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 VKirill/claude-lane-stack --skill googlegit clone --depth 1 https://github.com/VKirill/claude-lane-stackWrote 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/vkirill/claude-lane-stack/google)<a href="https://agentmods.dev/skills/vkirill/claude-lane-stack/google"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/google/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/vkirill/claude-lane-stack/google"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/google.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00147 | $0.01903 |
| Opus 5.5 | $0.00059 | $0.00761 |
| Sonnet 5.5 | $0.00029 | $0.00381 |
| Haiku 4.5 | $0.00015 | $0.00190 |
Grade A, and why
google scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Picks **one** child before writing code or curl How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google ecosystem
This SKILL.md is a router. Product knowledge lives in the child folders below. Do not answer APIs from this file.
Protocol
- Match the task to the route table.
- Read that child's
SKILL.md. - Load only that child's
references/row from its own API Reference table. - Two products → read both children. Do not merge their APIs, headers, or quotas.
Use this skill when
- Any Google product we cover: Ads, Analytics (GA4), Search Console, Tag Manager, Cloud auth
- Two or more of those in one request
- Shared Google OAuth / service account / ADC /
invalid_grant - Slash command
/google
Do not use this skill when
- Яндекс (Директ / Метрика / Вебмастер / Cloud) →
yandex - VK Ads / Telegram Ads →
telegram-ads-spec - Wordstat / live SERP XML →
seo-tools - Google Ads API (CampaignsService-style code) — no skill, do not invent one
- GCP compute / BigQuery / Gemini / nano-banana — no skill here
Route table
| Task | Child |
|---|---|
| RSA / PMax / Display / Demand Gen / лимиты 30/90, политики, РФ-бан Ads | google-ads/SKILL.md |
GA4: runReport, property_id, агрегаты, token quotas |
google-analytics/SKILL.md |
| GSC: queries, CTR, urlInspection, sitemap, Indexing API | google-search-console/SKILL.md |
| GTM: контейнер, теги/триггеры/переменные, publish, rollback, etag | google-tag-manager/SKILL.md |
OAuth / SA key.json / ADC / scopes / invalid_grant |
google-cloud-auth/SKILL.md |
Нет дочернего скилла: Google Ads API, GCP compute, BigQuery, Gemini.
Ambiguous prompts
| User says | Default | Not this |
|---|---|---|
| «позиции в Google» + свой сайт | google-search-console |
xmlstock = произвольный SERP |
| «позиции» + список ключей / чужой домен | xmlstock |
GSC only covers verified properties |
| «трафик» / «конверсии с сайта» | google-analytics |
GSC = search queries; Ads = paid |
| «статистика объявлений» / CPC / CTR ads | google-ads (кабинет) |
GA4 = on-site; нет Ads API скилла |
| «написать RSA / PMax» | google-ads |
сначала russia-context |
| «Google Ads в Россию» | google-ads → Я.Директ |
размещение в РФ недоступно |
| «запросы / индекс / sitemap Google» | google-search-console |
GA4 не знает поисковые запросы |
| «Measurement ID G-XXXX» в API | google-analytics: это не Property ID |
остановиться, взять numeric ID |
| «поставить GTM / тег / опубликовать контейнер» | google-tag-manager |
GA4 = отчёты; auth = ключи |
| «invalid_grant / SA / refresh token / ADC» | google-cloud-auth |
не чинить токен внутри GA4/GSC/GTM |
What ships with it
48 files 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.
- google-ads/references/ad-formats.md 18 KB
- google-ads/references/benchmarks.md 9.4 KB
- google-ads/references/character-limits.md 8.6 KB
- google-ads/references/creative-frameworks.md 11 KB
- google-ads/references/policies.md 11 KB
- google-ads/references/pre-launch-checklist.md 6.9 KB
- google-ads/references/REFERENCE.md 3.5 KB
- google-ads/references/russia-context.md 8.3 KB
- google-ads/references/validator-usage.md 7.5 KB
- google-ads/scripts/validate-ads.py 20 KB runs code
- google-ads/SKILL.md 16 KB
- google-analytics/references/admin-api.md 6.9 KB
- google-analytics/references/batch-and-quotas.md 7.2 KB
- google-analytics/references/errors.md 8.3 KB
- google-analytics/references/filters-and-expressions.md 7.2 KB
- google-analytics/references/integration.md 17 KB
- google-analytics/references/pivot-and-cohort.md 7.1 KB
- google-analytics/references/realtime.md 6.0 KB
- google-analytics/references/run-report.md 8.7 KB
- google-analytics/references/setup.md 7.0 KB
- google-analytics/references/workflow.md 14 KB
- google-analytics/SKILL.md 22 KB
- google-cloud-auth/references/adc.md 8.2 KB
- google-cloud-auth/references/errors.md 9.7 KB
- google-cloud-auth/references/oauth2-user-flow.md 9.4 KB
- google-cloud-auth/references/refresh-tokens.md 8.8 KB
- google-cloud-auth/references/scopes-catalog.md 8.0 KB
- google-cloud-auth/references/service-account.md 9.0 KB
- google-cloud-auth/SKILL.md 12 KB
- google-search-console/references/errors.md 4.4 KB
- google-search-console/references/indexing-api.md 3.6 KB
- google-search-console/references/integration.md 11 KB
- google-search-console/references/rate-limits.md 4.3 KB
- google-search-console/references/search-analytics.md 5.6 KB
- google-search-console/references/setup.md 4.9 KB
- google-search-console/references/sites-and-sitemaps.md 4.9 KB
- google-search-console/references/url-inspection.md 5.0 KB
- google-search-console/references/workflow.md 12 KB
- google-search-console/SKILL.md 19 KB
- google-tag-manager/references/cookbook.md 10 KB
- google-tag-manager/references/errors.md 7.9 KB
- google-tag-manager/references/resources-hierarchy.md 7.3 KB
- google-tag-manager/references/rollback.md 8.6 KB
- google-tag-manager/references/setup.md 5.7 KB
- google-tag-manager/references/tags-triggers-variables.md 7.2 KB
- google-tag-manager/references/versions-publish.md 6.6 KB
- google-tag-manager/references/workspaces.md 6.5 KB
- google-tag-manager/SKILL.md 12 KB
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.
- 1mo ago First seen · 137 lines · 147 tokens per session scan A 92b65ed33b88
google is a skill published in the GitHub repository VKirill/claude-lane-stack (122 stars, last pushed today), licensed MIT. It adds 147 tokens to every session and 1,903 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
eval-agents
Audit custom subagent definitions for Claude Code (.claude/agents/.md) and Codex (.codex/agents/.toml): loadability against the native schema, description overlap, model tier, tool scope, and headless-safe instructions. Use when onboarding to a project with agents, after adding or importing agents, or when the parent…
self-assessment
Interactive skill assessment with personalized learning path generation.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
source-command-methodology-advisor
Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.