Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From agent-rules
Generates and maintains AGENTS.md files for AI agent onboarding and codebase documentation, with scripts to detect project structure, extract build commands, CI rules, and verify freshness.
npx claudepluginhub netresearch/claude-code-marketplace --plugin agent-rulesHow this skill is triggered — by the user, by Claude, or both
Slash command
/agent-rules:agent-rulesThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate and maintain AGENTS.md files following the [agents.md convention](https://agents.md/). AGENTS.md is FOR AGENTS, not humans.
AGENTS.mdCLAUDE.mdassets/example-workflows/validate-agents.ymlassets/root-thin.mdassets/root-verbose.mdassets/scoped/backend-go.mdassets/scoped/backend-php.mdassets/scoped/backend-python.mdassets/scoped/backend-typescript.mdassets/scoped/claude-code-skill.mdassets/scoped/cli.mdassets/scoped/concourse.mdassets/scoped/ddev.mdassets/scoped/docker.mdassets/scoped/documentation.mdassets/scoped/examples.mdassets/scoped/frontend-typescript.mdassets/scoped/github-actions.mdassets/scoped/gitlab-ci.mdassets/scoped/oro-bundle.mdCreates and maintains concise AGENTS.md / CLAUDE.md files for projects. Analyzes toolchain, linters, and conventions to produce minimal agent-facing documentation under 100 lines.
Analyzes a project and generates a root AGENTS.md with operational commands, golden rules, and nested AGENTS.md files for high-context zones. Invoke via "AGENTS.md 만들어줘", "에이전트 규칙 만들어줘", or "/agents-md".
Generates AGENTS.md files in repo folders (root, src/tests/api, monorepos) with build commands, testing, code style, structure, boundaries for coding agents. Only if missing.
Share bugs, ideas, or general feedback.
Generate and maintain AGENTS.md files following the agents.md convention. AGENTS.md is FOR AGENTS, not humans.
| Script | Purpose |
|---|---|
scripts/generate-agents.sh PATH | Generate AGENTS.md files |
scripts/validate-structure.sh PATH | Validate structure compliance |
scripts/check-freshness.sh PATH | Check if files are outdated |
scripts/verify-content.sh PATH | Verify documented files/commands match codebase |
scripts/verify-commands.sh PATH | Verify documented commands execute |
scripts/score-agents.sh PATH | Grade AGENTS.md quality, worst-first |
scripts/detect-project.sh PATH | Detect language, version, build tools |
scripts/detect-scopes.sh PATH | Identify directories needing scoped files |
scripts/extract-commands.sh PATH | Extract commands from build configs |
scripts/extract-ci-rules.sh PATH | Extract CI quality gates and version matrix |
scripts/extract-architecture-rules.sh PATH | Extract module boundaries |
scripts/extract-adrs.sh PATH | Extract architectural decision records |
scripts/extract-github-rulesets.sh PATH | Extract GitHub rulesets and merge rules |
See references/scripts-guide.md for full options.
detect-project.sh + detect-scopes.sh to identify stacks and subsystemsextract-commands.sh, extract-ci-rules.sh, etc. to gather factsgenerate-agents.sh with --style=thin (default) or --verboseverify-content.sh + verify-commands.sh -- MANDATORY before doneUse --update to preserve human-curated content outside <!-- GENERATED --> markers.
ai-tool-compatibility.md)| File | Contents |
|---|---|
verification-guide.md | Verification steps, design principles, anti-bloat |
scripts-guide.md | Script options, validation checklist |
quality-rubric.md | Quality grading rubric |
ai-tool-compatibility.md | 16-agent compatibility matrix |
output-structure.md | Root/scoped sections |
git-hooks-setup.md | Hook framework detection and setup |
examples/ | Complete examples |
ai-contribution-guidelines.md | "3 Cs" framework for AI contributions |
directory-coverage.md | Scoped-file coverage rationale |
Root: assets/root-thin.md (default) or root-verbose.md. Scoped: assets/scoped/, one per stack (Go/PHP/Python/TYPO3/Symfony/Oro/CLI/TS/skill-repo).
Go, PHP (Composer/Laravel/Symfony/TYPO3/Oro), TypeScript (React/Next/Vue/Node), Python (pip/poetry/ruff/mypy), Skill repos, Hybrid (multi-stack with auto-scoping).
agent-harness-skill — broader agent-readiness harness (CI verification, enforcement).skill-repo-skill — skill-repo structure (plugin.json, split licensing, release workflows).