Home › Rules › Chrome extension

Chrome extension rules: AGENTS.md, CLAUDE.md & Cursor rules

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

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

Chrome extensions get rejected or break for two reasons: too many permissions and old Manifest V2 code. These rules handle both.

Stack these rules assume: Manifest V3, plain JavaScript, content scripts + service worker. 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: Chrome extension

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: Manifest V3, plain JavaScript, content scripts + service worker
- Version 1 only needs to: [the ONE thing it must do]

## Commands
- Load it in Chrome: chrome://extensions → turn on Developer mode → Load unpacked → pick the project folder
- Reload after changes: Click the reload icon on the extension card, then refresh the page you're testing

## Project rules
- Use Manifest V3 only. Background logic goes in a service worker, not a background page.
- Request the fewest permissions possible. Explain each permission and host permission in one line before adding it.
- All code ships inside the extension. Don't load remote scripts or use eval().
- Content scripts must handle pages that load content dynamically (use a MutationObserver when needed).
- Store settings with chrome.storage, not localStorage.
- After each change, tell me exactly what to reload and which page to test on.

## 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

• Chrome extension ruleUse Manifest V3 only. Background logic goes in a service worker, not a background page.Why: Manifest V2 is no longer supported in Chrome, but a lot of example code online is still V2.
• Chrome extension ruleRequest the fewest permissions possible. Explain each permission and host permission in one line before adding it.Why: Every permission shows up as a scary warning to users and slows down store review.
• Chrome extension ruleAll code ships inside the extension. Don't load remote scripts or use eval().Why: Manifest V3 doesn't allow remotely hosted code. It's a guaranteed review problem.
• Chrome extension ruleContent scripts must handle pages that load content dynamically (use a MutationObserver when needed).Why: Sites like YouTube change the page without reloading it. Code that only runs once "works" for exactly one page.
• Chrome extension ruleStore settings with chrome.storage, not localStorage.Why: chrome.storage is available to the service worker and syncs across the user's devices if you use sync.
• Chrome extension ruleAfter each change, tell me exactly what to reload and which page to test on.Why: Half of "it doesn't work" with extensions is a stale version still running.
• 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 Chrome extension
alwaysApply: true
---

# Chrome extension

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: Manifest V3, plain JavaScript, content scripts + service worker
- Version 1 only needs to: [the ONE thing it must do]

## Commands
- Load it in Chrome: chrome://extensions → turn on Developer mode → Load unpacked → pick the project folder
- Reload after changes: Click the reload icon on the extension card, then refresh the page you're testing

## 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: **/*.js, manifest.json
alwaysApply: false
---

# Project rules: Chrome extension

- Use Manifest V3 only. Background logic goes in a service worker, not a background page.
- Request the fewest permissions possible. Explain each permission and host permission in one line before adding it.
- All code ships inside the extension. Don't load remote scripts or use eval().
- Content scripts must handle pages that load content dynamically (use a MutationObserver when needed).
- Store settings with chrome.storage, not localStorage.
- After each change, tell me exactly what to reload and which page to test on.

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

• Best AI tool to make a Chrome extension (which tool to use, real prices)
• AGENTS.md, CLAUDE.md and Cursor rules formats explained