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.
npx agentmods add instructions/nymaxxx/checko-mcp/agents-mdgit clone --depth 1 https://github.com/Nymaxxx/checko-mcpWrote 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.
[](https://agentmods.dev/instructions/nymaxxx/checko-mcp/agents-md)<a href="https://agentmods.dev/instructions/nymaxxx/checko-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/nymaxxx/checko-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.04126 | $0.04126 |
| Opus 5 | $0.02063 | $0.02063 |
| Sonnet 5 | $0.00825 | $0.00825 |
| Haiku 4.5 | $0.00413 | $0.00413 |
Grade A, and why
checko-mcp 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Руководство для AI-агентов и разработчиков
Этот файл описывает структуру проекта, соглашения по коду и инструкции для AI-агентов, работающих над этим репозиторием.
Обзор проекта
checko-mcp — Python MCP-сервер для Checko.ru API v2. Предоставляет AI-ассистентам и MCP-клиентам:
- 12 инструментов (tools) — вызовы эндпоинтов API.
- 6 готовых сценариев (prompts) — типовые workflow с зашитой последовательностью вызовов.
- 5 справочных ресурсов (resources) — agent guide, правовая справка, методология аудита.
Стек:
- Python 3.10+ (CI: 3.10/3.11/3.12/3.13)
mcp[cli]— Python MCP SDK (stdio-транспорт)httpx— async HTTP-клиент (один экземпляр на жизнь сервера)python-dotenv— загрузка переменных окруженияpytest+pytest-asyncio— тестыruff— линтер- Docker / docker-compose — контейнеризация (приоритетный способ запуска)
Структура репозитория
checko-mcp/
├── src/
│ └── checko_mcp/
│ ├── __init__.py — версия пакета
│ ├── __main__.py — точка входа: asyncio.run(run())
│ ├── _validation.py — require_any, check_format, coerce_bool, ValidationError
│ ├── client.py — CheckoClient (httpx.AsyncClient + CheckoAPIError)
│ ├── tools.py — реестр TOOLS: список ToolSpec(name, endpoint, schema, pre)
│ ├── resources.py — реестр RESOURCES + загрузка markdown (package data + dev fallback)
│ ├── prompts.py — реестр PROMPTS: 6 готовых сценариев
│ ├── server.py — MCP Server: list_tools/call_tool, list_resources/read_resource,
│ │ list_prompts/get_prompt, run
│ └── _resources/ — package data: канонические markdown-файлы (force-include в wheel)
├── tests/
│ ├── conftest.py — фикстуры: подмена API-ключа, фабрика клиента с MockTransport
│ ├── test_validation.py — валидаторы
│ ├── test_client.py — HTTP-клиент (httpx.MockTransport)
│ ├── test_tools.py — реестр инструментов и pre-валидаторы
│ ├── test_resources.py — реестр ресурсов и загрузка markdown
│ └── test_prompts.py — реестр promptов и шаблоны
├── docs/
│ ├── api/ — справочник по эндпоинтам Checko API
│ │ ├── README.md
│ │ ├── search.md, company.md, entrepreneur.md, person.md
│ │ ├── finances.md, legal-cases.md, contracts.md, inspections.md
│ │ ├── bank.md, timeline.md, fedresurs.md, bankruptcy-messages.md
│ └── instructions/
│ └── agent-guide.md — каноничный текст ресурса checko://docs/agent-guide
├── playbooks/
│ ├── README.md
│ └── audit/ — методология/чеклист/шаблон (= ресурсы checko://playbooks/audit/*)
├── .github/
│ ├── workflows/ci.yml — lint + tests на 4 версиях Python + docker build
│ ├── ISSUE_TEMPLATE/
│ └── PULL_REQUEST_TEMPLATE.md
├── Dockerfile — multi-stage, python:3.13-slim
├── docker-compose.yml — приоритетный способ запуска (env_file: .env)
├── pyproject.toml — hatchling, ruff, pytest, [project.optional-dependencies] dev
├── .env.example
├── README.md — пользовательская документация
├── AGENTS.md — этот файл
├── CHANGELOG.md — Keep a Changelog + SemVer
├── CONTRIBUTING.md — как внести вклад
├── SECURITY.md — политика приёма уязвимостей
├── LEGAL.md — правовые основания (152-ФЗ, 149-ФЗ)
└── LICENSE — MIT
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.
- 5d ago First seen · 314 lines · 4,126 tokens per session scan A a780c12d4e02
checko-mcp AGENTS.md is an instructions file published in the GitHub repository Nymaxxx/checko-mcp (13 stars, last pushed 3mo ago), licensed MIT. It adds 4,126 tokens to every session, about $0.0206 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
seekstone CLAUDE.md
Claude Code instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
cyxj-groksearch CLAUDE.md
Claude Code instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.