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 akiotanaka847/qaio-desktop --skill audit-a-surfacegit clone --depth 1 https://github.com/akiotanaka847/qaio-desktopWrote 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/akiotanaka847/qaio-desktop/audit-a-surface)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/audit-a-surface"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/audit-a-surface/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/akiotanaka847/qaio-desktop/audit-a-surface"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/audit-a-surface.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 | $0.00064 | $0.02276 |
| Opus 5 | $0.00032 | $0.01138 |
| Sonnet 5 | $0.00013 | $0.00455 |
| Haiku 4.5 | $0.00006 | $0.00228 |
Grade A, and why
audit-a-surface 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 10d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit A Surface
Four possible audit surfaces. surface param picks probe;
Parameter: surface
site-seo- on-page + technical + content audit of configured domain via Semrush / Ahrefs / Firecrawl.ai-search- ChatGPT / Perplexity / Gemini / Google AI Overviews visibility probe + GEO recs.landing-page- fetch via Firecrawl, score 6 dimensions 0-3, prioritized fix list.form- flag unnecessary fields, rewrite labels + helper text, sequence by friction (non-signup forms - demo / contact / lead / checkout).
User names surface in plain English ("SEO audit", "GEO", "teardown my landing page", "fix my demo form") -> infer. Ambiguous -> ask ONE question naming 4 options.
When to use
- Explicit: "run an SEO audit", "audit AI search visibility", "GEO audit", "critique {URL}", "audit my lead form".
ai-searchtriggers: "do I show up in ChatGPT?", "are we visible in Perplexity / Gemini for our category?", "who shows up when someone asks about {category} in ChatGPT?".formtriggers: "audit my demo form", "my contact form is leaking", "this lead form is too long - what can I cut?", "rewrite the labels on this form", "review the fields on the application / checkout form".- Implicit: inside
plan-a-campaign(paid / launch) when routed landing page needs sharpening, or insidecheck-my-marketing(content-gap) when baseline site health unknown. - Per-surface cadence: site-seo weekly max, ai-search monthly max, landing-page on demand, form on demand.
Connections I need
I run external work through Composio. Before this skill runs I check that the categories below are linked. Missing -> I name the category, ask you to connect it from the Integrations tab, stop.
- Web scrape (Firecrawl) - optional. If not connected I fall back to basic HTTP fetch for
landing-page,form, and the on-page pass ofsite-seo, rougher but workable on static pages. - SEO (Semrush or Ahrefs) - on-page audit, indexation, content-fit, ranking data. Required for
site-seo- no fallback, that data is proprietary. - AI search (Perplexity / search providers) - probe ChatGPT / Perplexity / Gemini / AI Overviews for your visibility. Required for
ai-search- no useful fallback, the engines need API access.
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.
- 10d ago First seen · 164 lines · 64 tokens per session scan A e76df89db702
audit-a-surface is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 6d ago), licensed MIT. It adds 64 tokens to every session and 2,276 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 2026-08-31.
Other skills, from other repositories
magazine-web-ppt
For marketing and gtm work: bind launches, campaigns, events, and brand plans to growth and pipeline outcomes. Built around the core query "annual-marketing-plan", with GTM strategy lead judgment, buyer-ready proof, and this outcome: approve launch plan, campaign budget, or GTM motion.
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
ads
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…
attribution
When the user wants to figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model, or reconcile conflicting numbers across tools. Also use when the user mentions "attribution," "attribution model," "first-touch vs last-touch," "multi-touch," "which channel drives…
co-marketing
When the user wants to find co-marketing partners, plan joint campaigns, or brainstorm partnership opportunities. Use when the user says 'co-marketing,' 'partner marketing,' 'joint campaign,' 'who should we partner with,' 'integration marketing,' 'cross-promotion,' 'collaborate with another company,' 'partnership…
offers
When the user wants to design, construct, or improve an offer — the thing they actually sell — including value framing, bonus stacking, guarantee design, scarcity/urgency, naming, and payment structure. Also use when the user mentions 'offer,' 'offer design,' 'build an offer,' 'grand slam offer,' 'irresistible offer,'…