Borrowing it
Nothing to install: this file belongs to 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/yandex/kit-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/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/yandex/kit-skills/agents-md)<a href="https://agentmods.dev/instructions/yandex/kit-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/yandex/kit-skills/agents-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/yandex/kit-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/yandex/kit-skills/agents-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 | $0.01861 | $0.01861 |
| Opus 5.5 | $0.00744 | $0.00744 |
| Sonnet 5.5 | $0.00372 | $0.00372 |
| Haiku 4.5 | $0.00186 | $0.00186 |
Grade A, and why
kit-skills AGENTS.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 4d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yandex Kit Skills
Repo-level contract for agents working in Yandex Kit Skills — skills that manage the Яндекс.Кит e-com cabinet from Claude Code / Codex.
Per-skill contract: each skill has its own AGENTS.md and SKILL.md. Read
the skill's SKILL.md before acting; read its AGENTS.md before editing it.
Project rules
- Public API first. Skills call API endpoints and never scrape the web
cabinet or drive a browser when an endpoint exists. Most of that is the
published API at
api.kit.yandex.net;kit-storefront-constructorand the cabinet'saskcommands run on the experimental contour/api/experimental/v1, which is outside the published reference. Say which one you mean wherever a user reads it. - Cross-platform, zero-dependency. All scripts are Python 3 стандартная
библиотека only and resolve paths with
pathlib, so they run on Windows, macOS and desktop Linux without pip installs. - Read-before-write. Mutating operations require an explicit per-operation
confirmation gate (
--confirm); prefer showing the request to the user over executing it. - No secrets. Tokens come from environment variables (e.g.
KIT_TOKEN), never printed, logged, committed, or passed as process arguments. - Production by default. The built-in base URL is the production public API.
Other contours are reachable only through
KIT_API_BASE_URL/--base-url, and no non-production host is ever hardcoded in this repo. - Compatibility. Keep
SKILL.mdfrontmatter (name,description) valid for the Agent Skills standard and keep the Codexagents/openai.yamlin sync. - No development history in this tree. These skills have not shipped yet, so every reader here is meeting them for the first time: describe how something works, never how it came to work that way. No changelog, no «now X instead of Y», no notes about what an earlier draft did. A changelog starts at release and records what changed for people who already had the previous version. Provenance of external knowledge is a different thing and stays: «проверено 2026-08-06: 404» tells the model how fresh a fact about the platform is.
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.
- 4d ago First seen · 129 lines · 1,861 tokens per session scan A 64322ba3741a
kit-skills AGENTS.md is an instructions file published in the GitHub repository yandex/kit-skills (30 stars, last pushed 3d ago), licensed MIT. It adds 1,861 tokens to every session, about $0.0074 per session on Opus 5.5. 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 2026-11-11.
kit-skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kit-skills AGENTS.mdyandex/kit-skills | Instructions file | 30 | 3d ago | MIT | A | 1,861 | Codex, OpenCode |
| vibetags com-example-service-OrderService.instructions.mdPIsberg/vibetags | Instructions file | 25 | today | MIT | A | 553 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |