Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nebelov/yandex-direct-for-all --skill yandex-wordstatgit clone --depth 1 https://github.com/nebelov/yandex-direct-for-allWrote 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/skills/nebelov/yandex-direct-for-all/yandex-wordstat)<a href="https://agentmods.dev/skills/nebelov/yandex-direct-for-all/yandex-wordstat"><img src="https://agentmods.dev/badge/skills/nebelov/yandex-direct-for-all/yandex-wordstat/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/skills/nebelov/yandex-direct-for-all/yandex-wordstat"><img src="https://agentmods.dev/badge/skills/nebelov/yandex-direct-for-all/yandex-wordstat.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 | $0.00053 | $0.01659 |
| Opus 5 | $0.00026 | $0.00830 |
| Sonnet 5 | $0.00011 | $0.00332 |
| Haiku 4.5 | $0.00005 | $0.00166 |
Grade A, and why
yandex-wordstat 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 12d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yandex Wordstat API v2
Этот файл не задает порядок сбора семантики, смысловые решения, минус-слова, структуру кампаний или готовность к сборке.
Для любых задач Яндекс.Директа, ключевых фраз, SQR, семантики и стоп-слов сначала открыть yandex-direct-unified, его обязательные references и keyword-collection-runbook.md. Этот файл использовать только как справочник по текущему Wordstat API.
Канонический транспорт
- Базовый адрес:
https://searchapi.api.cloud.yandex.net. - Текущая версия: синхронный REST API v2.
- Старый
https://api.wordstat.yandex.net/v1/*и методuserInfoне использовать. folderIdпередается в теле каждого запроса.- Для локального клиента рабочий сбор идет по целевому гео; вся Россия может использоваться только как явно обозначенный фон.
Авторизация
Разрешены два варианта:
- API-ключ: заголовок
Authorization: Api-Key <key>. - IAM-токен: заголовок
Authorization: Bearer <iam-token>.
Для API-ключа нужна область yc.search-api.execute, а сервисному аккаунту или пользователю — роль search-api.webSearch.user на нужный каталог.
Секреты нельзя печатать, передавать в аргументах процесса или сохранять в raw/manifest. Канонический credential-файл должен находиться в закрытом каталоге 700, иметь владельца рабочего пользователя и права 600.
Общие перечисления
Устройства:
DEVICE_ALL;DEVICE_DESKTOP;DEVICE_PHONE;DEVICE_TABLET.
Если передается список devices, в нем не более трех значений. Для topRequests и dynamics список regions содержит не более 100 строковых ID.
Методы
POST /v2/wordstat/topRequests
Назначение: спрос за последние 30 дней, популярные вложенные фразы и ассоциации.
Запрос:
{
"phrase": "обязательная фраза до 400 символов",
"numPhrases": 2000,
"regions": ["регион"],
"devices": ["DEVICE_ALL"],
"folderId": "каталог"
}
numPhrases: от 1 до 2000.
Ответ:
{
"totalCount": 0,
"results": [{"phrase": "...", "count": 0}],
"associations": [{"phrase": "...", "count": 0}]
}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 178 lines · 53 tokens per session scan A 5f6665852329
yandex-wordstat is a skill published in the GitHub repository nebelov/yandex-direct-for-all (21 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,659 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
stss
Reduce defensive disclaimers, stacked hedging, and self-protective narration in proposals and decision-facing writing. Use when the user asks to rewrite or audit a proposal, plan, research contribution, executive summary, or similar text for directness. Do not use for ordinary code work or unrelated prose.