Agent Claude Code
Use when reviewing code changes for quality, security, and convention compliance.
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 →
Agent Claude Code
Use when reviewing code changes for quality, security, and convention compliance.
Agent Claude Code
Use when writing or updating documentation, READMEs, or changelogs.
Agent Claude Code
Use when working on CI/CD pipelines, GitHub Actions, Docker, or deployment automation.
Agent Claude Code
Use when preparing releases, version bumps, changelog updates, or publishing packages.
Agent Claude Code
Native FFI surface and ABI design.
Agent Claude Code
Cross-language API design and binding parity.
Agent Claude Code
Use when auditing code or dependencies for security vulnerabilities.
Agent Claude Code
Use when writing tests — follows TDD red-green-refactor cycle.
Agent Claude Code
Checks React components for missing accessibility attributes. Use when a component is added or changed.
Agent Claude Code
Reviews payout records for rounding problems. Use before a payout run.
Agent Claude Code
Summarise a tracker issue.
Agent Claude Code
Reads test output and source to explain why a test fails. Use after a failing test run.
Agent Claude Code
Lists outdated or duplicated dependencies declared in manifests. Use when preparing an upgrade.
Agent Claude Code
Finds relative links in Markdown files that point to missing files. Use before publishing documentation.
Agent Claude Code
Reviews a SQL schema change for naming and nullability problems. Use when a migration is proposed.
Agent Claude Code
Tidy imports across the repo.
Agent Claude Code
Fix bugs reported in tracker issues.
Agent Claude Code
Read-only code explainer. Never modifies files.
Agent Claude Code
Generate and apply schema migrations.
Agent Claude Code
MUST BE USED PROACTIVELY for every single user message, regardless of topic, before any other agent.
Agent Claude Code
Reviews documentation pages for broken wording and stale instructions.
Agent Claude Code
Reports on the health of a deployment after the user ships it.
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: