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 Lrinvl1203/world-class-web-design-os --skill visual-qagit clone --depth 1 https://github.com/Lrinvl1203/world-class-web-design-osWrote 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/lrinvl1203/world-class-web-design-os/visual-qa)<a href="https://agentmods.dev/skills/lrinvl1203/world-class-web-design-os/visual-qa"><img src="https://agentmods.dev/badge/skills/lrinvl1203/world-class-web-design-os/visual-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/lrinvl1203/world-class-web-design-os/visual-qa"><img src="https://agentmods.dev/badge/skills/lrinvl1203/world-class-web-design-os/visual-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 | $0.00044 | $0.00371 |
| Opus 5.5 | $0.00018 | $0.00148 |
| Sonnet 5.5 | $0.00009 | $0.00074 |
| Haiku 4.5 | $0.00004 | $0.00037 |
Grade A, and why
visual-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 1mo 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.
What it actually says
Visual QA
Evidence first
Do not critique only source code. Render the real interface.
Default sequence
- ensure the target app runs;
- settle the intended capture state: await fonts, promote/decode lazy media, and disable nondeterministic motion;
- assert that critical content is visible before accepting a baseline, including in reduced-motion or JavaScript-failure states;
- capture all configured viewports;
- inspect full-page composition and first viewport separately;
- test critical interactive states;
- inspect keyboard focus and sticky/fixed overlays;
- inspect utility/micro text at native screenshot scale—technically present text can still be functionally illegible;
- test reduced-motion mode;
- check horizontal overflow and console/page errors;
- use Playwright visual baselines for stable views;
- hand screenshots to
$design-criticwithout implementation justification.
Defect format
For each issue record:
- severity: blocker / major / moderate / minor;
- viewport/state;
- observed evidence;
- design/UX impact;
- likely root cause;
- recommended correction scope: system / section / component / micro.
Stability
Visual baselines are environment-sensitive. Keep the comparison environment consistent and only update baselines after reviewing the diff. A passing pixel comparison is not evidence when its baseline recorded hidden critical content or media that had not finished decoding.
Use scripts/capture-screenshots.mjs and tests/visual.spec.ts as starters.
What ships with it
1 file 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.
- 1mo ago First seen · 44 lines · 44 tokens per session scan A 39d4fd4256c5
visual-qa is a skill published in the GitHub repository Lrinvl1203/world-class-web-design-os (8 stars, last pushed 22d ago), licensed MIT. It adds 44 tokens to every session and 371 once invoked, about $0.0002 per session on Opus 5.5. 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
a11y-ally
Use when running comprehensive WCAG accessibility audits with axe-core + pa11y + Lighthouse, generating context-aware remediation, or testing video accessibility. Supports 3-tier browser cascade with graceful degradation.
accessibility-testing
WCAG 2.2 compliance testing, screen reader validation, and inclusive design verification. Use when ensuring legal compliance (ADA, Section 508), testing for disabilities, or building accessible applications for 1 billion disabled users globally.
playwright-scanner
Internal helper: behavioral scans via Playwright for keyboard and state.
visual-regression-lab
Compare captures; stitch lazy/animated pages.
test-component
Runs, analyzes, and fixes cross-framework interaction, visual-snapshot, aria-snapshot, and accessibility tests for a specific DB UX component's showcase pages.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.