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-landing-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-landing-audit)<a href="https://agentmods.dev/skills/khasky/awesome-agent-skills/awesome-landing-audit"><img src="https://agentmods.dev/badge/skills/khasky/awesome-agent-skills/awesome-landing-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-landing-audit"><img src="https://agentmods.dev/badge/skills/khasky/awesome-agent-skills/awesome-landing-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 | $0.00121 | $0.02376 |
| Opus 5 | $0.00060 | $0.01188 |
| Sonnet 5 | $0.00024 | $0.00475 |
| Haiku 4.5 | $0.00012 | $0.00238 |
Grade A, and why
awesome-landing-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 yesterday.
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Landing Audit
Audit a landing or marketing page for the structural conversion mechanics — the things you can observe in the rendered DOM, the form markup, and the layout — not the persuasiveness of the words. Read-only: it reports findings and a per-page verdict; it never rewrites copy or edits files. Treat the page as an auditable artifact (elements, attributes, JSON-LD, layout behavior), not as vibes. Every finding cites the signal it came from.
This is not a copy critique. "The headline is weak" is out of scope; "there are three equally-weighted primary CTAs above the fold" is in scope because you can point at the three buttons.
Scope and method
- Establish scope — one page, or a set of variants / audience pages. Audit each page as its own unit; a template shared across many URLs is audited once per distinct layout.
- Gather evidence — pull the rendered HTML (the state a visitor sees), the form markup, and the inbound context you were given (ad copy,
utm_*params, referring query). Note the viewport you evaluated the fold at (e.g.1366×768desktop,390×844mobile) — "above the fold" is meaningless without one. - Check the eight mechanics below — each maps to an observable signal. A signal you cannot observe (no ad copy supplied → can't judge message match) is
NOT ASSESSED, never a guess. - Score, gate, report — one SHIP / FIX / BLOCK verdict per page. See Output.
Done when: the evaluated viewport is stated, all eight mechanics carry a verdict or a NOT ASSESSED, and every finding points at a signal observable on the page.
The eight mechanics
| # | Check | Observable signal | Fails when |
|---|---|---|---|
| 1 | Single primary CTA per view | Count visually-primary CTAs (same weight/color/size) above the fold and per scroll section | Two-plus co-equal primary buttons compete in one view (Buy + Book demo + Download, all identical) |
| 2 | One conversion goal per page | Distinct destinations the primary CTAs point to | Page funnels to several unrelated goals (trial + newsletter + demo + contact) with no hierarchy |
| 3 | Above-the-fold value | Is an outcome headline + primary CTA visible without scrolling at the stated viewport? | Fold shows only logo/generic tagline; the value proposition and CTA sit below the fold |
| 4 | Message match | Compare inbound intent (ad text, utm_campaign, query) to the <h1>/hero |
Scent break — ad promises "50% off invoicing", hero says "Welcome to Acme" |
| 5 | Form-field friction | Count required inputs; check for email-first + hidden attribution fields |
Long required form on first touch; UTM/source asked of the user instead of captured as hidden inputs |
| 6 | Trust / social-proof presence | DOM elements + JSON-LD: logos, testimonials with attribution, case studies, Review/AggregateRating, security badges |
No trust element of any kind on a page asking for money or contact details |
| 7 | CLS-safe banners/interstitials | Layout behavior on inject: does the top strip / cookie bar / promo reserve height? | Banner injected into normal flow pushes content after paint (layout shift); or an interstitial covers content on first paint (mobile). This mechanic audits the structural cause (unreserved space); measuring the CLS metric itself at field p75 is awesome-performance-audit Track F |
| 8 | Image specificity and integrity | <img>/<picture> attributes and subjects: dimensions or aspect-ratio present; hero/product imagery shows the actual product/UI |
Product or hero imagery is generic atmospheric stock where the visitor needs to inspect the offer; images lack width/height (shift on load); a failed image leaves a raw broken-image icon in a conversion-critical slot |
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.
- yesterday Changed e270f1b2610a
- 3d ago Changed e5a55fc26c0d
- 6d ago Changed · +2 lines · -29 tokens per session fd867effe832
- 12d ago First seen · 101 lines · 150 tokens per session scan A ab6911e4eee2
awesome-landing-audit is a skill published in the GitHub repository khasky/awesome-agent-skills (8 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 2,376 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.
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-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.
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.
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.