A Markdown file in your repo that tells coding agents how to work there: setup and test commands, code style, PR rules, and what not to touch. OpenAI Codex reads it, and so do Cursor, GitHub Copilot, Google Jules, Amp, and other agents. Think of it as a README written for agents.

What does the review check?

Whether setup, build, test, and lint commands are present and runnable, whether monorepo packages need their own nested AGENTS.md, PR and commit conventions, boundaries for generated code, migrations, and secrets, vague rules, token bloat, and Claude Code-only syntax that other agents ignore. You get 5-10 numbered fixes and 1-3 rewritten paragraphs.

How do nested AGENTS.md files work in a monorepo?

Put an AGENTS.md inside each package that has its own commands or rules. Agents use the file closest to the code they are editing, so package rules stay out of the root file and out of unrelated tasks. The reviewer flags root-file rules that only apply to one package.

AGENTS.md vs CLAUDE.md: do I need both?

Claude Code reads CLAUDE.md. Codex and many other agents read AGENTS.md. Keep one source of truth: generate the other file with the CLAUDE.md Converter, or have CLAUDE.md import AGENTS.md. Review CLAUDE.md with the CLAUDE.md Reviewer and AGENTS.md here.

AGENTS.md Reviewer

AGENTS.md is the open instruction file that OpenAI Codex reads, and Cursor, GitHub Copilot, Google Jules, Amp, and other coding agents read it too. Agents re-read it on every task, so a missing test command or a vague rule costs you on every run. Paste your AGENTS.md and get a numbered audit: setup, build, test, and lint commands that are missing or not runnable, rules that belong in a nested AGENTS.md inside a monorepo package, missing PR and commit conventions, files agents must not touch, vague lines, token bloat, and Claude Code-only syntax (@imports, slash commands, hooks) that other agents ignore. The review ends with 1-3 rewritten paragraphs you can paste in. Starting from a Claude Code file? Review it with the CLAUDE.md Reviewer, then produce AGENTS.md with the CLAUDE.md Converter. Writing a Claude Agent Skill? Use the SKILL.md Reviewer.

AI-powered. Paste the AGENTS.md that Codex, Cursor, Copilot, Jules, and Amp read, and get a numbered audit plus rewritten paragraphs. No login. Daily-capped to stay free.

Try an example AGENTS.md

Paste your AGENTS.md

0 / 20,000 chars

Review & suggestions

Numbered, specific suggestions will appear here after you click Review.

Convert between formatsAGENTS.md, CLAUDE.md, Cursor, Copilot Review a CLAUDE.mdThe Claude Code version of this audit Review a SKILL.mdClaude Agent Skills

What gets reviewed

• Setup, build, test, and lint commands that actually run
• Nested AGENTS.md scoping for monorepo packages
• PR title, commit, and branch conventions
• Files and actions agents must not touch
• Vague rules and token bloat
• Claude-only syntax other agents ignore

Inputs to AI tools may be used to improve MarkdownMe. Data controls

Was this rewrite usable?

Get new tools by email

We add tools most weeks. Give an email address and we send you the new ones, plus short notes on how to use them. No more than one email a week. Unsubscribe with one click.

Example Input and Output

An AGENTS.md with prose instead of commands

AGENTS.md

# AGENTS.md

This is our web app. Keep the code clean.

Make sure all the tests pass before you finish.

See @docs/architecture.md for context.

Audit

1. Missing commands. "Make sure all the tests pass" names no command, so the agent guesses. Add a Testing section with the exact command, e.g. `TEST_COMMAND`.
2. Vague rule. "Keep the code clean" changes no behavior and is re-read on every task. Delete it or replace it with a concrete rule (formatter, lint command).
3. Claude-only syntax. `@docs/architecture.md` is a Claude Code import; Codex and Cursor read it as plain text. Write "Read docs/architecture.md before changing module boundaries."

Rewritten paragraph:
## Testing
- Run `TEST_COMMAND` and fix failures before you finish.
- Read docs/architecture.md before changing module boundaries.

Each finding names the line, why it fails for non-Claude agents, and the fix. Values the file never states stay as placeholders.

How to Use AGENTS.md Reviewer

Open the AGENTS.md Reviewer
Paste your AGENTS.md or pick an example
Run the AI review
Apply the numbered fixes and paste in the rewritten paragraphs
Move package-only rules into nested AGENTS.md files if the review flags them

Frequently Asked Questions

What is AGENTS.md?: A Markdown file in your repo that tells coding agents how to work there: setup and test commands, code style, PR rules, and what not to touch. OpenAI Codex reads it, and so do Cursor, GitHub Copilot, Google Jules, Amp, and other agents. Think of it as a README written for agents.
What does the review check?: Whether setup, build, test, and lint commands are present and runnable, whether monorepo packages need their own nested AGENTS.md, PR and commit conventions, boundaries for generated code, migrations, and secrets, vague rules, token bloat, and Claude Code-only syntax that other agents ignore. You get 5-10 numbered fixes and 1-3 rewritten paragraphs.
How do nested AGENTS.md files work in a monorepo?: Put an AGENTS.md inside each package that has its own commands or rules. Agents use the file closest to the code they are editing, so package rules stay out of the root file and out of unrelated tasks. The reviewer flags root-file rules that only apply to one package.
AGENTS.md vs CLAUDE.md: do I need both?: Claude Code reads CLAUDE.md. Codex and many other agents read AGENTS.md. Keep one source of truth: generate the other file with the CLAUDE.md Converter, or have CLAUDE.md import AGENTS.md. Review CLAUDE.md with the CLAUDE.md Reviewer and AGENTS.md here.

Claude Code tools

One CLAUDE.md, reviewed, generated, converted, and costed. Start at the hub for the guides.

CLAUDE.md reviewer — A numbered audit of an existing CLAUDE.md: vague rules, missing commands, token waste.
CLAUDE.md generator — Create a CLAUDE.md from your stack, commands, and conventions.
CLAUDE.md to AGENTS.md converter — The same instructions for Codex, Cursor, Copilot, and Windsurf.
SKILL.md reviewer — Audit a Claude Agent Skill: frontmatter, trigger description, and steps.
All Claude Code tools — The hub: every CLAUDE.md tool and guide on one page.

Related Tools

CLAUDE.md Converter

Convert agent configs between CLAUDE.md, AGENTS.md, .cursorrules, .github/copilot-instructions.md, and .windsurfrules. One file, every format.

CLAUDE.md Reviewer

Paste your existing CLAUDE.md and get specific, numbered suggestions for vague rules, missing commands, repo boundaries, and token waste.

SKILL.md Reviewer

Paste a Claude Agent Skill's SKILL.md and get numbered fixes for the frontmatter, the trigger description, the instructions, and the file layout.

CLAUDE.md Generator

Describe your project in 1-2 sentences and get a structured CLAUDE.md. AI-powered. Free, no login.

About AGENTS.md Reviewer

Paste your AGENTS.md and get numbered fixes for missing commands, monorepo scoping, PR rules, agent boundaries, vague rules, and token bloat. This AI-backed tool sends your input to MarkdownMe's capped AI endpoint to generate the result. You choose whether we keep it to improve the tools. See the privacy page. No account is required. MarkdownMe provides free, fast, and reliable Markdown tools for developers, writers, and anyone who works with Markdown.