analytics-console-review

analytics-console-review is a skill for Claude Code from PavloSEO/seohead-seotools. It costs 82 tokens per session (1,385 once invoked), scanned A, original, MIT.

A read-only review of data in search, analytics, tag-management, and user-experience dashboards, such as Google Search Console or GA4. It uses an authorized browser session or an export supplied by the user.

In plain words
What is it for?
Use it to review search traffic, website analytics, tags, or user-behaviour reports for a specific property and time period.
Why use it?
It helps when the needed data is visible in a provider’s dashboard but no direct connection to that provider is configured. It also keeps account access and data collection within a clearly defined scope.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to review search traffic, website analytics, tags, or user-behaviour reports for a specific property and time period.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pavloseo/seohead-seotools/analytics-console-review
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 PavloSEO/seohead-seotools --skill analytics-console-review
Clone the repo
git clone --depth 1 https://github.com/PavloSEO/seohead-seotools

Made for: Claude Code.

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 analytics-console-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/analytics-console-review/github.svg)](https://agentmods.dev/skills/pavloseo/seohead-seotools/analytics-console-review)
Your own site
<a href="https://agentmods.dev/skills/pavloseo/seohead-seotools/analytics-console-review"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/analytics-console-review/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 analytics-console-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/pavloseo/seohead-seotools/analytics-console-review"><img src="https://agentmods.dev/badge/skills/pavloseo/seohead-seotools/analytics-console-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,385 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 $0.00082 $0.01385
Opus 5 $0.00041 $0.00692
Sonnet 5 $0.00016 $0.00277
Haiku 4.5 $0.00008 $0.00138

Measured 10d ago against content hash be78b2386113, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

analytics-console-review 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 10d 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.

.claude/skills/analytics-console-review/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analytics console review

Use this method when the required evidence exists in a provider console but the toolkit has no configured API client for it. The browser belongs to the agent host, not SEOHEAD Tools: this skill does not bundle a browser, open a remote service, or make a provider integration appear to exist.

Preflight

Before navigation, establish a scope ticket with:

  • provider and already-authorized account;
  • exact property, counter, container, or project;
  • report and comparison periods;
  • dimensions, metrics, filters, and search type;
  • an ignored local output directory, for example _sandbox/analytics-console-review/2026-08-30/.

If the request says only “search traffic,” ask which evidence source is intended: GSC, Bing Webmaster, Yandex Webmaster, or a web-analytics platform. Do not assume that GSC access exists.

Ask the user to handle sign-in and account selection. Never type credentials, inspect cookies or tokens, open developer storage, or switch to another property to bypass missing access.

Report one explicit readiness state before collecting data:

  • browser unavailable;
  • sign-in required;
  • property selection required;
  • access denied;
  • read view available;
  • export available;
  • export unavailable.

When sign-in, property, or access is missing, stop console work with a concise handoff:

Readiness: sign-in required | property selection required | access denied
Provider: <provider or unresolved>
Needed from the user: sign in, select <property>, approve read-only review
Proposed scope: <report>, <period A> vs <period B>, <dimensions/metrics>
First export: <smallest aggregate table>
No settings, users, tags, sitemaps, or saved reports will be changed.

Read and export boundary

The user may authorize navigation, temporary report filters, aggregate table review, and named file downloads for the scoped task. A local download is not permission to share, commit, upload, or keep the data indefinitely.

Do not collect raw session recordings, ClientID or user identifiers, cookies, authentication material, unrestricted event logs, or browser network archives. Prefer aggregate CSV/XLSX exports and record when the UI exposes only a truncated or sampled view.

Read the full file on GitHub · 138 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. 10d ago First seen · 138 lines · 82 tokens per session scan A be78b2386113

Subscribe to this mod's changes

analytics-console-review is a skill published in the GitHub repository PavloSEO/seohead-seotools (0 stars, last pushed 6d ago), licensed MIT. It adds 82 tokens to every session and 1,385 once invoked, about $0.0004 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.

Related

Other skills, from other repositories