Borrowing it
Nothing to install: this file belongs to A1-x-Tech/mcp-yandex-merchants. 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/A1-x-Tech/mcp-yandex-merchants/main/CLAUDE.mdgit clone --depth 1 https://github.com/A1-x-Tech/mcp-yandex-merchantsWrote 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/a1-x-tech/mcp-yandex-merchants/claude-md)<a href="https://agentmods.dev/instructions/a1-x-tech/mcp-yandex-merchants/claude-md"><img src="https://agentmods.dev/badge/instructions/a1-x-tech/mcp-yandex-merchants/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/a1-x-tech/mcp-yandex-merchants/claude-md"><img src="https://agentmods.dev/badge/instructions/a1-x-tech/mcp-yandex-merchants/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 | $0.02765 | $0.02765 |
| Opus 5 | $0.01383 | $0.01383 |
| Sonnet 5 | $0.00553 | $0.00553 |
| Haiku 4.5 | $0.00277 | $0.00277 |
Grade A, and why
mcp-yandex-merchants 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 10d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — mcp-yandex-merchants
MCP server for the Yandex Merchants (Яндекс Товары) partner API (TypeScript,
stdio). This is a write API: tools wrap the 4 documented endpoints — feeds
info (GET /feeds-info), price updates (POST /offer-prices/updates), hiding
(POST /hidden-offers) and unhiding (DELETE /hidden-offers);
raw_request is the escape hatch. The server talks to
https://yandex.ru/products/api/ext/partner; auth is a Yandex OAuth token with
the products:partner-api scope, sent as Authorization: OAuth <token> — the
token must belong to the login that uploaded the YML feed. The token comes from
the in-chat login (start_login/finish_login, stored on disk) or from
YANDEX_MERCHANTS_OAUTH_TOKEN (which wins).
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_MERCHANTS_OAUTH_TOKEN)
Architecture
src/config.ts— env → config. A missingYANDEX_MERCHANTS_OAUTH_TOKENis NOT an error: the field staysundefined, the server starts anyway and the token is resolved per request (env → stored login); with neither source the client raisesAuthRequiredErrorat call time.ConfigError(with areasoncode) is reserved for malformed values, caught byloadConfigOrDegradedinindex.ts(no such checks exist today). OptionalYANDEX_MERCHANTS_BASE_URL,YANDEX_MERCHANTS_TIMEOUT_MS,YANDEX_MERCHANTS_MAX_RETRIES.src/oauth.ts— the OAuth flow: PKCE pair (S256), authorize URL againsthttps://oauth.yandex.ru/verification_code, code exchange and refresh, explicitscope=products:partner-api+force_confirm=yes. Noclient_secret— this is a public client («Яндекс Товары — A1-x-Tech MCP», overridable viaYANDEX_MERCHANTS_OAUTH_CLIENT_ID), 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-merchants/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, or the env var + restart). It replaced the formerCredentialsError.src/client.ts— maps each logical call (feedsInfo/updateOfferPrices/hideOffers/showOffers) to its endpoint:OAuthauth resolved per request viaTokenStore, the price wire shape ({ feed: { id }, id, price: { currencyId: "RUR", value, discountBase?, payBy? } }),hiddenOfferswithttlInHoursstamped onto every element.request()rethrowsAuthRequiredErrorbefore the retries and before fetch (a missing setup is not transport trouble), resolves the path against the base and rejects any path that escapes to a foreign origin (SSRF guard), retries 429 always but 5xx/network only for GET (a 502 after a write commits could duplicate it), re-mints a stored token once on 401 (403 stays out: here it means a wrong login or unconfirmed Webmaster rights, which a fresh token cannot fix), enforces an AbortController timeout that also covers reading the body, and throwsMerchantsError(status, body).src/tools/auth.ts—auth_status,start_login,finish_login(verifies the new token with a live feeds-info call and warns when it sees zero feeds — a wrong-login token),logout.src/tools/feeds.ts—list_feeds,check_access(diagnostics: failures come back as{ ok: false, error }data, notisError).src/tools/prices.ts—set_offer_price,update_offer_prices,set_offer_discount(validates the 5–95% window before the request).src/tools/hidden.ts—hide_offer,hide_offers,show_offers.src/tools/raw.ts—raw_request(GET/POST/DELETE, not read-only).src/tools/util.ts—ok/fail/errorMessage, theREAD_ONLY/WRITE/WRITE_IDEMPOTENT/WRITE_DELETEannotations and shared zod schema factories (feedId,offerId,price,ttlInHours,payByCondition).src/index.ts— wires everyregister*into the McpServer.loadConfigOrDegradedstarts the server even on a config problem;connected = tokens.hasToken()is read once, only to pick the instructions text — without a token the initializeinstructionsopen with the unconfigured prefix (log in viastart_login, or setYANDEX_MERCHANTS_OAUTH_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.
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.
- 10d ago First seen · 154 lines · 2,765 tokens per session scan A bede8623267f
mcp-yandex-merchants CLAUDE.md is an instructions file published in the GitHub repository A1-x-Tech/mcp-yandex-merchants (0 stars, last pushed 11d ago), licensed MIT. It adds 2,765 tokens to every session, about $0.0138 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).
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.
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).