adoptadrarchitecturedesigndiscoveryguideimplementoperateperformance-reviewplanproduction-readinessproject-statereleasereviewsecurity-review
Subagents (4)
| architecture-reviewer model: inherit | Independent review of a proposed architecture or technical design against the stated requirements. Challenges unjustified complexity, unclear boundaries, and undefined failure behavior. Use at the end |
| code-reviewer model: inherit | Reviews a diff for correctness, edge cases, contract compatibility, reliability, and test quality, in a context that never saw the code being written. Use after implementing a change and before mergin |
| production-readiness-reviewer model: inherit | Runs the GO / NO-GO readiness checklist against a change or a system and returns a verdict with evidence and named blockers. Use before a first release, before exposing something to real users or mone |
| security-reviewer model: inherit | Security review of a change or component against a control catalogue, producing blocking and non-blocking findings with concrete exploit conditions. Use before merging anything touching auth, secrets, |
Similar rigs
kapadias/nonna
Your AI agent says done. Nonna makes it prove it: she runs your test suite before a coding agent can stop, and blocks pushes to main and secrets in files. Claude Code plugin, plus git hooks for Codex, Cursor, Copilot, Gemini and more
Fort Knox 3.9k tok ·
rafagomes/ai-workflow
AI-assisted development workflow toolkit for Claude Code, Cursor, and Codex — skills, agents, and conventions for the full SDLC
Skill Collector 4.0k tok ·
r3dpepper/claude-dotfiles
Claude code workflow harness files. Goes to ~/.claude in user-scoped location.
Fort Knox 1.5k tok ·
steepy-it/steepy-apex
Context engineering and governed workflows for AI coding agents. Keep project knowledge coherent, route work to specialists, and scale from small fixes to bounded autonomous loops.
Orchestrator 851 tok ·