Agent Rules

If you're working with AI coding assistants across a team or maintaining multiple repos, this generates and maintains AGENTS.md files that follow the agents.md convention. It's basically structured onboarding docs for AI, not humans. The skill includes scripts to detect your project stack (Go, PHP, TypeScript, Python), extract commands from build configs and CI files, and generate either thin or verbose documentation with verification built in. The philosophy is pointer-based rather than duplicative, and it won't fabricate anything it can't verify. Useful when you want your AI agents to understand project conventions, build commands, and architecture rules without hunting through README files or guessing at undocumented patterns.

skills.sh installs: 839
GitHub stars: 89
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add netresearch/agent-rules-skill --skill agent-rules --agent claude-code

Installs into .claude/skills of the current project.

Files

AGENTS.md Generator Skill

Generate and maintain AGENTS.md files following the agents.md convention. AGENTS.md is FOR AGENTS, not humans.

When to Use

Creating or updating AGENTS.md for new/existing projects
Scaffolding a new repository — ship AGENTS.md with the initial commits; retrofitting later needs full re-verification
Standardizing agent documentation across repositories
Checking AGENTS.md freshness after code changes
Onboarding AI agents to an unfamiliar codebase

Scripts

Call every script by its full path: bash ${CLAUDE_SKILL_DIR}/scripts/<name> PATH. Calling one relative to the working directory is not covered by the frontmatter rule and raises a permission prompt per call.

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly