agentrigs
+ submit rig
~ / rigs / clnnn / playbook

clnnn/playbook

Agent skills for everything up to the code: canvas, PRD, story map, context maps, ADRs, and INVEST-sliced issues. The build stage stays yours.

↗ GitHub ★ 0 MIT updated today project Claude CodeCodex
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~161 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 clnnn/playbook/.claude ./rig-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.

$ npx degit clnnn/playbook/.agents/skills/lean-product-canvas .claude/skills/lean-product-canvas
$ npx degit clnnn/playbook/.agents/skills/napkin-math .claude/skills/napkin-math
$ npx degit clnnn/playbook/.agents/skills/to-prd .claude/skills/to-prd
$ npx degit clnnn/playbook/.agents/skills/to-slices .claude/skills/to-slices

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 (4)

lean-product-canvasnapkin-mathto-prdto-slices

Similar rigs

yuval/dotfiles
Personal dotfiles for macOS: zsh, Ghostty, Claude Code, VS Code, Emacs, and iTerm2
★ 0 setup Claude CodeCodex 4 skills 6mo ago
Minimalist 1.7k tok ·
caiuswang/regin
regin is not an agent platform. It's the layer around an agent — the harness.
★ 4 project Claude CodeCodex 3 mcp 5 skills today
Pragmatist 11.1k tok ·
ieuanign/skills
Ieuan's add-on agent skills for Claude Code — a dev-loop issue-to-PR pipeline over a custom agent roster, plus coding-standards setup. Install via: npx skills@latest add ieuanign/skills
★ 2 project Claude CodeCodex 9 skills today
YOLO Cowboy 2.1k tok ·
kdg212-lang/dotfiles
Claude Code agents and personal dotfiles
★ 0 setup Claude Code 12 skills 5mo ago
Skill Collector 903 tok ·
copied ✓