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 divyanshu-iitian/agent-website-design-skills --skill responsive-ui-qagit clone --depth 1 https://github.com/divyanshu-iitian/agent-website-design-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/divyanshu-iitian/agent-website-design-skills/responsive-ui-qa)<a href="https://agentmods.dev/skills/divyanshu-iitian/agent-website-design-skills/responsive-ui-qa"><img src="https://agentmods.dev/badge/skills/divyanshu-iitian/agent-website-design-skills/responsive-ui-qa/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/divyanshu-iitian/agent-website-design-skills/responsive-ui-qa"><img src="https://agentmods.dev/badge/skills/divyanshu-iitian/agent-website-design-skills/responsive-ui-qa.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 | $0.00628 |
| Opus 5 | $0.00032 | $0.00314 |
| Sonnet 5 | $0.00013 | $0.00126 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
responsive-ui-qa 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 11d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Responsive UI QA
Find root causes, not screenshot-specific patches. Produce evidence that the reported state works after the fix.
Workflow
- Read the repository's run and testing instructions. Start the app with its normal command.
- Build a compact test matrix:
- critical routes or components;
- default, loading, empty, error, long-content, and interactive states;
- narrow mobile, mobile, tablet or narrow container, desktop, and wide desktop as relevant.
- Reproduce the exact reported defect before editing. Capture the viewport, route, state, and interaction.
- Inspect layout mechanics: containing block, grid/flex constraints, intrinsic size, min-width, wrapping, positioning, stacking, overflow, and fixed/sticky offsets.
- Classify severity:
- Blocker - action or content is inaccessible;
- Major - interaction or comprehension is materially impaired;
- Minor - visible polish defect without task failure.
- Fix the underlying constraint with the smallest coherent change. Avoid viewport-specific offsets unless the design genuinely changes there.
- Test content stress: long labels, unbroken strings, localization expansion, missing/large media, validation text, and dynamic lists.
- Test input and preference modes: keyboard, touch-sized targets, focus visibility, zoom when feasible, and reduced motion.
- Re-run the failed case plus adjacent widths and states. Check that no new horizontal scroll or hidden content was introduced.
- Report evidence, remaining risks, and anything not testable locally.
Fix Rules
- Prefer intrinsic layout, wrapping,
minmax(),min-width: 0,max-width,aspect-ratio, and container-aware rules. - Change information architecture at breakpoints when reflow alone is insufficient.
- Do not "fix" overflow by globally hiding it or shrinking text below readability.
- Reserve fixed dimensions for controls and media with a real size contract.
- Keep fixed or sticky UI from covering focused elements and anchored content.
- Verify canvas, WebGL, video, charts, maps, and embeds by inspecting rendered pixels and resize behavior.
- Preserve behavior at the exact state that triggered the bug.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 52 lines · 64 tokens per session scan A 8b896a79c3d1
responsive-ui-qa is a skill published in the GitHub repository divyanshu-iitian/agent-website-design-skills (2 stars, last pushed 20d ago), licensed MIT. It adds 64 tokens to every session and 628 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
agent-evaluation-operations
Evaluate agent and skill behavior or routing.
frontend-quality-auditor
Audit launch readiness; report ship/no-ship.
animation-jank-qa
Diagnose a concrete rendered hitch or stutter.
browser-inspection-workflow
Coordinate rendered behavior and state evidence.
visual-regression-lab
Compare captures; stitch lazy/animated pages.
cross-browser-qa
Verify browser-engine compatibility.