yandex-webmaster-metrika

yandex-webmaster-metrika is a skill for Claude Code from antohins/seo-tools-mcp. It costs 92 tokens per session (1,199 once invoked), scanned A, original, MIT.

A connection to Yandex Webmaster and Yandex Metrica, two services for understanding search visibility and visitor behaviour. It examines search queries, rankings, indexing, site problems, and what visitors do after arriving.

In plain words
What is it for?
Use it to review Yandex search traffic, popular and page-specific queries, indexing history, site diagnostics, and visitor activity in Metrica.
Why use it?
It brings search performance and on-site behaviour together, so you can see both how people find a page and what happens next. This helps investigate falling rankings, missing pages, broken links, and weak landing-page results.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the metrika plugin — 1 skill shipped together

Good fit Use it to review Yandex search traffic, popular and page-specific queries, indexing history, site diagnostics, and visitor activity in Metrica.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/antohins/seo-tools-mcp/yandex-webmaster-metrika
Install

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.

Any agent
npx skills add antohins/seo-tools-mcp --skill yandex-webmaster-metrika
Clone the repo
git clone --depth 1 https://github.com/antohins/seo-tools-mcp

Made for: Claude Code.

Or install metrika, the plugin that ships this one along with the rest of its 1 skill.

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 yandex-webmaster-metrika

README.md
[![agentmods](https://agentmods.dev/badge/skills/antohins/seo-tools-mcp/yandex-webmaster-metrika/github.svg)](https://agentmods.dev/skills/antohins/seo-tools-mcp/yandex-webmaster-metrika)
Your own site
<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.

agentmods 80×15 button for yandex-webmaster-metrika

Your own site · 80×15
<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>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,199 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00092 $0.01199
Opus 5 $0.00046 $0.00600
Sonnet 5 $0.00018 $0.00240
Haiku 4.5 $0.00009 $0.00120

Measured 12d ago against content hash 8dc8126bbe7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

plugins/metrika/skills/yandex-webmaster-metrika/SKILL.md · 71 lines

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

  1. ywm_hostshost_id в формате https:example.com:443. Это не URL, а именно такой идентификатор; в YWM_HOST_ID кладётся он.
  2. metrika_counters → числовой counterId в METRIKA_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) есть truncated: true и offset — считать «всего» по одной выборке нельзя, для этого есть count.

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, с source: '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 вида ym:s:<name>.

Read the full file on GitHub · 71 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. 12d ago First seen · 71 lines · 92 tokens per session scan A 8dc8126bbe7e

Subscribe to this mod's changes

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.