Free AGENTS.md / CLAUDE.md / Cursor rules generator
Pick your project and your tool, flip the switches, and copy a ready rules file. Runs entirely in your browser; nothing you type is sent anywhere.
# AGENTS.md: Browser game (Phaser)
Instructions for AI coding agents working on this project. Replace anything in [brackets].
## Project
- What it is: [one sentence: what you are building and who it is for]
- Stack: Phaser 3 + Vite, JavaScript or TypeScript, runs in the browser
- Version 1 only needs to: [the ONE thing it must do]
## Commands
- Create the project (official Phaser starter): `npm create @phaserjs/game@latest`
- Install: `npm install`
- Run locally: `npm run dev`
- Production build: `npm run build`
## Project rules
- Keep each scene in its own file under src/scenes/ (or wherever the starter put them). Don't merge scenes.
- Add one mechanic per task (movement, then jumping, then enemies). After each one, the game must still start and be playable.
- Put tunable numbers (speed, gravity, spawn rate, lives) in one config object at the top of the scene or in a config file.
- Load assets in preload() with clear keys. If an asset file is missing, use a colored rectangle placeholder and tell me.
- Use the Phaser version that's in package.json. Don't use Phaser 2/CE examples or APIs.
- Don't add a physics engine, state library, or framework unless I ask. Use Phaser's built-in Arcade Physics.
## How to work
- Do one task per request. If my request is really several tasks, list them and do only the first.
- Before writing code, give a 3-line plan: what you'll change, which files, and how I'll test it.
- Make the smallest change that works. Don't refactor, rename, or reformat code I didn't ask about.
- Ask before adding a dependency, deleting or moving files, changing the data/database structure, or touching more than 3 files.
- If you're not sure a library, API, or setting exists in the version we use, say so and check the installed package or the docs instead of guessing.
- Never say something works unless you ran it or I confirmed it. Report errors exactly.
- Secrets (API keys, tokens, passwords) live only in environment variables or a .env file listed in .gitignore. Never print, hardcode, or commit them.
- Never run destructive commands (rm -rf, git reset --hard, force-push, dropping tables) without asking first.
## Finish every task with
1. What changed (list the files).
2. How to run or test it in under a minute, and what I should see.
3. A suggested git commit message.
Got it. Next step:
Step-by-step kits Our paid templates ($6 to $9) add a full prompt sequence and a worked example on top of rules like these.
Browse the kits → See what's inside
or get all 5 kits for $25 (save $14) →
Or get the free Starter Rules (rules file + kickoff prompt) by email: sign up below.
Want the reasoning behind each rule? Every project has a full page in the rules library. Not sure which file your tool reads? See formats explained.
Get the free Starter Rules, emailed instantly
- A copy-paste rules file to save as AGENTS.md or CLAUDE.md, or paste into Lovable, Bolt, v0 or Replit: small steps, ask before risky changes, no fake "it works", secrets kept out of code.
- A kickoff prompt that makes your AI ask up to 3 questions and plan 5 to 8 small, testable steps before it writes any code.
- The habit that saves projects: work, test, commit.
After that, an occasional email when we publish a new guide or rules file.
Free. No spam. Unsubscribe anytime. See our privacy note.