Skip to content
Back to search

ai-rulez

Standards-compliant lifecycle tool for agent knowledge and capabilities: author, generate, bundle, validate, govern, publish.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/Goldziher/ai-rulez with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/Goldziher/ai-rulez'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/goldziher--ai-rulez/badge.svg)](/listings/goldziher--ai-rulez)

HTML

<a href="/listings/goldziher--ai-rulez"><img src="/api/listings/goldziher--ai-rulez/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 308 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <p align="center">
  2. <img src="https://raw.githubusercontent.com/Goldziher/ai-rulez/main/docs/assets/ai-rulez-banner.png" alt="AI-Rulez" width="820" />
  3. </p>
  4. <p align="center">
  5. <strong>One source for the rules, skills and settings of every AI coding assistant</strong>
  6. </p>
  7. <p align="center">
  8. <a href="https://www.npmjs.com/package/ai-rulez"><img src="https://img.shields.io/npm/v/ai-rulez?color=blue" alt="npm version"></a>
  9. <a href="https://pypi.org/project/ai-rulez/"><img src="https://img.shields.io/pypi/v/ai-rulez?color=blue" alt="PyPI version"></a>
  10. <a href="https://github.com/Goldziher/homebrew-tap"><img src="https://img.shields.io/github/v/release/Goldziher/ai-rulez?label=homebrew&color=blue" alt="Homebrew version"></a>
  11. <a href="https://pkg.go.dev/github.com/Goldziher/ai-rulez/v5"><img src="https://img.shields.io/github/v/release/Goldziher/ai-rulez?label=go&color=blue" alt="Go version"></a>
  12. <a href="https://github.com/Goldziher/ai-rulez/actions/workflows/ci.yaml"><img src="https://img.shields.io/github/actions/workflow/status/Goldziher/ai-rulez/ci.yaml?branch=main&label=CI" alt="CI"></a>
  13. <a href="https://github.com/Goldziher/ai-rulez/blob/main/LICENSE"><img src="https://img.shields.io/github/license/Goldziher/ai-rulez?color=blue" alt="License"></a>
  14. <a href="https://goldziher.github.io/ai-rulez/"><img src="https://img.shields.io/badge/docs-ai--rulez-blue" alt="Documentation"></a>
  15. </p>
  16. <p align="center">
  17. <a href="https://goldziher.github.io/ai-rulez/"><strong>Documentation</strong></a> &middot;
  18. <a href="https://goldziher.github.io/ai-rulez/quick-start/"><strong>Quick Start</strong></a> &middot;
  19. <a href="https://goldziher.github.io/ai-rulez/examples/"><strong>Examples</strong></a>
  20. </p>
  21. ---
  22. ## What it is
  23. ai-rulez keeps the instructions for your AI coding assistants in one directory, `.ai-rulez/`: rules, context, skills,
  24. agents, commands, hooks, permissions and MCP servers. From that source it generates the native files of each assistant
  25. your team uses (`AGENTS.md`, `CLAUDE.md`, `.cursor/rules/`, `.github/instructions/`, skill folders, MCP and settings
  26. files) for 52 tools, and keeps them in sync.
  27. - **One source, every tool.** Edit `.ai-rulez/`, run `generate`, and Claude Code, Cursor, Codex, Copilot, Gemini CLI
  28. and the rest get the same guidance in their own format.
  29. - **Checked in CI.** `generate --check` catches drift; `validate` lints content, links and security issues with stable
  30. `AR` rule codes, and also works on plain `AGENTS.md` and `SKILL.md` files with no configuration.
  31. - **Governed like dependencies.** A lock file pins remote includes, installed skills and authored content; approvals,
  32. Sigstore signatures, SBOMs and an organization policy cover the rest.
  33. - **Packaged for distribution.** Build plugin bundles and marketplaces, Agent Plugins and ARD manifests, and publish
  34. them.
  35. ## 30-second example
  36. ```bash
  37. npx ai-rulez@latest init acme
  38. ```
  39. Set the tools you use in `.ai-rulez/config.toml`:
  40. ```toml
  41. version = "5.0"
  42. name = "acme"
  43. presets = ["claude", "cursor", "codex", "copilot", "gemini"]
  44. ```
  45. Add a rule and generate:
  46. ```bash
  47. npx ai-rulez@latest add rule testing --content '# Testing
  48. - Every bug fix ships with a regression test.'
