Borrowing it
Nothing to install: this file belongs to FlorianBruniaux/google-search-console-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/FlorianBruniaux/google-search-console-mcp/main/.claude/skills/onpage-audit/SKILL.mdgit clone --depth 1 https://github.com/FlorianBruniaux/google-search-console-mcpWrote 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/florianbruniaux/google-search-console-mcp/onpage-audit)<a href="https://agentmods.dev/skills/florianbruniaux/google-search-console-mcp/onpage-audit"><img src="https://agentmods.dev/badge/skills/florianbruniaux/google-search-console-mcp/onpage-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.
<a href="https://agentmods.dev/skills/florianbruniaux/google-search-console-mcp/onpage-audit"><img src="https://agentmods.dev/badge/skills/florianbruniaux/google-search-console-mcp/onpage-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00132 | $0.00819 |
| Opus 5 | $0.00066 | $0.00409 |
| Sonnet 5 | $0.00026 | $0.00164 |
| Haiku 4.5 | $0.00013 | $0.00082 |
Grade A, and why
onpage-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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
On-Page Audit
One URL in, one prioritized fix list out. Five tools, no auth beyond GSC, no quota burned on the page-level checks.
Input
A page URL. The GSC property is resolved with list_properties when the user has
not named it.
Steps
Run the five page-level tools. None of them needs Google credentials, so they run even when the property is not configured yet.
heading_audit: H1 uniqueness, level jumps, title vs H1, empty headingsinternal_links_audit: link placement by zone, footer-only targets, anchorspage_technical_audit: title and description length, canonical, robots, viewportcontent_quality: thin content, filler, information density, repetitionschema_validate: structured data present and valid
Then pull the ground truth, which is what turns findings into priorities:
content_brief: the queries this page already ranks for, and its GA4 engagementcrux_page_vitals: real-user Core Web Vitals, when the page has enough field data
The rule that overrides every finding
No destructive recommendation without the data behind it.
Before proposing to delete a page, noindex it, consolidate it into another, or strip content, read its clicks, impressions and indexing status over 90 days. A page that looks thin and generic next to a long article can still be indexed and bringing in traffic. Off-the-shelf SEO tools get this wrong routinely and recommend deleting whole sets of working local pages.
If the data says the page performs, the finding is downgraded to an observation and labelled as such. Say so out loud in the report rather than dropping it silently.
Same discipline on severity. A red flag on a page with no impressions is not urgent. A low-severity finding on the page that carries the most clicks probably is.
Output format
Verdict: one line, what state the page is in.
Where it stands today: clicks, impressions, average position, top three queries. This section comes first because it sets the weight of everything after it.
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.
- 11d ago First seen · 81 lines · 132 tokens per session scan A 2b62634f6fbc
onpage-audit is a skill published in the GitHub repository FlorianBruniaux/google-search-console-mcp (10 stars, last pushed 10d ago), licensed MIT. It adds 132 tokens to every session and 819 once invoked, about $0.0007 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.
Other skills, from other repositories
gsccli
Use when the user wants to query Google Search Console search analytics (clicks/impressions/CTR/position by query/page/country/device), inspect URL indexing status, manage sitemaps, or send Indexing API notifications via the gsccli shell command. Triggers on GSC, Search Console, sitemap, indexing API, mobile…
web-analytics
Analyze web traffic, SEO performance, and search engine trends using Google Search Console, Google Analytics 4, and Bing Webmaster Tools. Use when the user asks to analyze traffic, check SEO, or find keyword opportunities.
seo-mcp-reports
Generate professional, visually stunning SEO reports using SEO-MCP tools. Use when generating HTML/PDF SEO reports with charts, metric cards, gradient headers, and agency-quality styling. Covers weekly, monthly, quarterly, technical audit, competitive analysis, and client-friendly agency report formats. Requires…
seo
Use and read this skill immediately if the user request is in any way related to SEO or a site's organic search or AI search presence. That includes site audits, rankings, keyword research, competitors, backlinks, click or traffic changes, indexing problems, crawling, redirects, sitemaps, metadata, structured data…
bot-traffic-detection
Identify and exclude bot, scraper, and spam sessions from GA4 data.
featured-snippet-optimizer
Use when you want to win a featured snippet for a keyword you already rank for. The agent checks the current snippet format, analyzes your content, and rewrites the relevant section to match what Google wants.