Lint, secure, and manage AGENTS.md files — the open standard for AI coding agents. ESLint for AGENTS.md.
<p align="center"> <span style="font-size:80px">🔒</span> </p> <h1 align="center">agents-md-tools</h1> <p align="center"> <strong>Lint, secure, and manage <code>AGENTS.md</code> files — the open standard for AI coding agents.</strong> </p> <p align="center"> <a href="https://www.npmjs.com/package/agents-md-tools"><img src="https://img.shields.io/npm/v/agents-md-tools.svg?style=flat-square&color=6366f1" alt="npm version" /></a> <a href="https://www.npmjs.com/package/agents-md-tools"><img src="https://img.shields.io/npm/dm/agents-md-tools.svg?style=flat-square&color=10b981" alt="downloads" /></a> <a href="https://github.com/bysiber/agents-md-tools/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue.svg?style=flat-square" alt="license" /></a> <a href="https://github.com/bysiber/agents-md-tools/actions"><img src="https://img.shields.io/github/actions/workflow/status/bysiber/agents-md-tools/ci.yml?style=flat-square&label=CI" alt="CI" /></a> <a href="https://nodejs.org/en/"><img src="https://img.shields.io/badge/node-%3E%3D18-brightgreen.svg?style=flat-square" alt="node >= 18" /></a> </p> <p align="center"> <code>npx agents-md lint</code> — zero install, instant results. </p> --- > We scanned 74,688 `AGENTS.md` files on GitHub. **73% lack basic security boundaries.** No deny-lists, no scope definitions, no secret protections. Your AI agent can read, write, and delete anything — and the instructions file is the only thing between it and your `.env`. --- ## Demo <!-- TODO: Replace with actual asciinema recording --> <p align="center"> <img src="./assets/demo.gif" alt="agents-md lint demo" width="680" /> </p> ``` $ npx agents-md lint agents-md-tools v1.0.0 ✓ has-project-section +15 "## Project" heading found ✓ has-commands-section +15 "## Commands" heading found ✗ has-constraints-section 0 Missing "## Constraints" section ✓ has-runnable-test-command +10 Test command detected:
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.