agentrigs
+ submit rig
~ / rigs / RonaldPrecieux / claude-code-playbook

RonaldPrecieux/claude-code-playbook

Le guide opérationnel pour transformer Claude Code en workflow de développement autonome — CLAUDE.md template, sous-agents, workflow autonome

↗ GitHub ★ 0 no license updated 7mo ago project Claude Code
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~771 tokens
Featherweight · 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 RonaldPrecieux/claude-code-playbook/.claude ./rig-claude-code-playbook  # 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.

$ curl -fsSL --create-dirs -o .claude/agents/bug-fixer.md https://raw.githubusercontent.com/RonaldPrecieux/claude-code-playbook/main/.claude/agents/bug-fixer.md
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/RonaldPrecieux/claude-code-playbook/main/.claude/agents/code-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/explorer.md https://raw.githubusercontent.com/RonaldPrecieux/claude-code-playbook/main/.claude/agents/explorer.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 *)"
    ]
  }
}

Subagents (3)

bug-fixer
model: sonnet
Fixe un bug de manière autonome à partir d'un rapport d'erreur, logs, ou test qui échoue. Utiliser quand on a un bug à résoudre. Ne demande pas de guidance — analyse et résout.
code-reviewer
model: opus
Review le code modifié pour la qualité, la sécurité, et les edge cases. Utiliser après chaque changement significatif ou avant un commit. Invoque ce sous-agent de manière proactive après avoir écrit d
explorer
model: haiku
Explore le codebase pour répondre à des questions sans modifier quoi que ce soit. Utiliser pour comprendre l'architecture, trouver des patterns, localiser du code. Préserve le contexte principal.

Similar rigs

AizenvoltPrime/claude-setup
—
★ 269 setup Claude Code 1 mcp 1 agents 1 hooks 9mo ago
Pragmatist 1.2k tok ·
bi-boo/claude-code-config
我的 Claude Code 个人配置——CLAUDE.md 规则、Agent、记忆机制，以及 Ghostty 终端配置
★ 19 setup Claude Code 2 agents 2 hooks 5mo ago
YOLO Cowboy 1.4k tok ·
IvanKuzyshyn/dotfiles
Dotfiles optimized for speed, coffee, and questionable life choices. 😜
★ 5 setup Claude CodeCodex 2 agents 26d ago
Pragmatist 3.0k tok ·
HGInsights/claude-code-setup
Production-tested Claude Code harness configuration: hooks, skills, subagents, and automated review loops
★ 2 setup Claude CodeCodexGemini CLI 2 agents 17d ago
Pragmatist 1.9k tok ·
copied ✓