  49. npx ai-rulez@latest generate
  50. ```
  51. ```text
  52. AGENTS.md # rules and context, read by Codex, Cursor, Copilot and Gemini CLI
  53. CLAUDE.md # imports @AGENTS.md for Claude Code
  54. .agents/skills/ # skills
  55. .claude/skills/
  56. .gemini/settings.json # points Gemini CLI at AGENTS.md
  57. .mcp.json, .cursor/mcp.json, .vscode/mcp.json, .codex/config.toml
  58. ```
  59. Commit `.ai-rulez/` with the generated files, and add `ai-rulez generate --check` to CI. The
  60. [Quick start](https://goldziher.github.io/ai-rulez/quick-start/) walks through it in five minutes.
  61. <p align="center">
  62. <img src="https://raw.githubusercontent.com/Goldziher/ai-rulez/main/docs/assets/quickstart.gif" alt="ai-rulez init and generate: one .ai-rulez source becomes the native files of several AI tools" width="820" />
  63. </p>
  64. ## Install
  65. ```bash
  66. brew install goldziher/tap/ai-rulez # Homebrew (macOS, Linux)
  67. npm install -g ai-rulez # npm (Node.js 22+)
  68. pipx install ai-rulez # PyPI (Python 3.11+); or uv tool install ai-rulez
  69. go install github.com/Goldziher/ai-rulez/v5/cmd/ai-rulez@latest # Go (note the /v5)
  70. ```
  71. On Windows x64, install with Scoop:
  72. ```powershell
  73. scoop bucket add goldziher https://github.com/Goldziher/scoop-bucket
  74. scoop install goldziher/ai-rulez
  75. ```
  76. Or run it without installing: `npx ai-rulez@latest <command>` or `uvx ai-rulez <command>`. See
  77. [Installation](https://goldziher.github.io/ai-rulez/installation/) for platforms, shell completion and git hooks.
  78. ## Supported tools
  79. 52 built-in presets, one per assistant, CLI agent or IDE integration. Combine any of them in `presets = [...]`;
  80. [Supported harnesses](https://goldziher.github.io/ai-rulez/harnesses/) shows which rules, skills, agents, commands, MCP servers, hooks and permissions
  81. each one receives. A tool that is not listed can be added as a [custom preset](https://goldziher.github.io/ai-rulez/profiles/).
  82. <details>
  83. <summary><strong>All 52 built-in presets</strong></summary>
  84. | Preset | Tool |
  85. | ------ | ---- |
  86. | `aiassistant` | [JetBrains AI Assistant](https://www.jetbrains.com/help/ai-assistant/) |
  87. | `amp` | [Sourcegraph Amp](https://ampcode.com) |
  88. | `antigravity` | [Google Antigravity](https://antigravity.google/docs) |
  89. | `augment` | [Augment Code](https://docs.augmentcode.com) |
  90. | `baz` | [Baz](https://baz.ai/docs/agents/skills-and-instructions) |
  91. | `bob` | [IBM Bob](https://bob.ibm.com/docs) |
  92. | `claude` | [Claude Code](https://code.claude.com/docs) |
  93. | `cline` | [Cline](https://docs.cline.bot) |
  94. | `codebuddy` | [CodeBuddy Code](https://www.codebuddy.ai/docs/cli) |
  95. | `codebuff` | [Codebuff](https://www.codebuff.com/docs) |
  96. | `codewhale` | [Codewhale](https://github.com/codewhale-hq/Codewhale) |
  97. | `codex` | [OpenAI Codex](https://developers.openai.com/codex) |
  98. | `commandcode` | [Command Code](https://commandcode.ai/docs) |
  99. | `copilot` | [GitHub Copilot](https://docs.github.com/en/copilot) |
  100. | `copilot-cli` | [GitHub Copilot CLI](https://docs.github.com/en/copilot/how-tos/copilot-cli) |
  101. | `cortex` | [Snowflake Cortex Code](https://docs.snowflake.com/en/user-guide/cortex-code/extensibility) |
  102. | `crush` | [Crush](https://github.com/charmbracelet/crush) |
  103. | `cursor` | [Cursor](https://cursor.com/docs) |
  104. | `deepagents` | [Deep Agents Code](https://docs.langchain.com/oss/deepagents/code) |
  105. | `devin` | [Devin CLI](https://docs.devin.ai/cli) |
  106. | `dsh` | [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) |
  107. | `factory` | [Factory Droid](https://docs.factory.ai) |
