Borrowing it
Nothing to install: this file belongs to askads/mcp-yandex-direct. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/askads/mcp-yandex-direct/main/CLAUDE.mdgit clone --depth 1 https://github.com/askads/mcp-yandex-directWrote 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/askads/mcp-yandex-direct/claude-md)<a href="https://agentmods.dev/instructions/askads/mcp-yandex-direct/claude-md"><img src="https://agentmods.dev/badge/instructions/askads/mcp-yandex-direct/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.
<a href="https://agentmods.dev/instructions/askads/mcp-yandex-direct/claude-md"><img src="https://agentmods.dev/badge/instructions/askads/mcp-yandex-direct/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01836 | $0.01836 |
| Opus 5 | $0.00918 | $0.00918 |
| Sonnet 5 | $0.00367 | $0.00367 |
| Haiku 4.5 | $0.00184 | $0.00184 |
Grade A, and why
mcp-yandex-direct 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 8d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — mcp-yandex-direct
MCP server for the Yandex Direct API v5 (TypeScript, stdio). Tools wrap the JSON
services; raw_request is the escape hatch for everything without a dedicated tool.
Commands
npm run dev # run from source (tsx watch)
npm test # unit tests, no network
npm run typecheck # types for src + tests
npm run build # emit dist/
npm run smoke # live READ-ONLY calls (needs YANDEX_DIRECT_TOKEN)
More detail in docs/DEVELOPMENT.md. Tool list: docs/TOOLS.md.
Architecture
src/client.ts— HTTP client: timeout, retry/backoff, Units quota,getAllcursor pagination, report polling. Every request path (call/callV4/report) resolves the token through theTokenStoreper request; a missing token raisesAuthRequiredErrorbefore building the request, the retries and fetch. An authorization error (code 53) on a stored token triggers one silent refresh + replay per request.src/oauth.ts— the OAuth flow: PKCE pair (S256), authorize URL againsthttps://oauth.yandex.ru/verification_code, code exchange and refresh. Noclient_secret— this is a public client, and a secret inside an npm package would protect nothing. The pending verifier lives in one module-level slot (one stdio server = one user); a secondstart_loginreplaces it.src/credentials.ts—~/.config/mcp-yandex-direct/credentials.json, mode0600. An unparsable file reads as "not connected", never as an empty token.src/auth.ts—TokenStore: resolves the token per request (env wins over stored), refreshes on expiry, and raisesAuthRequiredErrorwhose message is the product — it is the only text the user ever sees about a missing token, and it names both fixes (start_login, env variable).src/tools/*.ts— one file per service, each exportsregister<Name>Tools(server, client);src/tools/auth.ts(auth_status, start_login, finish_login, logout) additionally takes theTokenStore.src/tools/util.ts— shared helpers (see conventions below).src/index.ts— wires everyregister*into the McpServer.loadConfigOrDegradedstarts the server even on a config problem; without a token the initializeinstructionsopen with the unconfigured prefix (connect viastart_login, or setYANDEX_DIRECT_TOKENand restart).src/telemetry.ts— anonymous usage pings (ids/names/versions only, never data or arguments; fire-and-forget, must never block or throw; opt-outASKADS_TELEMETRY=0).server_startmeans "a usable install started"; an install without a token sendsunconfigured_startinstead. Thereasonis a closed vocabulary (missing_token, …) — never a variable's name or value.startup_failedremains for a config unusable at load time (malformed values), also fire-and-forget.src/config.ts— env → config. A missingYANDEX_DIRECT_TOKENis NOT an error: the field staysundefined, the token is resolved per request (env → stored credentials) and the client raisesAuthRequiredErrorat call time.ConfigError(with areasoncode) is reserved for malformed values, caught byloadConfigOrDegradedinindex.ts(no such checks exist today — the optional variables fall back to defaults on junk).
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.
- 8d ago First seen · 114 lines · 1,836 tokens per session scan A cbf5471eda68
mcp-yandex-direct CLAUDE.md is an instructions file published in the GitHub repository askads/mcp-yandex-direct (1 stars, last pushed 18d ago), licensed MIT. It adds 1,836 tokens to every session, about $0.0092 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.
Other instructions, from other repositories
data-scientist copilot-instructions.md
Repository instructions for a data-science workflow in GitHub Copilot, covering datasets, statistics, and analysis files.
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.
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.
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).
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).
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.