Borrowing it
Nothing to install: this file belongs to askads/mcp-yandex-wordstat. 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-wordstat/main/CLAUDE.mdgit clone --depth 1 https://github.com/askads/mcp-yandex-wordstatWrote 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-wordstat/claude-md)<a href="https://agentmods.dev/instructions/askads/mcp-yandex-wordstat/claude-md"><img src="https://agentmods.dev/badge/instructions/askads/mcp-yandex-wordstat/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-wordstat/claude-md"><img src="https://agentmods.dev/badge/instructions/askads/mcp-yandex-wordstat/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 | $0.01930 | $0.01930 |
| Opus 5 | $0.00965 | $0.00965 |
| Sonnet 5 | $0.00386 | $0.00386 |
| Haiku 4.5 | $0.00193 | $0.00193 |
Grade A, and why
mcp-yandex-wordstat 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — mcp-yandex-wordstat
MCP server for the Yandex Wordstat API (TypeScript, stdio). Read-only: tools wrap
the search-demand reports (top/related queries, dynamics, regional distribution);
raw_request is the escape hatch. The server talks to the Yandex Cloud Search
API v2 (searchapi.api.cloud.yandex.net, POST /v2/wordstat/*); auth is an
Api-Key and every request body carries a folderId. (The legacy standalone
oauth flavor — api.wordstat.yandex.net, Bearer, v1/* — was removed in 2.0.0;
Yandex folded that functionality into the Search API.)
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 WORDSTAT_API_KEY + WORDSTAT_FOLDER_ID)
Architecture
src/config.ts— env → config. MissingWORDSTAT_API_KEY/WORDSTAT_FOLDER_IDis NOT an error: the fields stayundefined, the server starts degraded and the client raisesCredentialsErrorat call time.ConfigError(with areasoncode) is reserved for malformed values, caught byloadConfigOrDegradedinindex.ts(no such checks exist today). OptionalWORDSTAT_LANG,WORDSTAT_API_BASE,WORDSTAT_TIMEOUT_MS,WORDSTAT_MAX_RETRIES.src/client.ts— maps each logical call (topRequests/dynamics/regions/regionsTree) to av2/wordstat/*path:Api-Keyauth, allPOST,folderIdinjected into every body, regions as strings,DEVICE_*/PERIOD_*/REGION_*enums.request()first rejects a missing credential withCredentialsError(before building the request, the retries and fetch — the message is the product: it names the env variable to set and the needed restart), then resolves the path against the base and rejects any path that escapes to a foreign origin (SSRF guard), retries 429 / 5xx / network errors with backoff (honorsRetry-After), enforces an AbortController timeout that also covers reading the body, and throwsWordstatError(status, body).src/tools/wordstat.ts—top_requests,dynamics,regions,list_regions. Inputs are normalized (regionIds,devices,period,regionMode); the client does the wire mapping.src/tools/raw.ts—raw_request(POST only).src/tools/util.ts—ok/fail, theREAD_ONLYannotation and shared zod schema factories (deviceEnum,rfc3339Date).src/index.ts— wires everyregister*into the McpServer.loadConfigOrDegradedstarts the server even on a config problem; without credentials the initializeinstructionsopen with the unconfigured prefix (setWORDSTAT_API_KEY/WORDSTAT_FOLDER_IDand 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 credentials sendsunconfigured_startinstead. Thereasonis a closed vocabulary (missing_token,missing_folder_id) — never a variable's name or value.startup_failedremains for a config unusable at load time (malformed values), also fire-and-forget.
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.
- 9d ago First seen · 108 lines · 1,930 tokens per session scan A 00c2508fed2c
mcp-yandex-wordstat CLAUDE.md is an instructions file published in the GitHub repository askads/mcp-yandex-wordstat (5 stars, last pushed 19d ago), licensed MIT. It adds 1,930 tokens to every session, about $0.0097 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.