agentmods.dev

yandex-direct-mcp: Instructions file for Claude Code

CLAUDE.md

yandex-direct-mcp CLAUDE.md is an instructions file for Claude Code from nikolaymokh-dev/yandex-direct-mcp. It costs 10,170 tokens per session, scanned B, original, MIT.

A set of project instructions for Claude Code, an AI coding assistant, in a repository that manages Yandex.Direct advertising campaigns. It documents the project structure, architecture, contracts, and development rules.

In plain words
What is it for?
Use it when an AI agent needs to understand this repository’s architecture, its 129 MCP tools, its command-line wrapper, and its Claude Code or Codex setup.
Why use it?
It gives coding agents the context needed to work consistently in the repository. It also records that the MCP server must use the project’s Python command-line tool instead of calling Yandex.Direct directly.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is nikolaymokh-dev/yandex-direct-mcp's own configuration. It tells Claude Code how to work on yandex-direct-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 yandex-direct-mcp configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

not rated 0repo 9d ago B scan 10,170 tokens original MIT
View source ↗ nikolaymokh-dev/yandex-direct-mcp
Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nikolaymokh-dev/yandex-direct-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nikolaymokh-dev/yandex-direct-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10,170 This file is loaded in full into every session.
When invoked 10,170 The same file — it is already loaded in full.
Security scan B 3 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 $0.10170 $0.10170
Opus 5 $0.05085 $0.05085
Sonnet 5 $0.02034 $0.02034
Haiku 4.5 $0.01017 $0.01017

Measured 9d ago against content hash c42ee56e9647, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

yandex-direct-mcp CLAUDE.md scanned grade B with 3 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Add to `~/.claude/settings.json`:

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- MCP **never** calls Yandex.Direct directly. This is absolute — even as a workaround for a missing/broken CLI feature, the plugin does not bypass `direct-cli` via `urllib`, raw HTTP, or `tapi-yandex-direct` imports. If

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

2. **Mocks** (`pytest -m mocks`) — `unittest.mock.patch("subprocess.run")` for unreproducible edge cases
CLAUDE.md · 742 lines

How it starts

The opening of the file, as written. The whole thing — 742 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Claude Code plugin for managing Yandex.Direct advertising campaigns. Wraps direct CLI (Python) via an MCP server and delegates authentication to direct auth profiles.

Status: Implemented.

Architecture

direct (Python CLI)         — talks to Yandex.Direct API
       ↑
server/main.py (MCP)        — FastMCP server (stdio transport)
       ↑
server/contract.py          — machine-readable parity layer (129 tools)
server/cli/runner.py        — subprocess wrapper over `direct`
server/tools/               — 129 MCP tools across 34 active modules
       ↑
skills/                     — domain knowledge (SKILL.md files)
       ↑
.claude-plugin/plugin.json  — plugin manifest
.mcp.json                   — MCP server config

Contract hierarchy

MCP → direct → tapi-yandex-direct → Yandex.Direct API
  • MCP never calls Yandex.Direct directly. This is absolute — even as a workaround for a missing/broken CLI feature, the plugin does not bypass direct-cli via urllib, raw HTTP, or tapi-yandex-direct imports. If CLI lacks something, file an upstream issue in axisrow/direct-cli and wait for the release.
  • direct is the only execution/transport boundary.
  • tapi-yandex-direct naming is the default source reused by the CLI.
  • WSDL / Reports spec wins when CLI convenience names drift.

The machine-readable parity source is server/contract.py (PUBLIC_CONTRACT, TRANSPORT_BLOCKED_OPERATIONS, RENAMED_TOOL_MIGRATION).

Dual-channel layout (Claude Code + Codex bundle)

The repository ships the plugin to two distinct hosts, so manifests and .mcp.json deliberately exist in two places. This is not a duplication bug — do not "consolidate" them:

Channel Plugin manifest MCP config Launcher Bootstrap
Claude Code .claude-plugin/plugin.json .mcp.json hooks/run-server.sh hooks/setup.sh (SessionStart hook)
Codex bundle plugins/yandex-direct/.codex-plugin/plugin.json plugins/yandex-direct/.mcp.json plugins/yandex-direct/run-server.sh self-bootstrap inside the launcher (no SessionStart hook in Codex)

Read the full file on GitHub · 742 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 · 742 lines · 10,170 tokens per session scan B c42ee56e9647

Subscribe to this mod's changes

yandex-direct-mcp CLAUDE.md is an instructions file published in the GitHub repository nikolaymokh-dev/yandex-direct-mcp (0 stars, last pushed 9d ago), licensed MIT. It adds 10,170 tokens to every session, about $0.0508 per session on Opus 5. A static security scan graded it B with 3 findings (reads agent configuration directories, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Planningadvertisingclaudemcpmodel-context-protocolyandex
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