Goldziher/ai-rulez

Author, generate, validate and govern AI agent rules, skills, plugins and MCP configuration across 52 coding assistants. Review with verified model evidence, evaluate skills, lock and sign dependencies, and publish bundles. CLI, MCP server and Go API.

This repository also configures its own agents. See what ai-rulez tells them →

163Stars on the repository
202Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

code-reviewer

01

Goldziher/ai-rulez

Agent Claude Code

Use when reviewing code changes for quality, security, and convention compliance.

not rated 163 +4 changed 3d ago A 17 tokens original MIT

docs-writer

02

Goldziher/ai-rulez

Agent Claude Code

Use when writing or updating documentation, READMEs, or changelogs.

not rated 163 +4 today A 19 tokens original MIT

devops-engineer

03

Goldziher/ai-rulez

Agent Claude Code

Use when working on CI/CD pipelines, GitHub Actions, Docker, or deployment automation.

not rated 163 +4 today A 22 tokens original MIT

release-engineer

04

Goldziher/ai-rulez

Agent Claude Code

Use when preparing releases, version bumps, changelog updates, or publishing packages.

not rated 163 +4 today A 19 tokens original MIT

ffi-engineer

05

Goldziher/ai-rulez

Agent Claude Code

Native FFI surface and ABI design.

not rated 163 +4 today A 11 tokens original MIT

security-auditor

07

Goldziher/ai-rulez

Agent Claude Code

Use when auditing code or dependencies for security vulnerabilities.

not rated 163 +4 today A 14 tokens original MIT

test-writer

08

Goldziher/ai-rulez

Agent Claude Code

Use when writing tests — follows TDD red-green-refactor cycle.

not rated 163 +4 changed 3d ago A 17 tokens original MIT

a11y-checker

09

Goldziher/ai-rulez

Agent Claude Code

Checks React components for missing accessibility attributes. Use when a component is added or changed.

not rated 163 +4 today A 23 tokens original MIT

payout-auditor

10

Goldziher/ai-rulez

Agent Claude Code

Reviews payout records for rounding problems. Use before a payout run.

not rated 163 +4 today A 19 tokens original MIT

Goldziher/ai-rulez

Agent Claude Code

Reads test output and source to explain why a test fails. Use after a failing test run.

not rated 163 +4 today A 26 tokens original MIT

dependency-auditor

13

Goldziher/ai-rulez

Agent Claude Code

Lists outdated or duplicated dependencies declared in manifests. Use when preparing an upgrade.

not rated 163 +4 today A 20 tokens original MIT

docs-link-checker

14

Goldziher/ai-rulez

Agent Claude Code

Finds relative links in Markdown files that point to missing files. Use before publishing documentation.

not rated 163 +4 today A 23 tokens original MIT

schema-reviewer

15

Goldziher/ai-rulez

Agent Claude Code

Reviews a SQL schema change for naming and nullability problems. Use when a migration is proposed.

not rated 163 +4 today A 23 tokens original MIT

cleaner

16

Goldziher/ai-rulez

Agent Claude Code

Tidy imports across the repo.

not rated 163 +4 today A 10 tokens original MIT

issue-fixer

17

Goldziher/ai-rulez

Agent Claude Code

Fix bugs reported in tracker issues.

not rated 163 +4 today A 11 tokens original MIT

explainer

18

Goldziher/ai-rulez

Agent Claude Code

Read-only code explainer. Never modifies files.

not rated 163 +4 today A 13 tokens original MIT

migrator

19

Goldziher/ai-rulez

Agent Claude Code

Generate and apply schema migrations.

not rated 163 +4 today A 10 tokens original MIT

pre-flight

20

Goldziher/ai-rulez

Agent Claude Code

MUST BE USED PROACTIVELY for every single user message, regardless of topic, before any other agent.

not rated 163 +4 today A 26 tokens original MIT

docs-reviewer

21

Goldziher/ai-rulez

Agent Claude Code

Reviews documentation pages for broken wording and stale instructions.

not rated 163 +4 today A 14 tokens original MIT

deploy-watcher

22

Goldziher/ai-rulez

Agent Claude Code

Reports on the health of a deployment after the user ships it.

not rated 163 +4 today A 17 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: