google-search-console-mcp: Skill for Claude Code

.claude/skills/heading-audit/SKILL.md

heading-audit is a skill for Claude Code from FlorianBruniaux/google-search-console-mcp. It costs 123 tokens per session (560 once invoked), scanned A, original, MIT.

A check of a web page’s heading outline, including its main H1 heading and lower-level headings such as H2 and H3. It also compares the page title with the H1 and checks whether headings describe the content.

In plain words
What is it for?
Use it to review heading levels, count H1 headings, find jumps in the outline, assess heading descriptions, and identify overly long sections.
Why use it?
It reveals duplicated, missing, empty, or badly ordered headings that can make a page harder for people and search engines to understand.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is FlorianBruniaux/google-search-console-mcp's own configuration. It tells Claude Code how to work on google-search-console-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything google-search-console-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/FlorianBruniaux/google-search-console-mcp/main/.claude/skills/heading-audit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/FlorianBruniaux/google-search-console-mcp

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 heading-audit

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/florianbruniaux/google-search-console-mcp/heading-audit"><img src="https://agentmods.dev/badge/skills/florianbruniaux/google-search-console-mcp/heading-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 560 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 $0.00123 $0.00560
Opus 5 $0.00062 $0.00280
Sonnet 5 $0.00025 $0.00112
Haiku 4.5 $0.00012 $0.00056

Measured 11d ago against content hash c2d423f3ad97, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

heading-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.

.claude/skills/heading-audit/SKILL.md · 59 lines

What it actually says

Heading Audit

Headings and internal links are the two levers that move a page without touching anything else. This audit covers the headings half.

Input

A page URL.

Steps

  1. Call heading_audit on the target URL. No auth needed, no quota consumed.
  2. Check h1_count. Zero or two and above is the first thing to fix.
  3. Read hierarchy_jumps. An H2 followed by an H4 breaks the outline.
  4. Check title_h1_identical and title_h1_overlap. A title that repeats the H1 word for word wastes a free second angle on the target keyword.
  5. Read empty_headings and descriptive_ratio. The test to apply: can someone understand the page by reading only its headings?
  6. Check words_per_h2. Past 400, the page reads as a wall.

Cross-reference before rewriting a title

Call content_brief on the page to get the queries it already ranks for. Rewrite the title around a query the H1 does not already cover, not around a guess. If the page has impressions on a question query, that phrasing belongs in an H2.

Output format

Verdict: healthy or issues_found.

Structure: H1 count, heading count, words per H2, descriptive ratio.

Outline as it reads today: the headings in document order, indented by level. Then state plainly whether the page is understandable from that outline alone.

Title vs H1:

  • Current title
  • Current H1
  • Overlap score
  • If identical, propose a rewritten title covering a second angle

Priority list:

  1. Critical: missing or duplicated H1
  2. High: level jumps, no H2 on a long page
  3. Medium: headings that carry no information
  4. Low: subheading density

Rewrites are proposed as concrete text, not as advice to "improve the heading".

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 · 59 lines · 123 tokens per session scan A c2d423f3ad97

Subscribe to this mod's changes

heading-audit is a skill published in the GitHub repository FlorianBruniaux/google-search-console-mcp (10 stars, last pushed 9d ago), licensed MIT. It adds 123 tokens to every session and 560 once invoked, about $0.0006 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.