Prompt · Code & Agents

Project Rules Interview (AGENTS.md, CLAUDE.md, Cursor)

Answer five questions in chat and get one AGENTS.md that every coding agent reads, plus thin CLAUDE.md and Cursor rule files only where you need them, with every rule checkable against a diff.

Paid

Version 3Updated 15 Oct 2026

Use it when

  • You use one or more coding agents on a repo and they keep using the wrong command, folder or pattern.
  • You are setting up a new repo and want agent rules in place before the first big change.
  • You have an old rules file (including a legacy .cursorrules) that is long, vague or out of date.
  • You are working in a chat without repository access. With access, the Project Rules Writer skill reads the code itself.

Skip it when

  • The repo has no settled structure yet. Write rules once folders and commands stop changing.
  • The problem is a missing linter or formatter. Set that up first; this prompt deliberately leaves out what tools already enforce.

Example

Input: agents: Claude Code and Cursor. Next.js 14 App Router, TypeScript 5, pnpm; pnpm test (Vitest), pnpm typecheck, pnpm lint. Database access only in lib/db/. Generated UI in components/ui/. No new dependencies or .env* edits without asking.

Output excerpt:

AGENTS.md
## Commands
- Install: pnpm install · Test: pnpm test · Types: pnpm typecheck · Lint: pnpm lint
## Layout
- app/: routes only. lib/: shared logic; lib/db/ is the only code that talks to the database.
- components/ui/: generated. Regenerate it; do not edit it by hand.
## Ask first
- Adding or upgrading a package. Reading or editing any .env* file.
## Done means
- pnpm test and pnpm typecheck ran and passed in this session, or you say why not.

CLAUDE.md
@AGENTS.md

.cursor/rules/db-access.mdc
---
description: Database access rules for lib/db
globs: lib/db/**
alwaysApply: false
---
- Queries use the shared client from lib/db/client.ts. TODO: confirm the file name.
Questions your rules do not answer yet
1. Which environment variables may an agent read? Proposed rule: "Read only the variable names in .env.example."
2. Do UI components need tests? Proposed rule: "New components in app/ get one render test."
3. Who may change the database schema? Proposed rule: "Schema changes go in a separate PR and need your approval."

Illustrative example written by Meevra to show the target format; your model's wording will differ.

What is inside

The full prompt has these sections. The ones marked “in the pack” come with the download.

  • What it does in the pack
  • Use it when on this page
  • Skip it when on this page
  • The prompt in the pack
  • How to use in the pack
  • How to run (Oct 2026) in the pack
  • Example on this page
  • Troubleshooting in the pack

Get Project Rules Interview (AGENTS.md, CLAUDE.md, Cursor)

The full prompt is a file you keep and reuse: the checklist and the answer format written out, with how to run it on each model. It comes in the Code & Agents pack (5 prompts · 15 skills · 1 free), with a QUICKSTART, setup notes in every item and 12 months of updates.

Or check out via Payhip

What is in the pack

All-Access 39 € vs 7 packs × 12 € = 84 € · less than buying 4 or more packs one by one

Stuck? Email support@meevra.com — we'll help you set it up.

See the pack

  • PromptPaid

    ChatGPT Project Instructions (anti-drift)

    Fill-in instructions for a ChatGPT Project that keep the assistant on one job, in one answer shape and grounded in your project files, plus the steps to turn the same text into a skill you can share.

    Code & Agents
    • ChatGPT
    • Codex
  • PromptPaid

    CLAUDE.md for a Solo Founder Repo

    A fill-in CLAUDE.md that tells a coding agent your stack, your exact commands, what needs your approval and how to report each task, so it stops adding packages and reporting passes it never saw.

    Code & Agents
    • Claude Code
    • Claude
    • Codex
    • Cursor
    • Antigravity
  • PromptPaid

    Code Review Partner

    Paste one file or change and get a merge call, real defects ranked by impact with the input that triggers each, fixes re-checked against every finding, and what the reviewer still needs to see.

    Code & Agents
    • Claude
    • ChatGPT
    • Gemini
    • DeepSeek
    • Qwen
    • GLM
    • Kimi
  • PromptPaid

    Custom GPT to ChatGPT Migration Kit

    Paste a Custom GPT's configuration and get its replacement: cleaned Project instructions, a plugin-ready SKILL.md, a knowledge-file map, a parity test and a cutover checklist.

    Code & Agents
    • ChatGPT
    • Codex
  • SkillPaid

    AGENTS.md + Skills Starter

    One AGENTS.md that every coding agent reads, plus your repeated procedures turned into starter skills in the folders each agent loads.

    Code & Agents
    • Claude Code
    • Codex
    • Cursor
    • Antigravity
  • SkillPaid

    Algorithm Designer

    Turns a problem and its limits into an algorithm that provably fits them, with an invariant, a hand trace and a brute-force comparison test.

    Code & Agents
    • Claude
    • ChatGPT
    • Gemini
    • DeepSeek
    • Qwen
    • Claude Code
    • Codex
    • Cursor
    • Antigravity