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/axisrow/yandex-direct-mcp-plugin/agents-mdgit clone --depth 1 https://github.com/axisrow/yandex-direct-mcp-pluginWrote 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/axisrow/yandex-direct-mcp-plugin/agents-md)<a href="https://agentmods.dev/instructions/axisrow/yandex-direct-mcp-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/axisrow/yandex-direct-mcp-plugin/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 | $0.00700 | $0.00700 |
| Opus 5 | $0.00350 | $0.00350 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
yandex-direct-mcp-plugin 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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- yandex-direct-mcp AGENTS.md — 95% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Core code lives in server/. Use server/main.py as the MCP entrypoint, server/tools/ for tool handlers (campaigns.py, ads.py, keywords.py, reports.py, auth_tools.py), and server/cli/ for direct execution (installed via the direct-cli package). Authentication is delegated to direct auth profiles rather than a plugin-local auth module. Tests live in tests/, with cassette fixtures under tests/recordings/ and shared setup in tests/conftest.py and tests/cli_recorder.py. Documentation is in docs/, and skill definitions are in skills/.
Build, Test, and Development Commands
Install dev dependencies with pip install -e '.[dev]'. Run the server locally with python -m server.main. Use pytest for the default cassette-replay suite, pytest --record to refresh cassettes from the live CLI, pytest -m mocks for subprocess edge cases, and pytest -m integration for live-token checks. Run ruff check ., ruff format ., and mypy . before opening a PR. For docs, use make -C docs html.
Coding Style & Naming Conventions
Target Python 3.11+, 4-space indentation, and type annotations on public functions. Follow the current module naming style: lowercase snake_case files, descriptive test names like test_auth.py, and tool functions grouped by Yandex.Direct resource. Keep transport and auth concerns separated from tool logic. Use ruff for linting/formatting and mypy for type checks; prefer fixing root causes over adding ignores.
Testing Guidelines
The default test flow replays JSON cassettes instead of calling the API. Record only when behavior changes: pytest --record. After recording, sanitize sensitive values with python -m tests.sanitize; audit recordings with python -m tests.audit. Mark pure mock tests with @pytest.mark.mocks and live-token tests with @pytest.mark.integration. Do not commit raw tokens, secrets, or unsanitized cassette output.
Commit & Pull Request Guidelines
Recent history follows Conventional Commit style, for example fix: ..., refactor(auth): ..., and issue-linked subjects such as (#40). Keep commits focused and imperative. PRs should describe user-visible behavior, note auth or cassette changes, link the issue when applicable, and include command results for pytest, ruff, and mypy. Add screenshots only when updating docs or plugin UX text that benefits from visual context.
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.
- 4d ago First seen · 23 lines · 700 tokens per session scan A 149c73e92571
yandex-direct-mcp-plugin AGENTS.md is an instructions file published in the GitHub repository axisrow/yandex-direct-mcp-plugin (12 stars, last pushed 3d ago), licensed MIT. It adds 700 tokens to every session, about $0.0035 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.