Borrowing it
Nothing to install: this file belongs to askads/mcp-yandex-webmaster. 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-webmaster/main/CLAUDE.mdgit clone --depth 1 https://github.com/askads/mcp-yandex-webmasterWrote 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-webmaster/claude-md)<a href="https://agentmods.dev/instructions/askads/mcp-yandex-webmaster/claude-md"><img src="https://agentmods.dev/badge/instructions/askads/mcp-yandex-webmaster/claude-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 | $0.02746 | $0.02746 |
| Opus 5 | $0.01373 | $0.01373 |
| Sonnet 5 | $0.00549 | $0.00549 |
| Haiku 4.5 | $0.00275 | $0.00275 |
Grade A, and why
mcp-yandex-webmaster 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — mcp-yandex-webmaster
MCP server for the Yandex Webmaster API v4 (TypeScript, stdio). Mostly read
tools (sites, summary, diagnostics, search queries, indexing, sitemaps, links)
plus four non-destructive writes (add_site, add_sitemap, recrawl_url,
start_verification); raw_request is the escape hatch (GET/POST/DELETE). The
server talks to https://api.webmaster.yandex.net/v4; auth is a Yandex OAuth
token sent as Authorization: OAuth <token> — either YANDEX_OAUTH_TOKEN or a
token minted by the in-chat login (start_login/finish_login). Almost every
path lives under /user/{user-id}/... — the client resolves the user id via
GET /v4/user once and caches it (or takes YANDEX_USER_ID).
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 call (needs YANDEX_OAUTH_TOKEN)
Architecture
src/config.ts— env → config. A missingYANDEX_OAUTH_TOKENis NOT an error: the field staysundefined(an empty string reads as absent) and the server starts degraded — the token is resolved per request (env → stored login), so the user can connect from the chat.ConfigError(with areasoncode) is reserved for malformed values — today a non-numericYANDEX_USER_ID— and is caught byloadConfigOrDegradedinindex.ts. OptionalYANDEX_USER_ID,YANDEX_WEBMASTER_HOST_ID,YANDEX_WEBMASTER_API_BASE,YANDEX_WEBMASTER_TIMEOUT_MS,YANDEX_WEBMASTER_MAX_RETRIES.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. The client id is the dedicated Webmaster app, overridable viaYANDEX_WEBMASTER_OAUTH_CLIENT_ID; scope is pinned towebmaster:hostinfo webmaster:verify.src/credentials.ts—~/.config/mcp-yandex-webmaster/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_loginin the chat, orYANDEX_OAUTH_TOKEN+ restart). Replaced the oldCredentialsError.src/client.ts— one typed method per endpoint. Owns the wire vocabulary (TOTAL_SHOWS,MOBILE_AND_TABLET,DNS, ... viamap*helpers), the user-id promise cache (userId(), failure not cached — that is what lets the auto-detection run lazily on the first call after a mid-session login), the host path builder (hostPath()applies the config default and URL-encodes the id, failing fast without a fetch when both are missing) and query-string building (arrays become repeated params, undefined is dropped).request()resolves the token via theTokenStoreon every attempt, before fetch — a missing token throwsAuthRequiredErrorthere and is rethrown before the retry/backoff branch, which also stops the user-id auto-detection — resolves the path against the base and rejects any path that escapes to a foreign origin (SSRF guard), retries 429 (exceptQUOTA_EXCEEDED) but 5xx/network only for GET (a 502 after a committed write must not duplicate it), honorsRetry-After, re-mints a stored token once on 401 and replays, enforces an AbortController timeout that also covers reading the body, and throwsWebmasterError(status, body).src/types.ts— config + normalized unions;WebmasterErrorparses the API's{error_code, error_message, ...}body and appends follow-up hints forHOST_NOT_VERIFIED/HOST_NOT_LOADED/HOST_NOT_INDEXED(andavailable_user_idforINVALID_USER_ID).src/tools/auth.ts— the in-chat login (auth_status,start_login,finish_login,logout);hosts.ts— sites, summary, verification, diagnostics;queries.ts— popular queries + history;indexing.ts— crawl history, recrawl, important pages, sitemaps;links.ts— external links;raw.ts—raw_request(substitutes a{user-id}placeholder).util.ts—ok/fail, theREAD_ONLY/WRITE/WRITE_UPDATE/DESTRUCTIVEannotation constants and shared zod schema factories (hostId,isoDate).src/index.ts— wires everyregister*into the McpServer.loadConfigOrDegraded()catchesConfigError, pingsstartup_failed(fire-and-forget) and degrades the config to "no credentials";connected = tokens.hasToken()is resolved once, only to pick the instructions text — an unconfigured start prependsUNCONFIGURED_PREFIX(namingstart_loginand the env alternative) — plusПроблема конфигурации: <message>when a ConfigError was caught — to the initializeinstructions, andoninitializedsendsserver_startfor a configured install orunconfigured_start(with the reason) otherwise.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";unconfigured_startis a degraded start andstartup_faileda malformed config caught at load — both carry areasonfrom a closed vocabulary (missing_token,invalid_user_id) — never a variable's name or value.
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 · 152 lines · 2,746 tokens per session scan A b5d8882411f2
mcp-yandex-webmaster CLAUDE.md is an instructions file published in the GitHub repository askads/mcp-yandex-webmaster (0 stars, last pushed 17d ago), licensed MIT. It adds 2,746 tokens to every session, about $0.0137 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
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.
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.