  108. | `gemini` | [Gemini CLI](https://geminicli.com/docs/) |
  109. | `gitlab-duo` | [GitLab Duo CLI](https://docs.gitlab.com/user/gitlab_duo_cli/customize/) |
  110. | `goose` | [goose](https://goose-docs.ai) |
  111. | `grok` | [Grok Build CLI](https://docs.x.ai/build/overview) |
  112. | `hermes` | [Hermes Agent](https://hermes-agent.nousresearch.com/docs) |
  113. | `junie` | [JetBrains Junie](https://junie.jetbrains.com) |
  114. | `kilo` | [Kilo Code](https://kilo.ai/docs) |
  115. | `kimi` | [Kimi Code](https://moonshotai.github.io/kimi-code/) |
  116. | `kiro` | [Kiro](https://kiro.dev/docs) |
  117. | `letta` | [Letta Code](https://docs.letta.com) |
  118. | `mimocode` | [MiMo Code](https://mimo.xiaomi.com/mimocode) |
  119. | `muse` | [Meta Muse Code](https://dev.meta.ai/docs/muse-code) |
  120. | `omp` | [oh-my-pi](https://github.com/can1357/oh-my-pi) |
  121. | `openclaw` | [OpenClaw](https://docs.openclaw.ai) |
  122. | `opencode` | [OpenCode](https://opencode.ai/docs) |
  123. | `pi` | [pi](https://pi.dev/docs/latest) |
  124. | `poolside` | [Poolside Pool](https://docs.poolside.ai) |
  125. | `qoder` | [Qoder](https://docs.qoder.com/cli/quickstart) |
  126. | `qwen` | [Qwen Code](https://qwenlm.github.io/qwen-code-docs/en/) |
  127. | `reasonix` | [Reasonix](https://github.com/esengine/DeepSeek-Reasonix) |
  128. | `replit` | [Replit Agent](https://docs.replit.com/features/agent/overview) |
  129. | `rovodev` | [Atlassian Rovo Dev](https://www.atlassian.com/software/rovo-dev) |
  130. | `takt` | [Takt](https://github.com/nrslib/takt) |
  131. | `trae` | [Trae](https://docs.trae.ai/ide/rules) |
  132. | `vibe` | [Mistral Vibe](https://docs.mistral.ai/vibe) |
  133. | `warp` | [Warp](https://docs.warp.dev) |
  134. | `xum` | [Xum](https://xum.coder.com) |
  135. | `zcode` | [ZCode](https://zcode.z.ai/en/docs) |
  136. | `zed` | [Zed](https://zed.dev/docs/ai) |
  137. | `zoocode` | [Zoo Code](https://docs.zoocode.dev) |
  138. </details>
  139. ## What else it does
  140. | Area | Commands | Docs |
  141. | ---- | -------- | ---- |
  142. | Author | `add`, `edit`, `show`, `list`, `remove`, `domain`, `profile`, `include`, `skill install` | [Configuration](https://goldziher.github.io/ai-rulez/configuration/), [Rules](https://goldziher.github.io/ai-rulez/rules/), [Skills](https://goldziher.github.io/ai-rulez/skills/), [Includes](https://goldziher.github.io/ai-rulez/includes/) |
  143. | Import | `init --from auto`, `convert`, `migrate v5` | [CLI](https://goldziher.github.io/ai-rulez/cli/), [Migrating to v5](https://goldziher.github.io/ai-rulez/migration-v5/) |
  144. | Generate | `generate`, `generate --user`, `generate --recursive`, `generate --watch`, `clean` | [Harnesses](https://goldziher.github.io/ai-rulez/harnesses/), [Hooks and settings](https://goldziher.github.io/ai-rulez/settings/), [Monorepo](https://goldziher.github.io/ai-rulez/monorepo/) |
  145. | Validate | `validate`, `scan`, `verifiers run`, `judge`, `review` | [Strict validation](https://goldziher.github.io/ai-rulez/strict-validation/), [Verifiers](https://goldziher.github.io/ai-rulez/verifiers/), [Judge](https://goldziher.github.io/ai-rulez/judge/) |
  146. | Govern | `lock`, `update`, `approve`, `sign`, `verify`, `sbom` | [Lock file](https://goldziher.github.io/ai-rulez/lockfile/), [Signing](https://goldziher.github.io/ai-rulez/signing/), [Policy](https://goldziher.github.io/ai-rulez/policy/) |
  147. | Bundle and publish | `generate --plugin`, `verify --plugin`, `publish` | [Plugins](https://goldziher.github.io/ai-rulez/plugins/), [Publish](https://goldziher.github.io/ai-rulez/publish/) |
