~ / rigs / w2ur / claude-code-setup

w2ur/claude-code-setup

Claude Code hooks, agents and commands for running 10+ personal apps without babysitting every diff — MIT, 2 blocking hooks included.

↗ GitHub ★ 2 MIT updated 6d ago personal setup Claude Code Claude plugin
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~5.9k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit w2ur/claude-code-setup/.claude ./rig-claude-code-setup  # 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 w2ur/claude-code-setup/skills/ci-and-branch-protection .claude/skills/ci-and-branch-protection
$ npx degit w2ur/claude-code-setup/skills/claude-md-hygiene .claude/skills/claude-md-hygiene
$ npx degit w2ur/claude-code-setup/skills/design-tells .claude/skills/design-tells
$ npx degit w2ur/claude-code-setup/skills/memory-and-plans .claude/skills/memory-and-plans
$ npx degit w2ur/claude-code-setup/skills/portfolio-conventions .claude/skills/portfolio-conventions
$ npx degit w2ur/claude-code-setup/skills/python-uv .claude/skills/python-uv
$ npx degit w2ur/claude-code-setup/skills/scheduled-jobs .claude/skills/scheduled-jobs
$ npx degit w2ur/claude-code-setup/skills/testing-conventions .claude/skills/testing-conventions
$ curl -fsSL --create-dirs -o .claude/agents/docs-checker.md https://raw.githubusercontent.com/w2ur/claude-code-setup/main/agents/docs-checker.md
$ curl -fsSL --create-dirs -o .claude/agents/dummy-visitor.md https://raw.githubusercontent.com/w2ur/claude-code-setup/main/agents/dummy-visitor.md
$ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/w2ur/claude-code-setup/main/agents/implementer.md
$ curl -fsSL --create-dirs -o .claude/agents/portfolio-audit.md https://raw.githubusercontent.com/w2ur/claude-code-setup/main/agents/portfolio-audit.md
$ curl -fsSL --create-dirs -o .claude/agents/troubleshooter.md https://raw.githubusercontent.com/w2ur/claude-code-setup/main/agents/troubleshooter.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 (8)

Subagents (5)

docs-checker
model: sonnet
|
dummy-visitor
model: sonnet
|
implementer
model: sonnet
Executes well-scoped implementation tasks with clear specifications. Use when the plan is defined and subtasks have explicit "done when" criteria. Not for architecture decisions or ambiguous tasks.
portfolio-audit
model: haiku
Audits a project against the global portfolio standards (author signature, gitignore, no secrets, no dead code, test file placement). Use before releases or during compliance sweeps.
troubleshooter
model: inherit
|

Slash commands (7)

/audit/cleanup/model-review/new-app/ship-plan/sync-setup/tech-debt

Similar rigs

copied ✓