ai-rulez
Author, generate, validate and govern AI agent rules, skills, plugins and MCP configuration across 52 coding assistants. Review with verified model evidence, ev
What is 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.
Overview of ai-rulez
What it is
ai-rulez is a standards-compliant lifecycle tool for agent knowledge and capabilities. It manages rules, context, skills, agents, commands, hooks, permissions and MCP servers in a single source of truth (.ai-rulez/). The tool covers the full lifecycle: author → generate → bundle → lint/validate → govern → publish. It treats agent knowledge like software that is versioned, linted, locked, signed and audited, with an organization policy layer that enforces a minimum standard across repositories.
Key features
- One source, 52 targets: Author once in
.ai-rulez/and generate native files for 52 built-in harnesses including Claude Code, Cursor, Codex, Copilot and Gemini CLI. - Lock file:
ai-rulez.lockpins remote includes, installed skills and authored content, similar togo.sumorpackage-lock.json. - Supply-chain trust: Supports Sigstore signing, in-toto/DSSE attestations, CycloneDX/SPDX SBOMs and reviewer approvals.
- Org-wide policy: A central policy sets tighten-only floors that repository settings cannot loosen;
verifyand CI gates enforce it. - Static validation and security scanning: Checks config, content, scripts and conventional harness files with stable
ARcodes, without requiring an ai-rulez config. - Model-based judge: Reviews agent configuration for security, quality and governance with quoted evidence, an adjudicator, rubric skills, and change-impact selection.
- Skill evaluation: Runs harness-neutral eval cases through adapters; measures pass rate, trigger precision/recall, ablation and cost.
Use cases
- Managing and governing AI agent rules, skills, plugins and MCP configuration across multiple coding assistants.
- Ensuring consistency and compliance of agent configurations across a team or organization.
- Auditing and verifying which prompts and rules are actually in use in production.
- Publishing and distributing agent knowledge bundles with signed artifacts and SBOMs.
Getting started
See the repository README for installation and quick-start instructions.
License and pricing
The project is licensed under MIT and is open source. No pricing information is stated.
Based on the project's public README and repository metadata.