Home › Rules › Mobile app (Expo)

Mobile app (Expo) rules: AGENTS.md, CLAUDE.md & Cursor rules

Free to copy. File formats checked against the official docs on Oct 19, 2026 (sources).

• Mobile
• Claude Code
• OpenAI Codex
• Cursor
• GitHub Copilot

Mobile apps add two traps: packages that don't match your Expo SDK, and secrets shipped inside the app. These rules cover both.

Stack these rules assume: Expo (React Native), TypeScript, Expo Router, tested in Expo Go. Different stack? Customize it in the generator.

Quick start

1. Copy the AGENTS.md below into your project's root folder.
2. Fill in the three [bracketed] lines under "Project". Delete any rule that doesn't fit.
3. Start your first chat with: "Read AGENTS.md and follow it for this whole session."

AGENTS.md (works across tools)

Read by OpenAI Codex, Cursor, GitHub Copilot, Claude Code (when there's no CLAUDE.md) and many other agents.

# AGENTS.md: Mobile app (Expo)

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: Expo (React Native), TypeScript, Expo Router, tested in Expo Go
- Version 1 only needs to: [the ONE thing it must do]

## Commands
- Create the project: `npx create-expo-app@latest`
- Start the dev server: `npx expo start`
- Add a package (picks a compatible version): `npx expo install <package>`

## Project rules
- Install packages with npx expo install, not npm install, so versions match our Expo SDK.
- Screens live in the app/ folder (Expo Router file-based routes). One screen per file.
- Anything in the app bundle is public, including EXPO_PUBLIC_ variables. Secret keys stay on a server.
- Stick to packages that work in Expo Go for v1. Ask before adding anything that needs a development build.
- Test each change on a real phone with Expo Go, and say what to tap to check it.
- Handle loading and error states on every screen that fetches data.

## 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.

Why each rule exists

• Mobile app (Expo) ruleInstall packages with npx expo install, not npm install, so versions match our Expo SDK.Why: Mismatched native package versions are the top cause of mysterious crashes in Expo apps.
• Mobile app (Expo) ruleScreens live in the app/ folder (Expo Router file-based routes). One screen per file.Why: File-based routing means the folder structure is the navigation. Keep it predictable.
• Mobile app (Expo) ruleAnything in the app bundle is public, including EXPO_PUBLIC_ variables. Secret keys stay on a server.Why: People can unpack an app and read every string in it.
• Mobile app (Expo) ruleStick to packages that work in Expo Go for v1. Ask before adding anything that needs a development build.Why: Expo Go lets you test on your phone in seconds. Native modules mean custom builds and longer loops.
• Mobile app (Expo) ruleTest each change on a real phone with Expo Go, and say what to tap to check it.Why: Simulators hide real-world problems like keyboard overlap and small screens.
• Mobile app (Expo) ruleHandle loading and error states on every screen that fetches data.Why: Phone networks are flaky. A blank screen looks like a crash.
• How to workDo one task per request. If my request is really several tasks, list them and do only the first.Why: Big multi-part requests are where AI tools change 12 files and you can't tell which change broke things.
• How to workBefore writing code, give a 3-line plan: what you'll change, which files, and how I'll test it.Why: A plan you can read in 10 seconds catches the wrong approach before it costs you an hour or a pile of credits.
• How to workMake the smallest change that works. Don't refactor, rename, or reformat code I didn't ask about.Why: Drive-by "cleanups" are the #1 cause of "it was working yesterday".
• How to workAsk before adding a dependency, deleting or moving files, changing the data/database structure, or touching more than 3 files.Why: These are the changes that are hard to undo. One quick question is cheaper than a rollback.
• How to workIf 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.Why: AI tools confidently invent functions and config options. Making it check is the cure.
• How to workNever say something works unless you ran it or I confirmed it. Report errors exactly.Why: "Should work now" isn't a test result. You want facts, not optimism.
• How to workSecrets (API keys, tokens, passwords) live only in environment variables or a .env file listed in .gitignore. Never print, hardcode, or commit them.Why: Leaked keys get found by bots within minutes of a public push. This rule is the cheapest insurance you'll ever buy.
• How to workNever run destructive commands (rm -rf, git reset --hard, force-push, dropping tables) without asking first.Why: One bad command can delete the only copy of your work.
• Finish every task withWhat changed, how to test it, and a commit message.Why: This turns every task into a checkpoint: you test it, you commit it, and you always have a last good version to go back to.

Use it as CLAUDE.md (Claude Code)

Pick one:

1. Do nothing. Current Claude Code versions read AGENTS.md when the project has no CLAUDE.md. Run /memory in a session to check it loaded.
2. Import it (best if you want Claude-only extras, or you're on an older Claude Code). Create CLAUDE.md next to AGENTS.md:

@AGENTS.md

## Claude Code
- Use plan mode before any change that touches more than 3 files.

3. Claude only? Save the same AGENTS.md text as CLAUDE.md instead. Don't keep two separate copies; they drift apart.

Heads-up: if a project has both files and CLAUDE.md doesn't import AGENTS.md, Claude Code reads only CLAUDE.md by default. More in AGENTS.md vs CLAUDE.md.

Use it as Cursor rules (.cursor/rules/*.mdc)

Cursor reads AGENTS.md too, so the file above already works. If you prefer Cursor's own Project Rules, split it into two .mdc files. The .mdc extension and frontmatter are required; Cursor ignores plain .md files in .cursor/rules.

---
description: Project overview and working rules for Mobile app (Expo)
alwaysApply: true
---

# Mobile app (Expo)

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: Expo (React Native), TypeScript, Expo Router, tested in Expo Go
- Version 1 only needs to: [the ONE thing it must do]

## Commands
- Create the project: `npx create-expo-app@latest`
- Start the dev server: `npx expo start`
- Add a package (picks a compatible version): `npx expo install <package>`

## 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.

The project rules only attach when a matching file is in the chat (globs with alwaysApply: false). Want them on all the time? Change it to alwaysApply: true.

---
globs: app/**/*.tsx, components/**/*.tsx, **/*.ts
alwaysApply: false
---

# Project rules: Mobile app (Expo)

- Install packages with npx expo install, not npm install, so versions match our Expo SDK.
- Screens live in the app/ folder (Expo Router file-based routes). One screen per file.
- Anything in the app bundle is public, including EXPO_PUBLIC_ variables. Secret keys stay on a server.
- Stick to packages that work in Expo Go for v1. Ask before adding anything that needs a development build.
- Test each change on a real phone with Expo Go, and say what to tap to check it.
- Handle loading and error states on every screen that fetches data.

Use either AGENTS.md or these .mdc files, not both, so you don't send the same rules twice. See Cursor rules vs AGENTS.md.

Related

• AGENTS.md, CLAUDE.md and Cursor rules formats explained