Home › Rules › Discord bot

Discord bot rules: AGENTS.md, CLAUDE.md & Cursor rules

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

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

The two classic Discord bot disasters are a leaked token and a bot that asks for every permission. These rules stop both, and keep commands small.

Stack these rules assume: Node.js (LTS), discord.js v14, slash commands. 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: Discord bot

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: Node.js (LTS), discord.js v14, slash commands
- Version 1 only needs to: [the ONE thing it must do]

## Commands
- Install: `npm install`
- Register slash commands: `node deploy-commands.js`
- Start the bot: `node index.js`

## Project rules
- The bot token lives only in .env as DISCORD_TOKEN. Never paste it in code, logs, or chat. .env is in .gitignore.
- Use slash commands, one file per command in commands/. Re-run the deploy script when a command's name or options change.
- Request only the gateway intents the bot actually uses. Ask me before enabling privileged intents (Message Content, Server Members, Presence).
- Every command replies within 3 seconds, or calls deferReply() first for slow work.
- Catch errors in every command and reply with a short friendly message. Log the real error to the console.
- Add a cooldown to any command that calls an external API or costs money.

## 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

• Discord bot ruleThe bot token lives only in .env as DISCORD_TOKEN. Never paste it in code, logs, or chat. .env is in .gitignore.Why: Anyone with your token controls your bot. Discord resets leaked tokens, but only after the damage.
• Discord bot ruleUse slash commands, one file per command in commands/. Re-run the deploy script when a command's name or options change.Why: One file per command keeps changes small. Forgetting to re-register is the most common "my command doesn't show up" bug.
• Discord bot ruleRequest only the gateway intents the bot actually uses. Ask me before enabling privileged intents (Message Content, Server Members, Presence).Why: Privileged intents must be switched on in the Developer Portal, and bots in 100+ servers need Discord's approval for them.
• Discord bot ruleEvery command replies within 3 seconds, or calls deferReply() first for slow work.Why: Discord shows "The application did not respond" if an interaction isn't acknowledged in time.
• Discord bot ruleCatch errors in every command and reply with a short friendly message. Log the real error to the console.Why: One unhandled error shouldn't crash the whole bot for every server.
• Discord bot ruleAdd a cooldown to any command that calls an external API or costs money.Why: Someone will spam it. Cooldowns protect your rate limits and your wallet.
• 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 Discord bot
alwaysApply: true
---

# Discord bot

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: Node.js (LTS), discord.js v14, slash commands
- Version 1 only needs to: [the ONE thing it must do]

## Commands
- Install: `npm install`
- Register slash commands: `node deploy-commands.js`
- Start the bot: `node index.js`

## 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, **/*.ts
alwaysApply: false
---

# Project rules: Discord bot

- The bot token lives only in .env as DISCORD_TOKEN. Never paste it in code, logs, or chat. .env is in .gitignore.
- Use slash commands, one file per command in commands/. Re-run the deploy script when a command's name or options change.
- Request only the gateway intents the bot actually uses. Ask me before enabling privileged intents (Message Content, Server Members, Presence).
- Every command replies within 3 seconds, or calls deferReply() first for slow work.
- Catch errors in every command and reply with a short friendly message. Log the real error to the console.
- Add a cooldown to any command that calls an external API or costs money.

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 Discord bot (which tool to use, real prices)
• AGENTS.md, CLAUDE.md and Cursor rules formats explained