gsc-client-audit

gsc-client-audit is a skill for Claude Code from acamolese/google-search-console-mcp. It costs 64 tokens per session (549 once invoked), scanned A, original, MIT.

A tool for producing a branded HTML search-engine-optimization audit report for a client website. SEO is the work of improving how a website appears in search engines, and Google Search Console provides data about that visibility.

In plain words
What is it for?
Use it to create white-label audit documents in English or Italian for clients, including search performance, branding, and brand-versus-non-brand analysis.
Why use it?
It turns search data and analysis into a client-ready report with the correct website, period, language, brand terms, and visual identity.

Skill for Claude Code

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

Part of the google-search-console plugin — 5 skills, 2 MCP servers shipped together

Good fit Use it to create white-label audit documents in English or Italian for clients, including search performance, branding, and brand-versus-non-brand analysis.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/acamolese/google-search-console-mcp/gsc-client-audit
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 acamolese/google-search-console-mcp --skill gsc-client-audit
Clone the repo
git clone --depth 1 https://github.com/acamolese/google-search-console-mcp

Made for: Claude Code.

Or install google-search-console, the plugin that ships this one along with the rest of its 5 skills, 2 MCP servers.

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 gsc-client-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/acamolese/google-search-console-mcp/gsc-client-audit/github.svg)](https://agentmods.dev/skills/acamolese/google-search-console-mcp/gsc-client-audit)
Your own site
<a href="https://agentmods.dev/skills/acamolese/google-search-console-mcp/gsc-client-audit"><img src="https://agentmods.dev/badge/skills/acamolese/google-search-console-mcp/gsc-client-audit/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 gsc-client-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/acamolese/google-search-console-mcp/gsc-client-audit"><img src="https://agentmods.dev/badge/skills/acamolese/google-search-console-mcp/gsc-client-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 549 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 $0.00064 $0.00549
Opus 5 $0.00032 $0.00275
Sonnet 5 $0.00013 $0.00110
Haiku 4.5 $0.00006 $0.00055

Measured 11d ago against content hash e3318b0ce732, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

gsc-client-audit 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 11d 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.

skills/gsc-client-audit/SKILL.md · 52 lines

What it actually says

White-label client audit

This produces a document someone else will read. Get the inputs right before generating it: regenerating is cheap, sending a client a report with the wrong brand terms is not.

1. Confirm the inputs

Ask for anything not already known:

  • Property — exact string. gsc_sites lists what the account can read.
  • Period — never assume. The 28-day default is rarely what a client report wants; monthly or quarterly usually is. period="last_month" gives a clean calendar month.
  • Languagelanguage="en" or language="it".
  • Brand terms — the words that mark a query as branded. Without them the first label of the domain is used, which is wrong for abbreviations, holding companies and invented names, and it silently mislabels the brand split. Ask for the brand, its common misspellings and any sub-brands.

2. Branding

Colours, logo and report name come from a branding.json. Pass it with branding_path, or place it at ~/.config/mcp-google-search-console/branding.json to apply it by default. It can also carry thresholds and a ctr_curve for a vertical that behaves differently from the default curve.

3. Generate

gsc_audit with site_url, the period, language, brand_terms, and output="both" so you get the file and the document. output_dir sets where it lands.

inspect_top_pages defaults to 10 and costs one URL Inspection call each against a 2,000/day quota; set it to 0 to skip that section entirely.

4. Hand it over

The first content block is a compact JSON summary. Use it to tell the user, in their language, what the report says: headline KPIs with their changes, how many issues by severity, the top quick wins, and the roadmap. Then give them the file path.

Read the summary before summarising it. If brand.source is domain_label, the brand terms were guessed — say so and offer to regenerate with real ones.

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. 11d ago First seen · 52 lines · 64 tokens per session scan A e3318b0ce732

Subscribe to this mod's changes

gsc-client-audit is a skill published in the GitHub repository acamolese/google-search-console-mcp (8 stars, last pushed 19d ago), licensed MIT. It adds 64 tokens to every session and 549 once invoked, about $0.0003 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.