Bolt.new app rules: Project Knowledge template + AGENTS.md
Bolt's pricing FAQ says most token use comes from syncing your project's files to the AI, so the bigger the project, the more each message costs. These rules keep prompts small and changes targeted.
Stack these rules assume: Bolt (web app or site), using Bolt Database by default. Different stack? Customize it in the generator.
Where these go: Paste the Bolt version into Project settings → Knowledge. Rules for all your projects can go in your account-level knowledge.
Want the full step-by-step kit?
MVP Spec-to-Build Pack ($7): A fill-in 1-page spec, a landing page prompt, a 7-prompt build sequence in the right order, a "did I leak user data?" checklist, and cheap fix-it prompts.
Get the kit for $7 on Gumroad → See what's inside
or get all 5 kits for $25 (save $14) →
One markdown file, instant download. 7-day refund, no questions asked.
Quick start
- Copy the Project Knowledge below.
- In Bolt, open Project settings → Knowledge and paste it.
- Fill in the
[bracketed]lines. Delete any rule that doesn't fit. - Start your next message with: "Follow the project knowledge for this whole session."
Project Knowledge for Bolt (copy this)
Paste it into Project settings → Knowledge. It also works as-is in Lovable's Project Knowledge. It skips the Commands section, since the builder runs the project for you.
# Project rules: Bolt.new app
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: Bolt (web app or site), using Bolt Database by default
- Version 1 only needs to: [the ONE thing it must do]
## Project rules
- One feature or fix per message. If I ask for several, list them and build only the first.
- For anything bigger than a small change, outline the plan first and don't build until I say go.
- Only edit the files the change needs. Leave locked files alone and tell me if a change needs one of them.
- Use Bolt Database unless I say otherwise. Ask before switching databases or adding a new backend service.
- Secret keys live in the project's secrets and server functions, never in front-end code.
- If something breaks, explain the cause in one sentence before fixing it. Don't try the same fix twice.
## 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.
Building this in a browser app builder? These rules work as Project Knowledge in both. Try Bolt · Try Lovable
Disclosure: the Bolt link is an affiliate (referral) link. If you sign up or buy through it, VibeKits may earn a commission at no extra cost to you. The Lovable link is a plain link. It never changes our pick.
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: Bolt.new app
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: Bolt (web app or site), using Bolt Database by default
- Version 1 only needs to: [the ONE thing it must do]
## Project rules
- One feature or fix per message. If I ask for several, list them and build only the first.
- For anything bigger than a small change, outline the plan first and don't build until I say go.
- Only edit the files the change needs. Leave locked files alone and tell me if a change needs one of them.
- Use Bolt Database unless I say otherwise. Ask before switching databases or adding a new backend service.
- Secret keys live in the project's secrets and server functions, never in front-end code.
- If something breaks, explain the cause in one sentence before fixing it. Don't try the same fix twice.
## 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 the full step-by-step kit?
MVP Spec-to-Build Pack ($7): A fill-in 1-page spec, a landing page prompt, a 7-prompt build sequence in the right order, a "did I leak user data?" checklist, and cheap fix-it prompts.
Get the kit for $7 on Gumroad → See what's inside
or get all 5 kits for $25 (save $14) →
One markdown file, instant download. 7-day refund, no questions asked.
Why each rule exists
- Bolt.new app ruleOne feature or fix per message. If I ask for several, list them and build only the first.Why: Bolt's own prompting guide says the same thing: make one change, check it works, then move on.
- Bolt.new app ruleFor anything bigger than a small change, outline the plan first and don't build until I say go.Why: Bolt has a Plan Mode for this, or you can start a message with "Don't make any changes" to just talk it through. Planning costs far less than rebuilding.
- Bolt.new app ruleOnly edit the files the change needs. Leave locked files alone and tell me if a change needs one of them.Why: Bolt lets you lock files and target specific ones. This rule makes the agent respect that intent everywhere.
- Bolt.new app ruleUse Bolt Database unless I say otherwise. Ask before switching databases or adding a new backend service.Why: Bolt's docs say switching from Bolt Database to Supabase later takes extra steps.
- Bolt.new app ruleSecret keys live in the project's secrets and server functions, never in front-end code.Why: Anything in front-end code can be read by every visitor.
- Bolt.new app ruleIf something breaks, explain the cause in one sentence before fixing it. Don't try the same fix twice.Why: Repeated fix attempts on a big project eat tokens fast.
- 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 Bolt.new app
alwaysApply: true
---
# Bolt.new app
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: Bolt (web app or site), using Bolt Database by default
- 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.
---
globs: src/**/*.tsx, src/**/*.ts
alwaysApply: false
---
# Project rules: Bolt.new app
- One feature or fix per message. If I ask for several, list them and build only the first.
- For anything bigger than a small change, outline the plan first and don't build until I say go.
- Only edit the files the change needs. Leave locked files alone and tell me if a change needs one of them.
- Use Bolt Database unless I say otherwise. Ask before switching databases or adding a new backend service.
- Secret keys live in the project's secrets and server functions, never in front-end code.
- If something breaks, explain the cause in one sentence before fixing it. Don't try the same fix twice.
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 build a web app MVP (which tool to use, real prices)
- 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].