CLAUDE.md Converter

Example Input and Output

# Project

Next.js 16 static export.

## Commands

- `npm run build` before every commit

## Rules

- Do not edit backend/
- Use Tailwind, not CSS modules

Run npm run build before every commit.
Do not edit backend/.
Use Tailwind, not CSS modules.

How to Use CLAUDE.md Converter

1. Open the CLAUDE.md Converter
2. Paste your CLAUDE.md, AGENTS.md, or raw rules
3. Pick the target: AGENTS.md, .cursorrules, copilot-instructions.md, or .windsurfrules
4. Copy or download the converted file and commit it to the repo

Frequently Asked Questions

What is CLAUDE.md?

CLAUDE.md is the project instruction file that Claude Code reads at the start of every session. It sits in the repo root or in .claude/. It tells the agent the stack, the commands to run, the file boundaries, and the rules to follow. Other agents use the same idea under different names: AGENTS.md for Codex, .cursorrules for Cursor, .windsurfrules for Windsurf.

What should a CLAUDE.md contain?

Keep it short and concrete. Name the project and stack. List the build, test, and deploy commands. Name the folders the agent may and may not edit. State the style rules and the do-not rules. Skip general advice the model already knows. Run the CLAUDE.md Reviewer to find lines that cost tokens without changing behavior.

CLAUDE.md vs AGENTS.md: what is the difference?

Both are Markdown instruction files for a coding agent. CLAUDE.md is read by Claude Code. AGENTS.md is the open convention read by OpenAI Codex and many other agents. The content overlaps almost fully, so this converter maps one to the other and adds the preamble each tool expects.

What formats does this convert between?

Five agent config formats: CLAUDE.md (Claude Code), AGENTS.md (OpenAI Codex and other agents), .cursorrules (Cursor), .github/copilot-instructions.md (GitHub Copilot), and .windsurfrules (Windsurf). Paste any input, pick your target.

How is the conversion different per format?

Markdown-based targets (CLAUDE.md, AGENTS.md, copilot-instructions.md) keep the heading structure and add a format-appropriate preamble. Flat rule files (.cursorrules, .windsurfrules) extract imperative rules and drop prose, since Cursor and Windsurf work better with terse rule lists.

Do I need to edit the output?

Usually a quick review — each agent tool has quirks. For Cursor, keep rules imperative and under 2 lines each. For Copilot, first-person voice works best. For CLAUDE.md, include concrete commands. The output gets you 80% there; polish the rest.

Does it work with YAML frontmatter?

Yes. Frontmatter is preserved for markdown-based targets (CLAUDE.md, AGENTS.md, copilot-instructions.md) and dropped for flat rule files which don't support it.

Is this Karpathy-Skills or claude-doctor compatible?

Yes. Paste output from either and convert to your preferred format. The converter doesn't add behavioral rules itself — it restructures what you paste in. If you want a behavioral baseline, paste a known-good CLAUDE.md and convert down.

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.
• All Claude Code tools — The hub: every CLAUDE.md tool and guide on one page.