agentrigs
+ submit rig
~ / rigs / ucsahinn / agentchef

ucsahinn/agentchef

An unofficial, cross-platform setup kit for OpenAI Codex CLI and Anthropic Claude Code: specialist agents, curated skills, safe MCP defaults, preview-first installation, and clear verification.

↗ GitHub ★ 6 MIT updated 3d ago project Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~5.0k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/ucsahinn/agentchef

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 <redacted>-agent-routing .claude/skills/adaptive-agent-routing
$ npx degit <redacted>-brief .claude/skills/agent-brief
$ npx degit <redacted>-operator .claude/skills/agentchef-operator
$ npx degit <redacted>-budget-planner .claude/skills/context-budget-planner
$ npx degit <redacted>-research .claude/skills/evidence-research
$ npx degit <redacted>-review-workflow .claude/skills/external-review-workflow
$ npx degit <redacted> .claude/skills/fetch
$ npx degit <redacted>-handoff .claude/skills/gptpro-handoff
$ npx degit <redacted> .claude/skills/gptpro
$ npx degit <redacted>-diagram-triplet .claude/skills/offline-diagram-triplet
$ npx degit ucsahinn/agentchef/plugins/agentchef/skills/seo .claude/skills/seo

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 (11)

adaptive-agent-routingagent-briefagentchef-operatorcontext-budget-plannerevidence-researchexternal-review-workflowfetchgptpro-handoffgptprooffline-diagram-tripletseo

Similar rigs

addyosmani/web-quality-skills
Agent Skills for optimizing web quality based on Lighthouse and Core Web Vitals.
★ 2,867 collection Claude CodeCodex 6 skills 2mo ago
Pragmatist 1.9k tok ·
JacbK/persona
Persona is a drop in "Kit", "Care Package", or anything else you want to call it for your CLI (Claude Code, Codex, Gemini CLI, etc), that supports the setup, building, and deployment of your personal website.
★ 16 project Claude CodeCodexCursor 7 skills 20d ago
Pragmatist 1.8k tok ·
benmarte/codemunch
Zero-config, token-efficient code exploration for Claude Code — no MCP server, no Python, no database
★ 7 project Claude Code 7 skills 7mo ago
Pragmatist 997 tok ·
95gabor/agentic-workflow
🔨 Agentic workflow template
★ 2 project CodexCursor 10 skills 3mo ago
Skill Collector 4.5k tok ·
copied ✓