agentmods.dev

yandex360-mcp: Instructions file for Claude Code

CLAUDE.md

yandex360-mcp CLAUDE.md is an instructions file for Claude Code from pa1ch/yandex360-mcp. It costs 1,005 tokens per session, scanned A, original, MIT.

Release instructions for yandex360-mcp, a modular MCP server for Yandex 360 services. The document explains how an assistant should update versions, run checks, and publish releases through automated workflows.

In plain words
What is it for?
Following the project’s release procedure, including versioning, tests, package publishing, and GitHub and MCP Registry releases.
Why use it?
It helps prevent manual release steps from being missed or performed inconsistently, although the instructions say publishing is triggered by a version tag.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is pa1ch/yandex360-mcp's own configuration. It tells Claude Code how to work on yandex360-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything yandex360-mcp configures →

not rated 0repo 1mo ago A scan 1,005 tokens original MIT
View source ↗ pa1ch/yandex360-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to pa1ch/yandex360-mcp. 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/pa1ch/yandex360-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/pa1ch/yandex360-mcp

Made for: Claude Code.

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 yandex360-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pa1ch/yandex360-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/pa1ch/yandex360-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pa1ch/yandex360-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/pa1ch/yandex360-mcp/claude-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.

agentmods 80×15 button for yandex360-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pa1ch/yandex360-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/pa1ch/yandex360-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,005 This file is loaded in full into every session.
When invoked 1,005 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01005 $0.01005
Opus 5 $0.00502 $0.00502
Sonnet 5 $0.00201 $0.00201
Haiku 4.5 $0.00101 $0.00101

Measured 9d ago against content hash e92ce23b0722, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

yandex360-mcp CLAUDE.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 9d 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.

CLAUDE.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — гайд для ассистента

Публичный пакет yandex360-mcp — модульный MCP-сервер для сервисов Яндекс 360 (сейчас модуль wiki). Опубликован на PyPI, GitHub и в MCP Registry.

Релизы разработчик вручную не делает — релиз целиком проводит ассистент по запросу («выпусти патч», «сделай релиз 0.2.0»). Ниже — процедура; следуй ей.

Как устроен релиз (всё автоматически по тегу)

Пуш тега vX.Y.Z запускает .github/workflows/release.yml, который сам:

  • собирает пакет и гоняет тесты, сверяет тег == version в pyproject.toml;
  • публикует на PyPI (Trusted Publishing / OIDC, без токена);
  • собирает .mcpb-бандл и прикладывает к GitHub Release (вместе с wheel и sdist);
  • публикует в MCP Registry (mcp-publisher login github-oidc);
  • подставляет версию из тега в server.json и manifest.json.

Ничего из этого руками не делаем: ни uv publish, ни mcp-publisher, ни создание GitHub Release — только тег.

Процедура релиза (шаги ассистента)

  1. Выбрать версию по SemVer: patch — фиксы; minor — новый модуль/фича; major — ломающие изменения.
  2. Поднять версию ровно в двух файлах: pyproject.toml и src/yandex360_mcp/__init__.py. (server.json и manifest.json CI выставит из тега; бампать их не обязательно, но и не вредно.)
  3. CHANGELOG.md: перенести пункты из ## [Unreleased] в ## [X.Y.Z] - <сегодня>, оставить [Unreleased] пустым.
  4. Локальная проверка: uv build и uv run pytest -q; по желанию npx --yes @anthropic-ai/mcpb validate manifest.json.
  5. Коммит в main и пуш.
  6. Тег и пуш тега: 
    git tag vX.Y.Z && git push origin vX.Y.Z
  7. Дождаться пайплайна и проверить результат: 
    gh run watch <run-id> --exit-status
gh release view vX.Y.Z --json assets      # .mcpb + wheel + sdist
    В логе job mcp-registry должна быть строка ✓ Successfully published ... version X.Y.Z.

Гарды

  • Тег обязан совпадать с версией в pyproject.toml — иначе job build падает на сверке (это защита от рассинхрона).
  • Версии на PyPI неизменяемы. Никогда не переиспользуй номер — только вверх. Если релиз частично упал уже после публикации на PyPI, этот номер «сгорел» → почини и выпусти следующий патч.
  • Коммиты и PR — без любых упоминаний Claude/AI (Co-Authored-By и т.п.).
  • Trusted Publisher на PyPI и доверие OIDC для namespace io.github.pa1ch уже настроены — доп. действий не требуют.

Read the full file on GitHub · 69 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.

  1. 9d ago First seen · 69 lines · 1,005 tokens per session scan A e92ce23b0722

Subscribe to this mod's changes

yandex360-mcp CLAUDE.md is an instructions file published in the GitHub repository pa1ch/yandex360-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,005 tokens to every session, about $0.0050 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 2026-08-31.

Git and workflowReleasesmcpmcp-serveryandexyandex360
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens