recipe-readme

recipe-readme is a cursor rule for Cursor from AMDResearch/ai4science-studio. It costs 0 tokens per session (337 once invoked), scanned A, original, MIT.

A set of rules for organizing README.md files that explain how to run a recipe, such as a model task.

In plain words
What is it for?
Use it when creating or editing recipe READMEs. It covers prerequisites, environment variables, quick-start commands, details, links to scripts, and a healthcare disclaimer where needed.
Why use it?
It prevents recipe documentation from leaving out important setup details or putting them in inconsistent places.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/amdresearch/ai4science-studio/recipe-readme
Clone the repo
git clone --depth 1 https://github.com/AMDResearch/ai4science-studio

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for recipe-readme

README.md
[![agentmods](https://agentmods.dev/badge/rules/amdresearch/ai4science-studio/recipe-readme.svg)](https://agentmods.dev/rules/amdresearch/ai4science-studio/recipe-readme)
Your own site
<a href="https://agentmods.dev/rules/amdresearch/ai4science-studio/recipe-readme"><img src="https://agentmods.dev/badge/rules/amdresearch/ai4science-studio/recipe-readme.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 337 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00337
Opus 5 $0.00000 $0.00169
Sonnet 5 $0.00000 $0.00067
Haiku 4.5 $0.00000 $0.00034

Measured 4d ago against content hash fcf8b2ad8af3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recipe-readme scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/recipe-readme.mdc · 48 lines

What it actually says

Recipe README conventions

When creating or editing a README.md under any model's recipes/<task>/ directory:

Required sections (in order)

  1. Title# <Model> — <Task> Recipe

  2. Callout box — Link to ready-to-run scripts:

    > **Ready-to-run scripts:** see [`../../examples/`](../../examples/) for `docker_run.sh` and `run_<task>.sh`.
    
  3. Prerequisites — Structured list (not prose paragraph):

    ## Prerequisites
    - Container: `<image tag>`
    - GPU: <hardware requirement>
    - Runtime: <Docker/Apptainer>
    - Weights: <how to get them>
    - Data: <how to get it>
    
  4. Environment Variables table:

    ## Environment Variables
    | Variable | Required | Default | Description |
    |----------|----------|---------|-------------|
    | `VAR` | Yes/No | `default` or -- | What it does |
    
  5. Quick Start — One-liner to run the task.

  6. Details — Prose explanation, code samples, etc.

Healthcare disclaimer

All healthcare/ recipe READMEs must include at the top:

> **Research / engineering use only.** Not for clinical or diagnostic use.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 48 lines · 0 tokens per session scan A fcf8b2ad8af3

Subscribe to this mod's changes

recipe-readme is a cursor rule published in the GitHub repository AMDResearch/ai4science-studio (4 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 337 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.