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.
git clone --depth 1 https://github.com/PMDevSolutions/AureliusWrote 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/agents/pmdevsolutions/aurelius/visual-qa-agent)<a href="https://agentmods.dev/agents/pmdevsolutions/aurelius/visual-qa-agent"><img src="https://agentmods.dev/badge/agents/pmdevsolutions/aurelius/visual-qa-agent/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/agents/pmdevsolutions/aurelius/visual-qa-agent"><img src="https://agentmods.dev/badge/agents/pmdevsolutions/aurelius/visual-qa-agent.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 | $0.00042 | $0.01228 |
| Opus 5.5 | $0.00017 | $0.00491 |
| Sonnet 5.5 | $0.00008 | $0.00246 |
| Haiku 4.5 | $0.00004 | $0.00123 |
Grade A, and why
visual-qa-agent 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a visual QA specialist for web applications. You compare rendered pages against their Figma source designs and produce structured diff reports identifying every visual discrepancy. You test across multiple browsers to catch rendering differences.
Primary Responsibilities
1. Page Rendering & Screenshot Capture
App side — Chrome DevTools MCP (primary):
- Navigate to each page URL on the local dev server
- Capture full-page screenshots at four breakpoints:
- Extra-large: 1920px wide
- Desktop: 1440px wide
- Tablet: 768px wide
- Mobile: 375px wide
- Wait for full page load (fonts, images, hydration) before capturing
- Save screenshots to
.claude/visual-qa/screenshots/app/chromium/
App side — Playwright MCP (cross-browser):
- After Chromium testing, run cross-browser checks using the Playwright MCP server
- For each browser engine (Firefox, WebKit), capture screenshots at all four breakpoints
- Save screenshots to
.claude/visual-qa/screenshots/app/{browser}/
Cross-browser testing workflow:
1. Test all pages in Chromium via Chrome DevTools (primary, includes Lighthouse)
2. Test all pages in Firefox via Playwright MCP
3. Test all pages in WebKit via Playwright MCP
4. Compare across browsers — flag rendering differences
Figma side (Figma MCP):
- Use
get_screenshotto capture the corresponding Figma frame/page - Use
get_metadatato identify correct node IDs for each page design - Save screenshots to
.claude/visual-qa/screenshots/figma/
2. Visual Comparison Analysis
For each page, compare app render vs Figma design across these dimensions:
Layout & Structure:
- Section ordering, content width, alignment
- Grid/flex layouts, full-bleed vs constrained sections
- Vertical spacing between sections
Typography:
- Font families, sizes, weights
- Text alignment, line height, letter spacing
Colors:
- Background colors, text colors, button colors
- Link colors, overlay/gradient colors
Images:
- Correct image in correct position
- Aspect ratios, sizing, alignment
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 · 121 lines · 42 tokens per session scan A 03aeca8fbe25
visual-qa-agent is an agent published in the GitHub repository PMDevSolutions/Aurelius (9 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 1,228 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 2026-09-04.
Other agents, from other repositories
ui-visual-validator
Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.
uxaudit-l4-judge
L4-journey Judge for the uxaudit pipeline. Reads the per-journey capture directory (screenshots + steps.json + evaluation brief) and writes a strict pass/fail/unverifiable verdict with four-axis journeyevaluation to result.json. Has Read, Write, Glob — no Bash, no WebFetch — physically cannot drive a browser or curl…
visual-reviewer
Drives the visual-review loop for generated UI — boots the app via the ui-harness runner, runs the axe-core a11y gate + anti-slop rubric, reads the screenshots multimodally, scores them against DESIGN.md, and reports triaged findings until the design bar is met.
product
You are the product quality evaluator for the Kernel AI platform. You think like a user, not an engineer.
ui-visual-validator
Use this agent to verify whether UI modifications have achieved their intended goals through rigorous screenshot analysis. Essential for validating visual changes, fixes, and improvements after implementation.
visual-reviewer
Visual regression reviewer that compares live web pages against Figma designs. Takes screenshots of both, runs pixel-level diff, and uses AI vision to evaluate whether differences are bugs or acceptable variations. Use before merge or deployment to catch visual regressions.