agentrigs
+ submit rig
~ / rigs / gacabartosz / ai-dev-handbook

gacabartosz/ai-dev-handbook

Team workflow guidelines for AI coding agents (Claude Code, Codex) + ready-to-copy configs: hooks, statusline, subagents, skills (TDD, security, debugging), rule templates

↗ GitHub ★ 0 MIT updated 4mo ago project Claude Code
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~199 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/gacabartosz/ai-dev-handbook

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 gacabartosz/ai-dev-handbook/configs/skills/debug-protocol .claude/skills/debug-protocol
$ npx degit gacabartosz/ai-dev-handbook/configs/skills/secure-by-default .claude/skills/secure-by-default
$ npx degit gacabartosz/ai-dev-handbook/configs/skills/tdd-loop .claude/skills/tdd-loop

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 (3)

debug-protocolsecure-by-defaulttdd-loop

Similar rigs

hgkim0105/claude_config
Claude vibe coding config: skills, templates for FastAPI + Next.js fullstack development
★ 1 setup Claude Code 2 skills 6mo ago
Minimalist 2.4k tok ·
curtischoutw/claude-institution
After distilling Fable 5, the output is an indexed CLAUDE.md + on-demand rules + skills, an executable specification designed for weaker model sessions.
★ 5 project Claude Code 3 skills 6d ago
Minimalist 571 tok ·
jakub-029/agent-field-kit
The Agent Field Kit — field manual + config pack for Claude Code. Built during a public 7-day autonomous AI experiment.
★ 0 project Claude Code 3 skills 3mo ago
Minimalist 163 tok ·
qyndex/claude-init
Production-grade Claude Code harness — a spec-driven, TDD-first, verification-gated, security-aware .claude/ scaffold you drop into any repo with one command.
★ 2 project Claude Code 22 mcp 58 skills 33 agents 62 hooks today
Fort Knox 98.5k tok ·
copied ✓