# AGENTS.md, CLAUDE.md and Cursor rules starter files

> Six fill-in instruction files for coding agents (base, Next.js plus Supabase, FastAPI, browser game, CLAUDE.md pointer, scoped Cursor rules) and 8 prompts to write, trim and test your own.

- URL: https://paperchasewebb.ai/bots/marketplace/items/agents-md-claude-md-and-cursor-rules-starter-files/
- Type: Prompt pack
- Category: Vibe coding
- By: PaperChaseWebb
- Works with: Claude Code, Codex, Cursor (named in the listing); Plain .md
- Price: $14 USD
- Difficulty: Beginner
- Setup time: 20 min
- Time to result: A working AGENTS.md in under an hour
- Format: Markdown (.md) file, agents-md-claude-md-and-cursor-rules-starter-files.md
- Version: 1.0, updated 2026-10-15
- License: Personal and commercial use by the buyer. No resale, redistribution or republishing as a competing pack. See Downloads in the terms.

## What you end up with

One short instructions file your agents actually follow, with exact commands, clear limits and no three-way disagreement between tools.

## What you get

- Six starter files with [placeholders], written from scratch for this pack
- A one-source layout: AGENTS.md as the source, CLAUDE.md importing it, scoped Cursor rules
- 8 prompts: draft from an existing repo, trim, merge files that disagree, test against real tasks, review after a bad session
- A ten-point quality check for any instructions file

## Who it is for

Anyone using more than one coding agent on the same repo, or whose agent keeps guessing the test command, adding dependencies and editing files it should leave alone.

## Tools needed

- Codex, Claude Code, Cursor or any tool that reads AGENTS.md: follows the instructions file
- Your repo: the commands and paths the file must match
- You need: A project with at least a package file or README the agent can read

Cost to run: Free. Uses the coding agent you already have.

## Sample prompt: Write AGENTS.md from an existing repo (Codex, Claude Code or Cursor)

```
Do not edit any files except the one I ask you to create.
Read package files, config files, CI workflows, the README and a sample of source files in this repo.
Draft AGENTS.md using this structure: Project, Commands, Layout, How to work, Ask before you, Never, Done means.
Rules:
- Every command must appear in package scripts, a Makefile, CI or the README. Do not invent commands.
- Mark anything you inferred rather than read with (inferred).
- Under 150 lines.
- List at the end any questions I should answer to finish the file.
```

The (inferred) marker is what makes the draft safe to trust. Check those lines first.

## Sample prompt: Test the file against real tasks (Any coding agent)

```
Read AGENTS.md. Do not edit any code.
For each of these tasks, describe step by step what you would do, which files you would touch, which commands you would run and which rules in AGENTS.md apply:
1. [a small bug fix you did recently]
2. [a feature that touches the database]
3. [adding a dependency]
Then list any point where AGENTS.md did not tell you what to do, or where two rules pulled in different directions.
```

Run this every time you change the file. The gaps it finds are the next lines worth adding.

## Free preview of agents-md-claude-md-and-cursor-rules-starter-files.md

````markdown
# AGENTS.md, CLAUDE.md and Cursor rules starter files

PaperChase prompt pack, version 1.0. Six fill-in starter files, a layout that keeps them in sync, and 8 prompts that write, trim and test your agent instructions. For Codex, Claude Code, Cursor and any tool that reads AGENTS.md.

## What problem this solves

Coding agents read an instructions file before they touch your repo. Most of those files are either empty, a copy of someone else's 400-line rule dump, or three different files that disagree with each other. The agent then guesses your test command, adds a dependency you did not want and "fixes" a file it should never edit.

A good instructions file is short, specific to your repo and written as rules the agent can follow and you can check.

## The layout this pack uses

One source of truth, thin pointers for each tool:

```
AGENTS.md                 the real instructions (Codex, Cursor and others read it)
CLAUDE.md                 one line: @AGENTS.md, plus anything Claude Code specific
.cursor/rules/            optional scoped rules for Cursor, one topic per file
  security.mdc
  tests.mdc
apps/web/AGENTS.md        optional, only if this folder has different rules
```

Claude Code supports importing another file into CLAUDE.md with an @path line, so you write the rules once. Nested AGENTS.md files apply to their folder; the closest one to the file being edited takes priority.

## Contents

1. Base AGENTS.md (any stack)
2. Next.js plus Supabase variant
3. Python FastAPI variant
4. Browser game variant (Phaser or Three.js)
5. CLAUDE.md pointer file
6. Cursor scoped rules: security, tests, UI
7. Prompts: write from an existing repo, trim, test against real tasks, review after a bad session
8. A ten-point quality check for any instructions file
````

## Worth knowing

- Instruction files guide agents; they do not enforce anything. Review diffs.
- File names, import syntax and rule headers change between tool versions. Check your tool's docs if a file seems ignored.
- The starters are a base to edit, not a drop-in. Delete lines that do not apply to your repo.

## Questions

**Why AGENTS.md as the main file?** Codex, Cursor and a growing list of tools read it, and Claude Code can import it into CLAUDE.md with one line. Writing the rules once avoids files that drift apart.

**Can I use these in client projects?** Yes. Use and edit them in your own and your clients' repos. What you cannot do is resell or republish the pack itself.

## How to buy

$14 one time at https://paperchasewebb.ai/bots/marketplace/items/agents-md-claude-md-and-cursor-rules-starter-files/. Stripe checkout, then an instant download page; the download link is also in your emailed receipt.

Seller: PaperChaseWebb Inc., mgmt@paperchasewebb.com