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 winstonkoh87/Athena-Public --skill visual-verify-uigit clone --depth 1 https://github.com/winstonkoh87/Athena-PublicWrote 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/winstonkoh87/athena-public/visual-verify-ui)<a href="https://agentmods.dev/skills/winstonkoh87/athena-public/visual-verify-ui"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/visual-verify-ui/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/winstonkoh87/athena-public/visual-verify-ui"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/visual-verify-ui.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 | $0.00021 | $0.00208 |
| Opus 5.5 | $0.00008 | $0.00083 |
| Sonnet 5.5 | $0.00004 | $0.00042 |
| Haiku 4.5 | $0.00002 | $0.00021 |
Grade A, and why
visual-verify-ui 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 & UI Verification
Automates visual regression testing and responsive design checks by formally deploying browser tools to capture DOM states and screenshots.
Triggers
"check the UI", "does this look right", "take a screenshot"
Core Mechanics
- Boots local server if not running.
- Uses Browser tool to navigate to target URL.
- Captures full-page screenshots across Mobile, Tablet, and Desktop viewports.
- Returns visual evidence to the main protocol loop.
Reference Paths
.context/memories/protocols/engineering/99-visual-verification.md
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 · 31 lines · 21 tokens per session scan A 0300c2dbb1cc
visual-verify-ui is a skill published in the GitHub repository winstonkoh87/Athena-Public (619 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 208 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.
playwright
Use when the task requires capturing or automating a real browser from the terminal.
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
startup-qa-bot-getting-started
A guided first conversation for a product-checking assistant. It helps define a safe test environment and choose an initial check, such as following a sign-up flow or comparing two versions.
startup-qa-bot-ops
A working procedure for checking a product in a clearly separated test environment. It maintains a page map, records observations, compares known page lists, and reports reproducible problems.
startup-qa-bot-evidence
An offline comparison tool for two supplied page lists from the same test environment. It reports differences and status changes without opening a browser.