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 JakeLabate/Claude-SEO-Skills --skill meta-data-auditgit clone --depth 1 https://github.com/JakeLabate/Claude-SEO-SkillsWrote 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/jakelabate/claude-seo-skills/meta-data-audit)<a href="https://agentmods.dev/skills/jakelabate/claude-seo-skills/meta-data-audit"><img src="https://agentmods.dev/badge/skills/jakelabate/claude-seo-skills/meta-data-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/jakelabate/claude-seo-skills/meta-data-audit"><img src="https://agentmods.dev/badge/skills/jakelabate/claude-seo-skills/meta-data-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 | $0.00086 | $0.01588 |
| Opus 5 | $0.00043 | $0.00794 |
| Sonnet 5 | $0.00017 | $0.00318 |
| Haiku 4.5 | $0.00009 | $0.00159 |
Grade A, and why
meta-data-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 12d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta Data Audit
Audit the title tags and meta descriptions of a website and produce an actionable SEO report.
When to use this skill
Use this skill when the user asks to:
- Audit or analyze title tags and meta descriptions on a website
- Find pages with missing, duplicate, or multiple titles or meta descriptions
- Find titles or descriptions that are too long (truncated in SERPs) or too short (wasted snippet space)
- Identify generic, boilerplate, or keyword-stuffed metadata
- Improve click-through rates from search by tightening SERP snippets
Inputs to collect
Before starting, confirm with the user:
- Site URL or local files — a live site root URL (e.g.,
https://example.com), a sitemap URL, a list of URLs, or a local folder of HTML files. - Scope — full site, a specific section (e.g.,
/blog/), or a list of URLs. - Crawl limits — max pages (default 500) for live crawls.
- Brand suffix — the brand pattern appended to titles (e.g.,
| Acme Co), if any, so brand-only and duplicate-after-brand titles can be detected accurately.
Workflow
Step 1: Gather the page set and extract metadata
- If a sitemap is available (
/sitemap.xml), fetch it to get the canonical page list. - Otherwise, crawl from the homepage following only same-host links.
- For local HTML folders, enumerate all
.htmlfiles.
Use scripts/extract_metadata.py to fetch pages and collect every title tag and meta description into a JSON inventory:
python3 scripts/extract_metadata.py https://example.com --max-pages 500 --output metadata_inventory.json
For every page, the inventory records: every <title> and <meta name="description"> value (including duplicates), the first <h1>, canonical URL, meta robots, and og:title/og:description for comparison.
If you've already crawled the site once into a shared page cache (e.g. as part of a full SEO audit), skip the crawl and extract from it instead — same inventory, no extra network:
python3 scripts/fetch_pages.py https://example.com --output page_cache.json # crawl once
python3 scripts/extract_metadata.py --from-cache page_cache.json --output metadata_inventory.json
What ships with it
7 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.
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.
- 12d ago First seen · 136 lines · 86 tokens per session scan A 5d5839f330bc
meta-data-audit is a skill published in the GitHub repository JakeLabate/Claude-SEO-Skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 1,588 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.
Other skills, from other repositories
seo-audit
A checklist-based SEO review for a website. SEO, or search engine optimization, is the work of improving a site so search engines can understand and rank it.
fire-your-seo-agency
A procedure for improving how a website appears in search engines and how AI answer systems find and cite it. It covers search, answer-engine, generative-AI, and Naver visibility.
geo-loop
Run one bounded eGEOagents loop iteration over a workspace domain - read the charter and fresh collector data, do ONE unit of work, write substrate artifacts, append one Timeline entry and one LOG line. Use for loop mode, /geo:loop, scheduled GEO runs, or continuous monitoring.
content-scoring
Score content against the 10 GEO criteria with evidence and prioritized fixes. Use when users ask to score, rate, evaluate, or estimate ranking strength.
competitive-analysis
Analyze AI-search competitors for a query and recommend ranking strategy. Use when users ask competitor analysis, who ranks, or competitive landscape.
validation-doctor
Check Brave Search and Chrome DevTools MCP availability and provide exact setup snippets. Use when validation dependencies are missing or uncertain.