a1-yandex-kit-skills: Instructions file for Claude Code

CLAUDE.md

a1-yandex-kit-skills CLAUDE.md is an instructions file for Claude Code from ztemerbekov/a1-yandex-kit-skills. It costs 1,918 tokens per session, scanned A, original, MIT.

A set of instructions for working on a1-yandex-kit-skills, an npm-workspaces monorepo containing a Yandex KIT e-commerce API client, MCP server, and agent skills. It defines commands, repository conventions, generated files, and checks.

In plain words
What is it for?
Use it when developing, testing, generating, validating, or refreshing the API-based components and skills in that repository.
Why use it?
It explains how the repository fits together and how to verify changes without manually editing generated output. A monorepo is one repository that contains multiple related packages.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Codex.

This is ztemerbekov/a1-yandex-kit-skills's own configuration. It tells Claude Code how to work on a1-yandex-kit-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything a1-yandex-kit-skills configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/ztemerbekov/a1-yandex-kit-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ztemerbekov/a1-yandex-kit-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for a1-yandex-kit-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ztemerbekov/a1-yandex-kit-skills/claude-md/github.svg)](https://agentmods.dev/instructions/ztemerbekov/a1-yandex-kit-skills/claude-md)
Your own site
<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.

agentmods 80×15 button for a1-yandex-kit-skills CLAUDE.md

Your own site · 80×15
<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>
Per session 1,918 This file is loaded in full into every session.
When invoked 1,918 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash b07aac8be42e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

CLAUDE.md · 139 lines

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/coreyandex-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-text limited body, no Retry-After) and LIMIT_EXCEEDED which 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 via listAll, per-operation content type: merge-patch and multipart where the spec says so), KitApiError, ajv-based validateRequestBody/resolveOperationSchema, and src/generated/{registry.json,types.ts}.
  • packages/mcpmcp-yandex-kit: stdio MCP server with 88 tools; src/tools/*.ts is one file per domain; meta.ts hosts 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-out YANDEX_KIT_TELEMETRY=0). startup_failed is the exception: sendBlocking awaits it, because the caller exits right after and a fire-and-forget ping would die in flight. Its reason is 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 in skills/<name>/AGENTS.md.
  • plugin.json + mcp.json — portable Agent Plugins package; mcp.json deliberately contains no store token.
  • .codex-plugin/, .cursor-plugin/, .claude-plugin/, .agents/ and .mcp.json — client-specific or compatibility artifacts retained alongside the portable core.

Read the full file on GitHub · 139 lines

Changes

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.

  1. 5d ago Changed · +2 lines · +21 tokens per session b07aac8be42e
  2. 11d ago First seen · 137 lines · 1,897 tokens per session scan A 92146c28337a

Subscribe to this mod's changes

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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,126 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens