> agent-rules

Use when creating or updating AGENTS.md files, .github/copilot-instructions.md, or other AI agent rule files, onboarding AI agents to a project, standardizing agent documentation, or when anyone mentions AGENTS.md, agent rules, project onboarding, or codebase documentation for AI agents.

fetch
$curl "https://skillshub.wtf/netresearch/agent-rules-skill/agent-rules?format=md"
SKILL.mdagent-rules

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
  • Standardizing agent documentation across repositories
  • Checking if AGENTS.md files are current with recent code changes
  • Onboarding AI agents to an unfamiliar codebase

Scripts

ScriptPurpose
scripts/generate-agents.sh PATHGenerate AGENTS.md files
scripts/validate-structure.sh PATHValidate structure compliance
scripts/check-freshness.sh PATHCheck if files are outdated
scripts/verify-content.sh PATHVerify documented files/commands match codebase
scripts/verify-commands.sh PATHVerify documented commands execute
scripts/detect-project.sh PATHDetect language, version, build tools
scripts/detect-scopes.sh PATHIdentify directories needing scoped files
scripts/extract-commands.sh PATHExtract commands from build configs
scripts/extract-ci-rules.sh PATHExtract CI quality gates and version matrix
scripts/extract-architecture-rules.sh PATHExtract module boundaries
scripts/extract-adrs.sh PATHExtract architectural decision records
scripts/extract-github-rulesets.sh PATHExtract GitHub rulesets and merge rules

See references/scripts-guide.md for full options.

Core Principles

  • Structured over Prose -- tables and maps parse faster than paragraphs
  • Verified Commands -- commands that don't work waste tokens debugging
  • Pointer Principle -- point to files, don't duplicate content
  • Audit Before Generating -- discover existing docs before running scripts
  • Hooks Before Commits -- detect and install: ls lefthook.yml captainhook.json .pre-commit-config.yaml .husky/pre-commit 2>/dev/null || echo "No hooks — add one". Then make setup or framework-specific install. See references/git-hooks-setup.md.

Cross-Agent Compatibility

After generating AGENTS.md, create symlinks for agents using their own format:

scripts/generate-agents.sh /path/to/project --symlinks
# Or manually: ln -s AGENTS.md CLAUDE.md && ln -s AGENTS.md GEMINI.md

Claude Code loads subdirectory CLAUDE.md on demand -- without symlinks, subdirectory AGENTS.md files are never loaded. Commit symlinks to git (9 bytes each).

See references/ai-tool-compatibility.md for the full 16-agent compatibility matrix.

References

FileContents
verification-guide.mdVerification steps, design principles
scripts-guide.mdScript options, validation checklist
ai-tool-compatibility.md16-agent compatibility matrix
output-structure.mdRoot/scoped sections
git-hooks-setup.mdHook framework detection and setup
examples/Complete examples

Templates

Root: assets/root-thin.md (default), root-verbose.md. Scoped: assets/scoped/ -- backend-go.md, backend-php.md, python-modern.md, typo3.md, symfony.md, skill-repo.md, cli.md, frontend-typescript.md, oro.md.

Supported Projects

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).

┌ stats

installs/wk0
░░░░░░░░░░
github stars35
███████░░░
first seenMar 17, 2026
└────────────

┌ repo

netresearch/agent-rules-skill
by netresearch
└────────────

┌ tags

└────────────