  148. | Operate | `mcp --serve-skills`, `search`, `eval`, `tokens`, `cost`, `catalog`, `telemetry` | [MCP server](https://goldziher.github.io/ai-rulez/mcp-server/), [Evals](https://goldziher.github.io/ai-rulez/evals/) |
  149. | Embed | `pkg/airulez` | [Go API](https://goldziher.github.io/ai-rulez/embedding/) |
  150. `validate --strict` flags a defect, `--explain` describes it, and `generate --check` fails on drift:
  151. <p align="center">
  152. <img src="https://raw.githubusercontent.com/Goldziher/ai-rulez/main/docs/assets/validate.gif" alt="ai-rulez validate --strict flags a defect, --explain describes it, and generate --check fails on drift" width="820" />
  153. </p>
  154. `verify --plugin` reports hand-edited or stray files in a plugin bundle, and `generate --plugin` restores it:
  155. <p align="center">
  156. <img src="https://raw.githubusercontent.com/Goldziher/ai-rulez/main/docs/assets/plugin-drift.gif" alt="ai-rulez verify --plugin reporting changed and extra files in a plugin bundle, then generate --plugin restoring it" width="820" />
  157. </p>
  158. Claude Code and Codex discover native skills through their names and descriptions, then load skill bodies on demand.
  159. In repositories with nested skill directories, metadata from multiple scopes can accumulate as a session moves between them.
  160. MCP delivery keeps served skills out of the native catalog. For Claude Code, generated project guidance tells Claude
  161. when to search for served skills using the task and repository path. Skill selection still depends on the model and client
  162. settings. [Compare delivery options](https://goldziher.github.io/ai-rulez/mcp-server/#choosing-the-delivery).
  163. <p align="center">
  164. <img src="https://raw.githubusercontent.com/Goldziher/ai-rulez/main/docs/assets/skills-mcp.gif" alt="ai-rulez tokens before and after serving skills over MCP, then find_skill and load_skill" width="780" />
  165. </p>
  166. In a monorepo, `generate --recursive` and `validate --recursive` process every nested `.ai-rulez/`:
  167. <p align="center">
  168. <img src="https://raw.githubusercontent.com/Goldziher/ai-rulez/main/docs/assets/monorepo.gif" alt="ai-rulez generate --recursive over two nested roots, recursive validation, and a token budget check" width="780" />
  169. </p>
  170. ## How it compares
  171. Static checks of `ai-rulez scan` against other open-source skill scanners, on a public dataset we did not write:
  172. <!-- skillbench:start -->
  173. 1384 skills (839 malicious, 545 benign) from the MaliciousSkillBench source-disjoint `test` partition, static, text-only, no LLM. Scored on each tool's own verdict; intervals are 95% clustered bootstrap.
  174. | Tool | Version | Recall | False-positive rate | Precision | F1 |
  175. | ---- | ------- | ------ | ------------------- | --------- | -- |
  176. | ai-rulez | 5.11.1 | 0.195 (0.139-0.271) | 0.338 (0.297-0.378) | 0.471 | 0.276 (0.210-0.354) |
  177. | skill-scanner | 2.3.2 | 0.077 (0.044-0.125) | 0.040 (0.025-0.058) | 0.747 | 0.140 (0.082-0.216) |
  178. | skillspector | 2.13.4 | 0.113 (0.073-0.167) | 0.194 (0.161-0.228) | 0.473 | 0.183 (0.124-0.254) |
  179. <!-- skillbench:end -->
  180. That table is the last held-out read, of release 5.11.1. Unreleased changes are measured only on the `dev` partition,
  181. which rule changes are tuned on, so expect lower numbers on held-out sources. `ai-rulez-threat` is
  182. `scan --fail-on threat`, the gate to compare with the other scanners; `ai-rulez` is `--fail-on warning`:
  183. <!-- skillbench-dev:start -->
  184. 8213 skills (6523 malicious, 1690 benign) from the MaliciousSkillBench source-disjoint `dev` partition, static, text-only, no LLM. Scored on each tool's own verdict; intervals are 95% clustered bootstrap.
  185. | Tool | Version | Recall | False-positive rate | Precision | F1 |
  186. | ---- | ------- | ------ | ------------------- | --------- | -- |
  187. | ai-rulez-threat | unreleased | 0.225 (0.209-0.242) | 0.007 (0.004-0.011) | 0.992 | 0.367 (0.345-0.389) |
  188. | ai-rulez | unreleased | 0.437 (0.420-0.454) | 0.074 (0.062-0.087) | 0.958 | 0.600 (0.584-0.616) |
  189. | skill-scanner | 2.3.2 | 0.312 (0.298-0.326) | 0.008 (0.004-0.013) | 0.993 | 0.475 (0.459-0.491) |
  190. | skillspector | 2.13.4 | 0.323 (0.306-0.339) | 0.155 (0.138-0.173) | 0.889 | 0.473 (0.455-0.492) |
  191. <!-- skillbench-dev:end -->
  192. And on real, widely used skills, where every flag is a false alarm:
  193. <!-- skillbench-clean:start -->
  194. 563 real skills from the `clean` track, all treated as benign, static, text-only, no LLM. A flag is a false alarm.
  195. | Tool | Version | Skills flagged | Share flagged |
  196. | ---- | ------- | -------------- | ------------- |
  197. | ai-rulez-threat | unreleased | 12 of 563 | 2.1% (1.1-3.4) |
  198. | ai-rulez | unreleased | 53 of 563 | 9.4% (7.1-11.9) |
  199. | skill-scanner | 2.3.2 | 26 of 563 | 4.6% (3.0-6.4) |
  200. | skillspector | 2.13.4 | 167 of 563 | 29.7% (25.9-33.4) |
  201. <!-- skillbench-clean:end -->
  202. Every number is reproducible with one command. See [Scanner benchmark](https://goldziher.github.io/ai-rulez/benchmarks/)
  203. for the protocol and its limits.
  204. ## Standards
  205. ai-rulez generates and validates AGENTS.md, Agent Skills, Agent Plugins, ARD, llms.txt, OKF (the format of
  206. `.ai-rulez/` itself), MCP server configuration and Server Cards, CycloneDX and SPDX SBOMs, and in-toto/DSSE
  207. attestations in Sigstore bundles. [Standards conformance](https://goldziher.github.io/ai-rulez/standards/) lists the versions, the conformance tests
  208. and the known gaps.
  209. ## CI and git hooks
  210. GitHub Actions:
  211. ```yaml
  212. steps:
  213. - uses: actions/checkout@v7
  214. - uses: Goldziher/ai-rulez@v5
  215. with:
  216. version: 5.14.0
  217. - run: ai-rulez generate --check
  218. - run: ai-rulez validate
  219. ```
  220. See [GitHub Actions](https://goldziher.github.io/ai-rulez/github-actions/) for the full workflow and the governance gate.
  221. pre-commit or prek:
  222. ```yaml
  223. repos:
  224. - repo: https://github.com/Goldziher/ai-rulez
  225. rev: v5.14.0
  226. hooks:
  227. - id: ai-rulez-recursive
  228. - id: ai-rulez-validate
  229. ```
  230. See [GitHub Actions](https://goldziher.github.io/ai-rulez/github-actions/) for the governance gate and scheduled pin
  231. updates, and [Installation](https://goldziher.github.io/ai-rulez/installation/#git-hooks) for Lefthook, Poly and `init --setup-hooks`.
  232. ## Upgrading from 4.x
  233. Run `ai-rulez migrate v5 --dry-run`, then follow [Migrating to v5](https://goldziher.github.io/ai-rulez/migration-v5/).
  234. ## Documentation
  235. Full documentation: [goldziher.github.io/ai-rulez](https://goldziher.github.io/ai-rulez/). Contributors: see
  236. [CONTRIBUTING.md](CONTRIBUTING.md) and [Architecture](https://goldziher.github.io/ai-rulez/architecture/).
  237. ## License
  238. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.