AI Rulez
Goldziher/ai-rulez
Escreva regras uma vez, gere configs nativas para 19+ ferramentas IA
Ver no GitHubGerador de configuração unificado para 19+ ferramentas de IA (Claude, Cursor, Copilot, Windsurf, Gemini, etc). Define suas regras, skills e agents uma vez e gere configurações nativas para cada plataforma. Inclui 33 domínios de regras pré-configuradas cobrindo governança, qualidade de código, testes, git e segurança.
Instalação
npx convez-ai Goldziher/ai-rulez1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Sincronizar regras de IA em múltiplas ferramentas (Claude, Cursor, Copilot)
- Estabelecer padrões de desenvolvimento com regras pré-configuradas de qualidade
- Gerenciar agents especializados para tarefas específicas de desenvolvimento
- Evitar drift de configurações entre diferentes IDEs e assistentes IA
Veredito

Solução robusta e bem-arquitetada para quem usa múltiplas ferramentas IA no desenvolvimento. O catálogo de 33 domínios pré-configurados economiza tempo de setup, mas exige Go/npm/pip para executar. Ideal para times que querem governança centralizada.
README
A tradução para o português deste README ainda está na fila.
The Problem
Every AI coding tool wants its own config: Claude needs CLAUDE.md, Cursor wants .cursor/rules/, Copilot expects .github/copilot-instructions.md. Each has different formats, frontmatter, and directory conventions. If you use more than one tool, you're maintaining duplicate rules that inevitably drift apart.
The Solution
Write your rules, context, skills, agents, and commands once in .ai-rulez/. Run generate. Get native configs for every tool you use.
npx ai-rulez@latest init && npx ai-rulez@latest generate
ai-rulez generates correct, tool-native output for 19 platforms: Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Continue.dev, Codex, OpenCode, Amp, Junie, Antigravity, and more. Each preset respects the target tool's conventions — proper frontmatter, directory structure, file extensions, agent formats.
What Ships Out of the Box
ai-rulez isn't just a config generator. It ships with 33 builtin domains containing opinionated rules, agents, and workflows that establish a professional development baseline immediately.
Builtin Rules (auto-included)
These activate automatically. No configuration needed.
| Domain | What it enforces |
|---|---|
| ai-governance | No AI signatures in commits. Concise communication. Systematic debugging. Verification before claiming success. Critical review of subagent output. |
| code-quality | Anti-patterns prevention. Complexity limits. Dead code removal. Error handling standards. Readability. |
| testing | TDD workflow (red-green-refactor, no exceptions). Testing anti-patterns. Meaningful assertions. Test independence. |
| git-workflow | Atomic commits. Conventional commit messages. Safe operations. Branch hygiene. |
| security | Secrets handling. Input validation. Dependency auditing. Least privilege. |
| token-efficiency | Task runner usage. Incremental approach. Context preservation. Batch operations. |
| agent-delegation | Multi-agent coordination and delegation patterns. |
Builtin Agents
Specialized agents ready to use as subagents:
| Agent | Domain | Model | What it does |
|---|---|---|---|
| code-reviewer | ai-governance | sonnet | Reviews changes for correctness, security, and conventions. Reports by severity. |
| test-writer | testing | sonnet | Writes tests following strict TDD. Fails first, then implements. |
| security-auditor | security | sonnet | Audits dependencies, scans for CVEs, reviews input validation. |
| docs-writer | ai-governance | haiku | Writes clear, concise documentation. No fluff. |
| devops-engineer | cicd | haiku | CI/CD pipelines, GitHub Actions, Docker, deployment automation. |
| release-engineer | cicd | haiku | Version management, changelogs, multi-registry publishing. |
Opt-in Domains
Enable these based on your stack:
Languages (10): rust, python, typescript, go, java, ruby, php, elixir, csharp, r
Bindings (10): pyo3, napi-rs, magnus, ext-php-rs, rustler, wasm, jni-rs, extendr, cgo, vite-plus
Operational: cicd, docker, observability, documentation, polyglot-bindings, default-commands
