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 khasky/awesome-agent-skills --skill awesome-seo-auditgit clone --depth 1 https://github.com/khasky/awesome-agent-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/khasky/awesome-agent-skills/awesome-seo-audit)<a href="https://agentmods.dev/skills/khasky/awesome-agent-skills/awesome-seo-audit"><img src="https://agentmods.dev/badge/skills/khasky/awesome-agent-skills/awesome-seo-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/khasky/awesome-agent-skills/awesome-seo-audit"><img src="https://agentmods.dev/badge/skills/khasky/awesome-agent-skills/awesome-seo-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00154 | $0.06331 |
| Opus 5 | $0.00077 | $0.03166 |
| Sonnet 5 | $0.00031 | $0.01266 |
| Haiku 4.5 | $0.00015 | $0.00633 |
Grade A, and why
awesome-seo-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 today.
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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Audit
Audit a site or web codebase for how it performs in both classic search and AI/agent discovery, and whether a set of generated pages is safe to ship. It treats SEO surfaces as auditable artifacts — files, headers, markup, rendered output — not as vibes. Read-only: it reports findings and a verdict; it never writes content or edits files. For fixing the issues, hand the report to the relevant content/dev workflow.
Three audit tracks plus a re-audit mode, run the ones in scope:
- A. Technical SEO — the on-page and crawl fundamentals.
- B. Programmatic and scaled-content quality gate — is a generated page set safe from thin-content, doorway, and borrowed-reputation penalties?
- C. AI / agent readability — can LLMs, AI crawlers, and the agents acting for their users fetch, parse, cite, and operate this?
- Re-audit — diff the current surfaces against a stored baseline; this is the after-a-deploy mode.
Scope and method
- Establish scope — one page, a page type (all
/location/*), or the whole site. For a generated set, sample per cohort (page type), don't eyeball one page and generalize. - Build the URL set, and keep the count it started at — take
sitemap.xmland every sitemaprobots.txtnames, add what an internal-link crawl from the entry point reaches, then subtract what is not a page: resource extensions (.pdf,.jpg,.png,.svg,.css,.js,.xml), feed and API paths (/feed/,/wp-json/, JSON endpoints), and URLs that differ from one already in the set only by tracking parameters. Deduplicate, then cap. The count before the cap is the denominator every coverage claim is measured against; a set built without the subtraction inflates it with URLs that were never pages. - Set the budget before fetching — how many URLs, how many requests, and for a metered API how much it may spend. At the cap, stop and report where it stopped instead of quietly auditing less, and record what the run used (requests, wall time, cost) so the next re-audit can be scoped against a real number.
- Gather evidence, don't assume — fetch
robots.txt,sitemap.xml,llms.txt, page HTML (rendered and raw), the full response headers (X-Robots-Taglives there, not in the markup), the status chain, the HTML byte size, and the JSON-LD. Every finding cites the artifact it came from (file:line, a header value, a URL). A pattern match is a lead; confirm it in context. A URL that fails to fetch is recorded as a failure with its status or error — never dropped from the set, because a dropped URL is what turns a partial audit into a clean-looking one. - Persist raw pulls before synthesizing when auditing many URLs (
raw/<target>/<date>/…) so a re-audit can diff against it. - Score, gate, report — see Output.
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.
- today Changed 9ad420c18019
- 2d ago Changed · +46 lines · +24 tokens per session 49064f3aa13f
- 5d ago Changed · +2 lines · -39 tokens per session 94052190015d
- 11d ago First seen · 93 lines · 169 tokens per session scan A 40c9df0ccbcd
awesome-seo-audit is a skill published in the GitHub repository khasky/awesome-agent-skills (8 stars, last pushed yesterday), licensed MIT. It adds 154 tokens to every session and 6,331 once invoked, about $0.0008 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
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…
9router-web-fetch
Fetch URL → markdown / text / HTML via 9Router /v1/web/fetch using Ollama Cloud / Firecrawl / Jina Reader / Tavily Extract / Exa Contents. Use when the user wants to scrape a webpage, extract URL content, read article, or convert a URL to markdown.
9router-web-search
Web and X search via 9Router /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity / Xquik. Use when the user wants to search the web, find articles, or search public X posts.
9router-stt
Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.