agentmods.dev

weekly-report

weekly-report is a skill for Claude Code from BoxLab-Ltd/yandex-metrica-mcp. It costs 88 tokens per session (920 once invoked), scanned A, original, MIT.

A reporting workflow for Yandex Metrica, a web-analytics service, and optionally Yandex Webmaster, a service that reports how a site appears in search. It compares the last complete week with the week before.

In plain words
What is it for?
Use it to produce a short weekly site report covering visits, users, non-robot traffic, selected conversions, traffic sources, pages, and search information.
Why use it?
It removes the need to gather traffic, goal conversions, search health, and important changes by hand. It also states when search data is unavailable or too old.

Skill for Claude Code

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

Part of the yandex-insights plugin — 2 skills shipped together

not rated 15repo yesterday A scan 88 tokens original MIT

Good fit Use it to produce a short weekly site report covering visits, users, non-robot traffic, selected conversions, traffic sources, pages, and search information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/boxlab-ltd/yandex-metrica-mcp/weekly-report
View source ↗ BoxLab-Ltd/yandex-metrica-mcp npmjs.com
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 BoxLab-Ltd/yandex-metrica-mcp --skill weekly-report
Clone the repo
git clone --depth 1 https://github.com/BoxLab-Ltd/yandex-metrica-mcp

Made for: Claude Code.

Or install yandex-insights, the plugin that ships this one along with the rest of its 2 skills.

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 weekly-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/boxlab-ltd/yandex-metrica-mcp/weekly-report/github.svg)](https://agentmods.dev/skills/boxlab-ltd/yandex-metrica-mcp/weekly-report)
Your own site
<a href="https://agentmods.dev/skills/boxlab-ltd/yandex-metrica-mcp/weekly-report"><img src="https://agentmods.dev/badge/skills/boxlab-ltd/yandex-metrica-mcp/weekly-report/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 weekly-report

Your own site · 80×15
<a href="https://agentmods.dev/skills/boxlab-ltd/yandex-metrica-mcp/weekly-report"><img src="https://agentmods.dev/badge/skills/boxlab-ltd/yandex-metrica-mcp/weekly-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 920 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 $0.00088 $0.00920
Opus 5.5 $0.00035 $0.00368
Sonnet 5.5 $0.00018 $0.00184
Haiku 4.5 $0.00009 $0.00092

Measured yesterday against content hash 29044754dab4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

weekly-report 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 yesterday.

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/yandex-insights/skills/weekly-report/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Weekly report

A weekly report is read in a minute and acted on rarely. Its job is to say whether anything happened, not to fill a page: most weeks the honest headline is "stable". Keep it to one screen.

Sources

Metrica tools are required. Webmaster tools are optional: without them, write the Metrica part and one line saying search data (pages in search, diagnostics, Yandex clicks) was not available. If a metrica-hygiene or webmaster-audit skill is available, its rules apply.

Collect

  1. Weeks. B = the last full Monday–Sunday week (or the week the user names), A = the week before. Never include today.
  2. Counter and goals. describe_counter with include: ["settings", "goals"]. Use the owner's explicit goals (action and url types); skip auto-goals ("Автоцель: …") and "any goal" metrics.
  3. Headline. run_comparison, A vs B, filtersA/filtersB = ym:s:isRobot=='No', metrics ym:s:visits, ym:s:users, ym:s:bounceRate and ym:s:goal<id>reaches for up to three key goals. Take users from this query's totals — never sum days or rows.
  4. Movers. The same comparison by ym:s:lastsignTrafficSource, then by ym:s:startURLPath (limit ~20). Keep only rows that pass the noise bar below.
  5. Search (Webmaster). For the main host: get_hosts with hostId (pages in search, SQI), get_diagnostics (active problems — note any that started during week B), get_indexing report: "search_events" for week B (appeared / removed), search_queries report: "trend" for both weeks (shows, clicks). Note the latest data date of each; if it ends before week B, say "no Webmaster data for this week" instead of reporting it.

Noise bar

Call a change notable only if it is at least 10% and at least ~50 visits (for goals: at least 10% and 10 conversions). Below that it is "flat" or "about the same" — even if the percentage looks big on a small base (a source going 20 → 32 is +60% and still nothing). Do not round notable changes into drama either: say the number.

Read the full file on GitHub · 73 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. yesterday First seen · 73 lines · 88 tokens per session scan A 29044754dab4

Subscribe to this mod's changes

weekly-report is a skill published in the GitHub repository BoxLab-Ltd/yandex-metrica-mcp (15 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 920 once invoked, about $0.0004 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 2026-11-06.

Analytics and metricsMarketing and SEOclaudecursormcpmetrikamodel-context-protocol
Related

weekly-report compared with skills from other repositories

weekly-report next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
weekly-reportBoxLab-Ltd/yandex-metrica-mcpSkill15yesterdayMITA88Claude Code
21st-ui21st-dev/magic-mcpSkill6.4k1mo agoISCA63Claude Code
testrail-qauarlouski/testrail-mcp-serverSkill444d agoApache-2.0A70Claude Code, Codex
usage-reportergetpapi/papiSkill11yesterdayMITA57Claude Code
slack-send-safelyjtalk22/slack-mcp-serverSkill323d agoMITA65Claude Code, Codex
papi-buildgetpapi/papiSkill11yesterdayMITA26Claude Code
deployment-completeness-auditgetpapi/papiSkill11yesterdayMITA44Claude Code