Home › Rules › Replit Agent app (replit.md)
replit.md template: rules for Replit Agent
Replit Agent reads a file called replit.md in your project root, and it may rewrite that file as it learns. These rules go in there so they stick, plus one rule that stops Agent from quietly dropping them.
Stack these rules assume: Replit Agent (web apps, bots, scripts, APIs), with persistent rules in replit.md. Different stack? Customize it in the generator.
Where these go: Add the replit.md section below to replit.md in your project root (Agent usually creates one; you can edit it or create it yourself). Rules for every project go in your Workspace custom instructions.
Quick start
- Copy the replit.md section below.
- Paste it at the end of
replit.mdin your project root. - Fill in the
[bracketed]lines. - Tell Agent: "Read replit.md and follow the VibeKits rules section."
replit.md section (copy this)
Open replit.md in your project root and paste this at the end. No file yet? Create replit.md in the root folder (Agent won't find it in a subfolder).
## VibeKits rules (keep this section)
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: Replit Agent (web apps, bots, scripts, APIs), with persistent rules in replit.md
- Version 1 only needs to: [the ONE thing it must do]
### Project rules
- Keep this "VibeKits rules" section when you update replit.md. Don't shorten, summarize, or remove it.
- One task per request. For anything bigger than a small fix, show a short plan first.
- Before anything that costs extra (more powerful models, paid modes, or new paid services), tell me why it's needed.
- Secrets go in Replit's Secrets, never in code or in replit.md.
- Ask before changing the database schema or deleting data, and tell me if a change can't be undone.
- After each change, tell me how to check it in the preview and what I should see.
### 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.
Replit's referral program pays in Replit credits, not cash, so this is a plain link: replit.com.
AGENTS.md (if you sync to GitHub or work locally)
Same rules as a file, for when you export the code or keep editing it in Cursor, Codex, Copilot or Claude Code.
# AGENTS.md: Replit Agent app (replit.md)
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: Replit Agent (web apps, bots, scripts, APIs), with persistent rules in replit.md
- Version 1 only needs to: [the ONE thing it must do]
## Project rules
- Keep this "VibeKits rules" section when you update replit.md. Don't shorten, summarize, or remove it.
- One task per request. For anything bigger than a small fix, show a short plan first.
- Before anything that costs extra (more powerful models, paid modes, or new paid services), tell me why it's needed.
- Secrets go in Replit's Secrets, never in code or in replit.md.
- Ask before changing the database schema or deleting data, and tell me if a change can't be undone.
- After each change, tell me how to check it in the preview and what I should see.
## 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.
Want a step-by-step kit?
Our paid templates ($6 to $9) add a full prompt sequence and a worked example on top of rules like these, for games, Discord bots, email triage, MVPs and fixing messy code.
Why each rule exists
- Replit Agent app (replit.md) ruleKeep this "VibeKits rules" section when you update replit.md. Don't shorten, summarize, or remove it.Why: Replit's docs say Agent may update replit.md as it learns, and summarizes it when it grows. This protects your rules.
- Replit Agent app (replit.md) ruleOne task per request. For anything bigger than a small fix, show a short plan first.Why: Small steps mean you always know which change broke what.
- Replit Agent app (replit.md) ruleBefore anything that costs extra (more powerful models, paid modes, or new paid services), tell me why it's needed.Why: Replit asks before paid work starts. A one-line reason helps you say yes or no.
- Replit Agent app (replit.md) ruleSecrets go in Replit's Secrets, never in code or in replit.md.Why: replit.md is a plain file in your project. Anyone who can see the project can read it.
- Replit Agent app (replit.md) ruleAsk before changing the database schema or deleting data, and tell me if a change can't be undone.Why: Replit's docs list database restore windows on paid plans (7 days on Core, 28 on Pro). Treat them as a last resort, not a plan.
- Replit Agent app (replit.md) ruleAfter each change, tell me how to check it in the preview and what I should see.Why: You test it, you trust it.
- 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:
- Do nothing. Current Claude Code versions read
AGENTS.mdwhen the project has noCLAUDE.md. Run/memoryin a session to check it loaded. - Import it (best if you want Claude-only extras, or you're on an older Claude Code). Create
CLAUDE.mdnext toAGENTS.md:
@AGENTS.md
## Claude Code
- Use plan mode before any change that touches more than 3 files.
- Claude only? Save the same AGENTS.md text as
CLAUDE.mdinstead. 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 Replit Agent app (replit.md)
alwaysApply: true
---
# Replit Agent app (replit.md)
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: Replit Agent (web apps, bots, scripts, APIs), with persistent rules in replit.md
- Version 1 only needs to: [the ONE thing it must do]
## 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.
---
description: Project rules for Replit Agent app (replit.md)
alwaysApply: true
---
# Project rules: Replit Agent app (replit.md)
- Keep this "VibeKits rules" section when you update replit.md. Don't shorten, summarize, or remove it.
- One task per request. For anything bigger than a small fix, show a short plan first.
- Before anything that costs extra (more powerful models, paid modes, or new paid services), tell me why it's needed.
- Secrets go in Replit's Secrets, never in code or in replit.md.
- Ask before changing the database schema or deleting data, and tell me if a change can't be undone.
- After each change, tell me how to check it in the preview and what I should see.
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
- Lovable vs Bolt vs Replit for beginners (honest picks, real prices)
- AGENTS.md, CLAUDE.md and Cursor rules formats explained
Sources
Checked Oct 19, 2026. These tools change often; if something here no longer matches, tell us at [email protected].