# .ai-rulez/config.toml
builtins = ["rust", "python", "pyo3", "cicd", "docker", "default-commands"]
Content Types
| Type | Purpose | Example |
|---|---|---|
| Rules | What AI must/must not do | Security standards, coding conventions |
| Context | What AI should know | Architecture docs, domain knowledge |
| Skills | Reusable prompts and workflows | Deployment checklist, review protocol |
| Agents | Specialized AI personas | Code reviewer, performance engineer |
| Commands | Slash commands across tools | /review, /deploy, /test |
Organization at Scale
ai-rulez scales from solo projects to large organizations:
Domains — Group content by feature, language, or team:
.ai-rulez/domains/backend/rules/
.ai-rulez/domains/frontend/rules/
Profiles — Generate different configs for different audiences:
[profiles]
backend = ["backend", "database"]
frontend = ["frontend", "ui"]
Remote Includes — Share rules across repositories:
[[includes]]
name = "company-standards"
source = "https://github.com/company/ai-rules.git"
merge_strategy = "local-override"
Reasoning effort across providers — Tune how hard each AI tool thinks:
# .ai-rulez/agents/security-reviewer.md
---
name: security-reviewer
description: Reviews code for security regressions
effort: high
---
# .ai-rulez/config.toml
[defaults]
effort = "medium" # global default for every supported preset
[defaults.effort_by_preset]
codex = "high" # overrides the global default for Codex
claude = "xhigh" # …and for Claude
Accepted values: low, medium, high, xhigh, max, inherit. ai-rulez emits the right field per preset:
- Claude —
effortin.claude/agents/*.mdfrontmatter (per-agent) - Codex —
model_reasoning_effortin.codex/config.tomland.codex/agents/*.toml - Amp —
amp.anthropic.effortin.amp/settings.json(global) - Windsurf —
reasoning_effortin.windsurf/agents/*.mdfrontmatter (per-agent) - Opencode —
reasoningEffortin.opencode/agents/*.mdfrontmatter (per-agent)
Each preset maps the value to its own vocabulary; tools without a documented config surface (Cursor, Copilot, Gemini, etc.) are silently skipped. See docs/configuration.md for the full mapping table.
Per-preset model selection for subagents — Model strings differ per provider, so the same agent can declare a different model for each preset it targets:
# .ai-rulez/agents/research-helper.md
---
name: research-helper
description: Multi-provider research subagent
claude_model: opus
copilot_model: gpt-5
cursor_model: claude-3.7-sonnet
---
# .ai-rulez/config.toml — project-wide defaults
[defaults.model_by_preset]
claude = "sonnet" # used when an agent doesn't set its own claude_model
copilot = "gpt-5"
Per-agent <preset>_model wins over defaults.model_by_preset; the legacy single model: field on an agent is the lowest-priority fallback for backward compatibility.
Installed Skills — Pull reusable skills from external repos:
[[installed_skills]]
name = "kreuzberg"
source = "https://github.com/kreuzberg-dev/kreuzberg"
MCP Server
ai-rulez includes a built-in MCP server with 35+ tools that lets AI assistants manage their own governance. Add rules, update context, generate configs — all programmatically.
[[mcp_servers]]
name = "ai-rulez"
command = "npx"
args = ["-y", "ai-rulez@latest", "mcp"]
Installation
No install needed — npx ai-rulez@latest <command> works out of the box. Pick a permanent option below:
brew install goldziher/tap/ai-rulez
npx ai-rulez@latest <command>
npm install -g ai-rulez
uvx ai-rulez <command>
uv tool install ai-rulez
pip install ai-rulez
# or, isolated:
pipx install ai-rulez
Add to .pre-commit-config.yaml:
repos:
- repo: https://github.com/Goldziher/ai-rulez
rev: v4.4.1
hooks:
- id: ai-rulez-recursive # generate outputs across the repo
- id: ai-rulez-validate # dry-run validation
Available hook ids: ai-rulez-validate, ai-rulez-generate, ai-rulez-recursive, ai-rulez-enforce, ai-rulez-enforce-fix. Triggers on changes under .ai-rulez/.
Add to lefthook.yml:
pre-commit:
commands:
ai-rulez:
glob: ".ai-rulez/**"
run: ai-rulez generate --recursive
Or run ai-rulez init --setup-hooks while initializing a repo to wire hooks in automatically.
Documentation
Full documentation at goldziher.github.io/ai-rulez.
License
MIT