What is mcp-recipe-shopping-list AGENTS.md?

Repository instructions for an MCP server that reads recipes from food.ru, finds their ingredients on magnit.ru, and returns a shopping list with prices. The instructions also document important project restrictions and technical details.

Use them when developing or debugging the recipe shopping-list server, especially its recipe parsing and product-search workflows.

They warn the coding agent about rules such as not creating a cart, not sending images, and handling JavaScript-heavy websites correctly.

How KrivchenkoEgor/mcp-recipe-shopping-list configures Codex and OpenC

Reuse

Borrowing it

Nothing to install: this file belongs to KrivchenkoEgor/mcp-recipe-shopping-list. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/KrivchenkoEgor/mcp-recipe-shopping-list/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/KrivchenkoEgor/mcp-recipe-shopping-list

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/krivchenkoegor/mcp-recipe-shopping-list/agents-md/github.svg)](https://agentmods.dev/instructions/krivchenkoegor/mcp-recipe-shopping-list/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/krivchenkoegor/mcp-recipe-shopping-list/agents-md"><img src="https://agentmods.dev/badge/instructions/krivchenkoegor/mcp-recipe-shopping-list/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/krivchenkoegor/mcp-recipe-shopping-list/agents-md"><img src="https://agentmods.dev/badge/instructions/krivchenkoegor/mcp-recipe-shopping-list/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 7,026 This file is loaded in full into every session.

When invoked 7,026 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.07026	$0.07026
Opus 5.5	$0.02810	$0.02810
Sonnet 5.5	$0.01405	$0.01405
Haiku 4.5	$0.00703	$0.00703

Measured 2mo ago against content hash ad83dabd444c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-recipe-shopping-list AGENTS.md 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 2mo 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.

AGENTS.md · 660 lines

How it starts

The opening of the file, as written. The whole thing — 660 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Конституция ИИ-агента для проекта MCP Recipe Shopping List

Проект: MCP-сервер, который парсит рецепты с food.ru, находит ингредиенты на magnit.ru и возвращает список покупок с ценами. Этот документ стабилен. Меняется редко, только с одобрения пользователя. Накопленные приёмы → LESSONS.md. Текущее состояние → progress.md и checkpoint.md.

⛔ КРИТИЧЕСКИЕ ЗАПРЕТЫ (читать первым)

1. 🚫 Картинки в чате запрещены

DeepSeek в этом окружении не видит изображения. Любая картинка в чате — мгновенный краш сессии.

При первом сообщении каждой сессии: «Не присылай картинки — я их не вижу, и сессия упадёт. Всё присылай текстом или файлами.»
Графики, которые я строю — только для пользователя; корректность проверяю программно по данным

2. 🚫 Оба сайта — SPA (JavaScript-heavy)

Это главный технический факт проекта.

magnit.ru — Next.js / React SPA:

Простой httpx.get() + BeautifulSoup не работает — сервер возвращает HTML-шаблон без данных
При поиске «говядина» сайт вернул мармелад, открытки и канцелярию (проверено)

food.ru — аналогичная SPA:

Рецепты рендерятся через JavaScript
Блок "Продукты для рецепта" загружается динамически

Следствия:

Обязательно Playwright (асинхронный, headless Chromium) для обоих сайтов
httpx/requests + BeautifulSoup можно использовать только как fallback или для статичных страниц
Каждый парсер должен уметь ждать появления нужных DOM-элементов (wait_for_selector)
Таймауты обязательны (30 сек на загрузку страницы, 5 сек на селектор)

3. 🚫 Не формируем корзину — только список покупок

Корзина на Магните — серверная сессия, URL вида https://magnit.ru/checkout?items=... не работает.

Вместо этого:

Возвращаем список товаров с ценами и прямыми ссылками на magnit.ru
Пользователь добавляет товары в корзину вручную одним кликом
Показываем итоговую сумму списка покупок

4. 🚫 Уважение к серверам

Пауза 2–5 секунд между запросами к каждому сайту
Ротация User-Agent (5–10 реальных браузерных UA)
Экспоненциальный backoff при 429/503 ошибках (до 3 попыток)
Кэширование результатов поиска на 15 минут
Никаких массовых обходов и DDOS-подобного поведения

Read the full file on GitHub · 660 lines

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.

2mo ago First seen · 660 lines · 7,026 tokens per session scan A ad83dabd444c

Subscribe to this mod's changes

mcp-recipe-shopping-list AGENTS.md is an instructions file published in the GitHub repository KrivchenkoEgor/mcp-recipe-shopping-list (1 stars, last pushed 2mo ago), licensed MIT. It adds 7,026 tokens to every session, about $0.0281 per session on Opus 5.5. 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.

E-commerce fastmcp grocery mcp model-context-protocol playwright

mcp-recipe-shopping-list AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-recipe-shopping-list AGENTS.mdKrivchenkoEgor/mcp-recipe-shopping-list	Instructions file	1	2mo ago	MIT	A	7,026	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

mcp-recipe-shopping-list: Instructions file for Codex