Borrowing it
Nothing to install: this file belongs to ztemerbekov/a1-yandex-kit-skills. 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/ztemerbekov/a1-yandex-kit-skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/ztemerbekov/a1-yandex-kit-skillsWrote 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/ztemerbekov/a1-yandex-kit-skills/claude-md)<a href="https://agentmods.dev/instructions/ztemerbekov/a1-yandex-kit-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/ztemerbekov/a1-yandex-kit-skills/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/ztemerbekov/a1-yandex-kit-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/ztemerbekov/a1-yandex-kit-skills/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 | $0.01918 | $0.01918 |
| Opus 5 | $0.00959 | $0.00959 |
| Sonnet 5 | $0.00384 | $0.00384 |
| Haiku 4.5 | $0.00192 | $0.00192 |
Grade A, and why
a1-yandex-kit-skills 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 5d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — a1-yandex-kit-skills
npm-workspaces monorepo: typed client, MCP server (stdio) and Claude agent skills for the
Yandex KIT e-commerce API, all driven by the bundled OpenAPI spec
(specs/kit-swagger.openapi.json — 166 operations, 24 tag groups, the single source of truth).
Commands
npm ci
npm run typecheck # builds core first, then checks every workspace
npm run build # core + mcp -> dist/
npm test # unit tests, no network
npm run gen # regenerate registry/types/TOOLS.md/skills (deterministic)
npm run validate:agent-plugin # validate root Agent Plugins manifest, MCP config and skills
npm run spec:fetch # refresh specs/ from Yandex + diff report
npm run smoke # live READ-ONLY calls (needs YANDEX_KIT_TOKEN)
npm run e2e # live WRITE calls — TEST store only (needs YANDEX_KIT_E2E_WRITE=1)
Verify like CI does (node 20/22/24 matrix):
npm run typecheck && npm run build && npm test
npm run gen
git add -N -- packages/core/src/generated docs/TOOLS.md skills # register untracked generated files
git diff --exit-code -- packages/core/src/generated docs/TOOLS.md skills
npx @modelcontextprotocol/inspector@2 --cli node packages/mcp/dist/index.js --method tools/list -e YANDEX_KIT_TOKEN=dummy
More detail in docs/DEVELOPMENT.md. Tool list: docs/TOOLS.md.
Repo map
packages/core—yandex-kit-core:KitClient(Bearer auth, timeout, token-bucket rate limiter at 3 rps, backoff retries on network/5xx/429 (the live limiter answers 429 with a plain-textlimitedbody, no Retry-After) andLIMIT_EXCEEDEDwhich arrives with HTTP 400 — GET only: mutations always make exactly one network attempt (no idempotency contract from the API, a repeated write could duplicate the change), auto-pagination vialistAll, per-operation content type: merge-patch and multipart where the spec says so),KitApiError, ajv-basedvalidateRequestBody/resolveOperationSchema, andsrc/generated/{registry.json,types.ts}.packages/mcp—mcp-yandex-kit: stdio MCP server with 88 tools;src/tools/*.tsis one file per domain;meta.tshosts the trio (search_operations,get_operation_schema,kit_request) that covers all 166 operations (92 have curated tools).telemetry.ts— anonymous usage pings to usage.gistrec.cloud (ids/names/versions only, never data or arguments; fire-and-forget, must never block or throw; opt-outYANDEX_KIT_TELEMETRY=0).startup_failedis the exception:sendBlockingawaits it, because the caller exits right after and a fire-and-forget ping would die in flight. Itsreasonis a closed vocabulary (missing_token,invalid_config) — never a variable's name or value.packages/codegen— private generators run via tsx:gen-registry,gen-types,gen-docs,gen-skills,fetch-spec, plus the offline Agent Plugins validator.skills/— 6 generated API skills plus setup and the manually maintained operator, catalog-doctor, promo-launcher and launch-check scenarios. Each manual scenario skill records its editing invariants inskills/<name>/AGENTS.md.plugin.json+mcp.json— portable Agent Plugins package;mcp.jsondeliberately contains no store token..codex-plugin/,.cursor-plugin/,.claude-plugin/,.agents/and.mcp.json— client-specific or compatibility artifacts retained alongside the portable core.
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.
- 5d ago Changed · +2 lines · +21 tokens per session b07aac8be42e
- 11d ago First seen · 137 lines · 1,897 tokens per session scan A 92146c28337a
a1-yandex-kit-skills CLAUDE.md is an instructions file published in the GitHub repository ztemerbekov/a1-yandex-kit-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 1,918 tokens to every session, about $0.0096 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).