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/responsive-sweep/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/responsive-sweep)<a href="https://agentmods.dev/skills/wlsdks/ontology-atlas/responsive-sweep"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/responsive-sweep/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/responsive-sweep"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/responsive-sweep.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 | $0.00035 | $0.00821 |
| Opus 5 | $0.00017 | $0.00411 |
| Sonnet 5 | $0.00007 | $0.00164 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
responsive-sweep 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 6d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Responsive sweep
Run only when pnpm design:route includes responsive-sweep. Use its scope:
affected bands for a breakpoint-local change, the full matrix for a new surface
or information architecture.
- A breakpoint is a width where layout changes (
md768px,lg1024px). - A rect is the measured
getBoundingClientRect()geometry. - Chrome is the frame around content: header, toolbar, tab bar, and panels.
Static class reading missed three live defects: max-lg:pb-* lost to a later
md:py-* rule at 768–1023px, three chrome rows overlapped by 79px, and a tab bar
intercepted content. Only computed geometry and elementFromPoint proved them.
Width matrix
| Viewport | Band |
|---|---|
| 600×900 | phone/small portrait tablet; below md |
| 768×1024 | md boundary; side panels begin, tab bar remains |
| 834×1112 | 11-inch tablet |
| 1024×768 | lg boundary; vertical navigation begins, tab bar leaves |
| 1440×900 | 14-inch laptop; labels progressively compact |
| 1920×1080 | FHD |
| 2560×1440 | QHD |
Use the router's returned bands. A local chrome or layout repair does not independently require the full matrix. If additional breakpoints are affected, update the change facts and use the resulting scope.
Loop at each width
- Resize and navigate to a URL reproducing the exact state, such as
?index=expandedor?recent=auto. Setguides=offas a query parameter (use&when a query already exists); the first-run overlay otherwise captures everyelementFromPoint. Use?guides=resetonly when testing the guide itself. - Evaluate geometry:
- collect fixed/floating rects and calculate their intersection in pixels;
- probe the centre of every important control with
document.elementFromPoint(cx, cy)and record the intercepting element; - below
lg, compare the primary tab bar's top with the last scrolled content's bottom and every bottom-attached panel.
- Capture a screenshot for human evidence.
After the measured loop, capture at least the affected representative state with the computer-use capability and record app/window identity, accessibility owner, and saved screenshot path. Browser automation screenshots support the rect evidence but do not replace this capture.
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.
- 6d ago Changed · +2 lines 1905f8e890fc
- 8d ago Changed · +9 lines 3934d3065a7a
- 12d ago First seen · 63 lines · 35 tokens per session scan A 69409ae66cf8
responsive-sweep is a skill published in the GitHub repository wlsdks/ontology-atlas (104 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 821 once invoked, about $0.0002 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
waitlist-page
Minimal pre-launch landing with email capture, brand logo, and optional decorative layer. Reads DESIGN.md for colors, typography, and layout rules. Best for: product launches, beta signups, early access programs, indie projects.
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.
webgl-liquid-metal
A real-time liquid-metal shader — a domain-warped noise field shaded as molten chrome, with a sweeping specular highlight over an iridescent thin-film (cosine-palette) sheen. No textures. Rendered as a single self-contained index.html. Use when the brief asks for "liquid metal", "molten chrome", "iridescent"…
webgl-neon-grid
A real-time synthwave scene — a perspective floor grid scrolling toward a banded retro sun under a neon starfield, all from one fragment shader. No textures. Rendered as a single self-contained index.html. Use when the brief asks for "synthwave", "outrun", "retro 80s", "neon grid", "perspective grid", "vaporwave", or…
webgl-particle-galaxy
A real-time particle galaxy — tens of thousands of additive-blended GPU points spiraling around a bright core, their orbits solved entirely in the vertex shader (from glVertexID), so the whole cloud draws in one call. Rendered as a single self-contained index.html. Use when the brief asks for a "particle field"…
webgl-depth-gallery
A scroll-reactive 3D image gallery in Three.js: Z-stacked images crossfade over per-image mood backgrounds with velocity breath, a glowing cursor trail and an editorial CMYK/RGB/HEX/PMS color card.