agentrigs
+ submit rig
~ / rigs / whanksta / Multi-Agent-Setup

whanksta/Multi-Agent-Setup

One canonical rulebook every AI coding agent reads (Claude Code, Codex, Antigravity) — survives cloud sync, self-heals, audits its own docs.

↗ GitHub ★ 1 mit updated 1mo ago personal setup Claude CodeCodex
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~885 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 whanksta/Multi-Agent-Setup/.claude ./rig-multi-agent-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 whanksta/Multi-Agent-Setup/.claude/skills/codebase-audit .claude/skills/codebase-audit
$ npx degit whanksta/Multi-Agent-Setup/.claude/skills/docreview .claude/skills/docreview

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 *)"
    ]
  }
}

Skills (2)

codebase-auditdocreview

Similar rigs

fredrikaverpil/dotfiles
—
★ 259 setup Claude CodeCursorGemini CLI 3 mcp 16 skills 1 hooks 6d ago
YOLO Cowboy 33.3k tok ·
ferraroroberto/fleet-config
Versioned home for my user-scope Claude Code config: hooks, helpers, and slash commands that shape Claude across the home-stack fleet.
★ 1 setup Claude CodeCodex 33 skills today
Skill Collector 4.8k tok ·
Saturate/agents
Skills, plugins, and config for AI coding agents (Claude Code, OpenCode, and more)
★ 0 collection Claude Code 37 skills 3 agents 2mo ago
Skill Collector 4.3k tok ·
michielvandermeer/skills
—
★ 9 project Claude CodeCodex 34 skills 8 agents 1 hooks 1d ago
Orchestrator 2.5k tok ·
copied ✓