Borrowing it
Nothing to install: this file belongs to wlsdks/ontology-atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/wlsdks/ontology-atlas/main/.agents/skills/design-audit/SKILL.mdgit clone --depth 1 https://github.com/wlsdks/ontology-atlasWrote 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/wlsdks/ontology-atlas/design-audit)<a href="https://agentmods.dev/skills/wlsdks/ontology-atlas/design-audit"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/design-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/wlsdks/ontology-atlas/design-audit"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/design-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 | $0.00026 | $0.01447 |
| Opus 5 | $0.00013 | $0.00724 |
| Sonnet 5 | $0.00005 | $0.00289 |
| Haiku 4.5 | $0.00003 | $0.00145 |
Grade A, and why
design-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 3d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Measure a finished UI change
People and models localize small spacing, alignment, and overlap defects poorly by sight. An unlocalized feeling cannot become a reliable fix, while imagined defects damage healthy code. The fixed order is: measure → list violations → attach screenshots as evidence.
Run only when pnpm design:route includes design-audit. Audit its returned
scope: one affected state for a local change, affected map state for topology,
or the full surface for a structural change. Copy-only, pure logic, motion-only,
and topology-gesture-only work use their own routed proof.
0. Fix the state
Use a fixed viewport and dataset, wait for fonts and one explicit ready element,
move the pointer off interactive targets, and use reduced motion for a static
audit. Do not use networkidle as the default readiness signal; hydration can
still be incomplete.
Add ?guides=off. Closing a first-run guide manually changes focus and adds its
own motion. Use ?guides=reset only when auditing the guide. Playwright may call
the shared seedFirstRunSeen(page) helper.
1. Overlap and reachability
Filter to painted elements
A non-zero rect does not mean the element is painted. Children inside a closed
<details> retain visible styles and a healthy rect while absent from the screen.
The first audit without this filter produced three false findings.
const painted = (el) => {
const c = getComputedStyle(el);
const b = el.getBoundingClientRect();
if (b.width < 1 || b.height < 1) return false;
if (c.visibility === 'hidden' || c.display === 'none' || Number(c.opacity) < 0.05) return false;
if (el.closest('details:not([open])')) return false;
for (let n = el.parentElement; n && n !== document.body; n = n.parentElement) {
const nc = getComputedStyle(n);
const r = n.getBoundingClientRect();
if (nc.overflow !== 'visible' && (b.bottom < r.top || b.top > r.bottom)) return false;
if (nc.contentVisibility === 'hidden' || n.hasAttribute('inert')) return false;
}
return b.top < innerHeight && b.bottom > 0 && b.left < innerWidth && b.right > 0;
};
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.
- 3d ago Changed eae674bfa380
- 8d ago Changed · +14 lines a3869109aa02
- 12d ago First seen · 138 lines · 26 tokens per session scan A adfa98b48c4d
design-audit is a skill published in the GitHub repository wlsdks/ontology-atlas (104 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,447 once invoked, about $0.0001 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
web-prototype
General-purpose desktop web prototype. Single self-contained HTML file built by copying the seed assets/template.html and pasting section layouts from references/layouts.md. Default for any landing / marketing / docs / SaaS page when no more specific skill matches.
velar-luxury-real-estate
Use this plugin when the user wants a high-end luxury real-estate / architecture landing page with cinematic scroll choreography: a typewriter preloader that lifts away, a scroll-driven house image that rises from below and scales up while pinning to a dark statement section, a sticky dark stats band with count-up…
mockup-device-3d
Static iPhone and MacBook 3D-style showcase with real HTML embedded on screens, glass-lens refraction, and 360-degree turntable composition.
web-prototype-taste-brutalist
Swiss industrial-print web prototype. Newsprint canvas, monolithic black grotesque, viewport-bleeding numerals, hairline grid dividers, hazard-red accent, ASCII syntax decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Swiss Industrial Print mode).
web-prototype-taste-editorial
Editorial-minimalist web prototype. Warm monochrome canvas, serif display + grotesque body, 1px hairline borders, muted pastel chips, generous macro-whitespace, ambient micro-motion. Distilled from Leonxlnx/taste-skill minimalist-skill.
web-prototype-taste-soft
Apple-tier soft web prototype. Silver/cream canvas, double-bezel cards, button-in-button CTAs, generous squircle radii, spring motion, ambient mesh. Distilled from Leonxlnx/taste-skill soft-skill + sections 4–8 of taste-skill.