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 superamped/ai-marketing-skills --skill search-page-auditgit clone --depth 1 https://github.com/superamped/ai-marketing-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/superamped/ai-marketing-skills/search-page-audit)<a href="https://agentmods.dev/skills/superamped/ai-marketing-skills/search-page-audit"><img src="https://agentmods.dev/badge/skills/superamped/ai-marketing-skills/search-page-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/superamped/ai-marketing-skills/search-page-audit"><img src="https://agentmods.dev/badge/skills/superamped/ai-marketing-skills/search-page-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 | $0.00064 | $0.01883 |
| Opus 5 | $0.00032 | $0.00941 |
| Sonnet 5 | $0.00013 | $0.00377 |
| Haiku 4.5 | $0.00006 | $0.00188 |
Grade A, and why
search-page-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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Audit
Usage
Ask your AI tool to audit a URL for search and AI readiness. You can optionally request a focus area — seo-only, geo-only, eeat-only, or content-only.
Process
Step 1: Fetch & Parse
Fetch the page at the provided URL. Extract:
- Full HTML source (for schema, meta tags, heading structure)
- Rendered page content (for content evaluation)
Then fetch these three files from the same domain:
{domain}/robots.txt— check for AI crawler directives{domain}/sitemap.xml— check for existence{domain}/llms.txt— check for existence
Step 2: SEO Fundamentals (10 checks)
Evaluate traditional SEO hygiene. These are prerequisites — if broken, nothing else matters.
- HTTPS — Page is served over HTTPS
- Title tag — Exists, 50-60 characters, descriptive
- Meta description — Exists, 150-160 characters, includes target intent
- Single H1 — Exactly one H1 tag present
- Heading hierarchy — Logical order (H1 > H2 > H3), no skipped levels, no empty headings
- Image alt text — All images have descriptive alt attributes
- Clean URL — Descriptive, readable, no excessive parameters
- Internal links — Links to and from related pages on the site
- Crawlable content — Key content in standard HTML, not hidden behind JavaScript rendering
- Page speed — No obvious performance issues (heavy uncompressed images, render-blocking scripts, excessive DOM size)
Step 3: Content Structure (10 checks)
Evaluate how well the content is structured for both human readers and AI extraction.
- Direct answer up front — Each section leads with the key insight in the first 1-2 sentences
- Question-based headings — H2s/H3s mirror how users phrase queries (What is..., How do I..., Why does...)
- Short paragraphs — 2-4 sentences per paragraph, no wall-of-text blocks
- FAQ section — Dedicated Q&A section with real customer/user questions, 1-3 sentence answers
- Comparison tables — Side-by-side content uses tables (35% higher AI extractability)
- Lists for structure — Numbered lists for processes, bullet points for features/options
- "[TERM] is..." definitions — Key concepts defined with at least two defining sentences
- Conversational keywords — 5+ natural, long-tail query variations woven into content
- Intent clusters — Covers related follow-up questions a user would likely ask next
- Multimedia — Images, video, or infographics present as content signals
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 · 184 lines · 64 tokens per session scan A 3e24723d6d09
search-page-audit is a skill published in the GitHub repository superamped/ai-marketing-skills (67 stars, last pushed 25d ago), licensed MIT. It adds 64 tokens to every session and 1,883 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 2026-08-30.
Other skills, from other repositories
newsjack-detector
Monitor current news and reaction signals, then decide which are credible newsjacking opportunities for a client. Uses the local monitoring engine for evidence, but the skill owns PR judgment, brand safety, standing, decay, angle fit, and handoff.
crisis-holding
Draft crisis holding statements, journalist Q&A posture, and what-not-to-say guidance from confirmed incident facts, with a hard legal-counsel gate. Builds each statement through proven crisis-comms frameworks (holding-statement anatomy, SCCT, CAP order, the legitimate non-answer, bridge/flag/block).
voice-extractor
Capture a user's real writing voice from 5-20 prior samples, store a local voice.yaml fingerprint, and enforce it on newsjack drafts so AI tells disappear. Measures voice with named stylometry lenses (Burrows's Delta function-word vector, MATTR lexical diversity, sentence-length burstiness, Biber Dimension-1 register…
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
fact-check
Extract factual claims from PR copy, verify each claim independently, attach concrete citations, and warn when certainty is low. Runs each claim through proven newsroom verification methods (lateral reading, source-tier climbing, provenance pillars, triangulation, calibrated rating) and puts the burden of proof on the…
pr-calendar
Turn the Medialyst PR calendar feed into a brand-specific, lead-time-aware plan. Pull source-backed upcoming moments, keep only the few a brand has real standing to own, schedule backward from the event date, screen out tone-deaf hooks, and hand selected moments to angle and journalist prep ahead of time. The planned…