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 antohins/seo-tools-mcp --skill yandex-webmaster-metrikagit clone --depth 1 https://github.com/antohins/seo-tools-mcpWrote 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/antohins/seo-tools-mcp/yandex-webmaster-metrika)<a href="https://agentmods.dev/skills/antohins/seo-tools-mcp/yandex-webmaster-metrika"><img src="https://agentmods.dev/badge/skills/antohins/seo-tools-mcp/yandex-webmaster-metrika/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/antohins/seo-tools-mcp/yandex-webmaster-metrika"><img src="https://agentmods.dev/badge/skills/antohins/seo-tools-mcp/yandex-webmaster-metrika.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 | $0.00092 | $0.01199 |
| Opus 5 | $0.00046 | $0.00600 |
| Sonnet 5 | $0.00018 | $0.00240 |
| Haiku 4.5 | $0.00009 | $0.00120 |
Grade A, and why
yandex-webmaster-metrika 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Яндекс: Вебмастер + Метрика
Два сервиса на одном OAuth-приложении Яндекса, но токены разные — авторизоваться нужно
дважды (ywm_oauth_start/finish, metrika_oauth_start/finish). Вебмастер отвечает на
«что происходит в поиске», Метрика — «что дальше делает пришедший человек».
Настройка
ywm_hosts→host_idв форматеhttps:example.com:443. Это не URL, а именно такой идентификатор; вYWM_HOST_IDкладётся он.metrika_counters→ числовойcounterIdвMETRIKA_COUNTER_ID.
Вебмастер: что где брать
ywm_summary— быстрый снимок: ИКС, страниц в поиске, исключено, число проблем.ywm_popular— топ-запросы хоста за неделю (до 3000). Фильтра по URL здесь нет.ywm_search_queries— запросы по конкретному URL, окно по умолчанию около двух недель.ywm_recommended_queries— недобранные запросы по URL. Это аппроксимация: в API v4 нет «рекомендованных», инструмент собирает три категории — показы без кликов, позиции на грани топа и запросы с низким CTR. Так и подавать пользователю, не как официальный список Яндекса.ywm_queries_history— суммарная динамика (показы, клики, средние позиции) по датам.ywm_indexing_history— сколько страниц в поиске по датам (окно по умолчанию 30 дней).ywm_sqi_history— история ИКС (по умолчанию 180 дней). ИКС обновляется редко и рывками: ежедневная динамика по нему бессмысленна.ywm_diagnostics,ywm_broken_links,ywm_important_urls,ywm_sitemaps— техническая часть. У выборок (external_links,broken_links) естьtruncated: trueиoffset— считать «всего» по одной выборке нельзя, для этого естьcount.
Метрика: что где брать
metrika_traffic_sources— визиты по каналам (organic,direct,ad,referral…).metrika_top_landings— топ посадочных из органики.metrika_landing_behavior— поведение по конкретной посадочной, сsource: 'organic'и достижениями целей (goalIds; список —metrika_goals).metrika_search_phrases— поисковые фразы по посадочной. В основном Яндекс: Google свои запросы шифрует, поэтому по нему тут почти пусто, и это не поломка.metrika_report/metrika_bytime— произвольные отчёты Stat API, имена видаym:s:<name>.
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 · 71 lines · 92 tokens per session scan A 8dc8126bbe7e
yandex-webmaster-metrika is a skill published in the GitHub repository antohins/seo-tools-mcp (3 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 1,199 once invoked, about $0.0005 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 skills, from other repositories
yandex-webmaster
Loaded automatically when the description matches the active task. Read only the section you need, then follow the link to the relevant reference file.
mutagen
Skill "mutagen" from VKirill/claude-lane-stack, covering 🎯 version requirements (august 2026), usage, use this skill when, do not use this skill when and purpose.
xmlstock
Skill "xmlstock" from VKirill/claude-lane-stack, covering 🎯 version requirements (august 2026), usage, use this skill when, do not use this skill when and purpose.
google-search-console
Skill "google-search-console" from VKirill/claude-lane-stack, covering version requirements (may 2026), usage, use this skill when, do not use this skill when and purpose.
marketing-skills
42 marketing agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and 6 more coding agents. 7 pods: content, SEO, CRO, channels, growth, intelligence, sales. Foundation context + orchestration router. 27 Python tools (stdlib-only).
yandex-workspace
Guide for agents using the Yandex Workspace MCP server.