~ / rigs / tugayerdogan-mkz / claude-agent-kit

tugayerdogan-mkz/claude-agent-kit

Portable Claude Code agent workflow: /feature pipeline (build→test→security→performance→ship), 5 specialist sub-agents, doc-sync Stop hook, CI + health-check + scheduled-job templates

↗ GitHub ★ 0 no license updated 2mo ago project Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~179 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit tugayerdogan-mkz/claude-agent-kit/agents ./rig-claude-agent-kit/agents
$ npx degit tugayerdogan-mkz/claude-agent-kit/commands ./rig-claude-agent-kit/commands
$ npx degit tugayerdogan-mkz/claude-agent-kit/hooks ./rig-claude-agent-kit/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.

$ curl -fsSL --create-dirs -o .claude/agents/backend-developer.md https://raw.githubusercontent.com/tugayerdogan-mkz/claude-agent-kit/master/agents/backend-developer.md
$ curl -fsSL --create-dirs -o .claude/agents/frontend-developer.md https://raw.githubusercontent.com/tugayerdogan-mkz/claude-agent-kit/master/agents/frontend-developer.md
$ curl -fsSL --create-dirs -o .claude/agents/performance-engineer.md https://raw.githubusercontent.com/tugayerdogan-mkz/claude-agent-kit/master/agents/performance-engineer.md
$ curl -fsSL --create-dirs -o .claude/agents/security-auditor.md https://raw.githubusercontent.com/tugayerdogan-mkz/claude-agent-kit/master/agents/security-auditor.md
$ curl -fsSL --create-dirs -o .claude/agents/test-automator.md https://raw.githubusercontent.com/tugayerdogan-mkz/claude-agent-kit/master/agents/test-automator.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(~/.aws/**)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(.env)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/.env.*)",
      "Read(**/*.key)",
      "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(npm publish:*)",
      "Bash(wget *)",
      "Bash(git rebase *)",
      "Bash(gh pr merge *)",
      "Bash(git commit *)"
    ]
  }
}

Subagents (5)

Backend Developer
model: sonnet
Server-side development — data models, business logic, APIs, background jobs, migrations, integrations
Frontend Developer
model: sonnet
UI development — components, pages, state, data fetching, styling, i18n, accessibility
Performance Engineer
model: opus
Analyze & optimize performance — DB queries, API latency, bundle size, caching, realtime, resource use
Security Auditor
model: opus
Security audit — authN/authZ, injection, secret exposure, CORS, cookies, transport, dependency risk
Test Automator
model: sonnet
Write and run tests — unit, integration, API, and end-to-end; make them hermetic and CI-ready

Hooks (1)

eventmatcherruns
Stop*$CLAUDE_PROJECT_DIR/.claude/hooks/doc-reminder.sh

Slash commands (2)

/feature/sync-docs

Similar rigs

copied ✓