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 agentmods add skills/mrhinkle/vibecoding-a-website/qa-testernpx skills add mrhinkle/VibeCoding-a-Website --skill qa-testergit clone --depth 1 https://github.com/mrhinkle/VibeCoding-a-WebsiteWrote 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/mrhinkle/vibecoding-a-website/qa-tester)<a href="https://agentmods.dev/skills/mrhinkle/vibecoding-a-website/qa-tester"><img src="https://agentmods.dev/badge/skills/mrhinkle/vibecoding-a-website/qa-tester.svg" alt="Measured on agentmods" 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 | $0.00092 | $0.03016 |
| Opus 5 | $0.00046 | $0.01508 |
| Sonnet 5 | $0.00018 | $0.00603 |
| Haiku 4.5 | $0.00009 | $0.00302 |
Grade A, and why
qa-tester 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 4d 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 — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Tester: Complete Website Quality Assurance
You're about to launch or update your site. Before it goes live, you need one unified quality gate — not a dozen separate audits, but a comprehensive walkthrough that answers the real question: Does this thing actually work?
That's what the QA Tester does. It's the final gatekeeper.
Why QA Testing Matters
Individual audits (link checker, SEO, performance, accessibility) each answer narrow questions. But they don't tell you if your site is usable. QA testing does. It catches the intersection of failures: broken forms that pass validation, pages that load but feel broken, third-party scripts that silently fail, mobile designs that look good but aren't tappable.
This skill walks through your entire site systematically and hands you a report with clear, fixable issues.
Test Categories
1. Page Rendering
Every page on your site should load cleanly.
- All pages return HTTP 200 (or appropriate 3xx redirects, never 404 on purpose)
- No blank pages, broken images, or missing content
- Layout doesn't break at standard viewport widths (320px, 768px, 1024px, 1440px+)
- No console errors or warnings that suggest rendering failures
- Flash of unstyled content (FOUC) doesn't disorient users
Why it matters: A page that loads but looks broken tanks conversions and signals poor quality.
2. Cross-Browser Testing
Your site works in modern browsers, not just the one you tested in.
- Chrome/Edge: Latest version — test on Windows and macOS
- Safari: Test on both macOS and iOS (different rendering engines)
- Firefox: Latest version — often catches CSS edge cases others miss
- Check: form submission, JavaScript execution, CSS layout, video playback, animations
Why it matters: 10-15% of traffic still uses Safari or Firefox. Broken in one browser = lost customers.
3. Mobile & Responsive Testing
Half your traffic is mobile. Your site must work there.
- Viewport meta tag is present and correct:
<meta name="viewport" content="width=device-width, initial-scale=1"> - No horizontal scrolling on mobile (ever)
- Touch targets are at least 48x48px (easy to tap, not tiny)
- Buttons and links are tappable, not overlapped by modals or sticky headers
- Images scale correctly; no text is cut off
- Forms are mobile-friendly: single-column layout, large input fields
- Test at actual device sizes: 320px, 375px, 768px, 1024px, 1440px
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.
- 4d ago First seen · 328 lines · 92 tokens per session scan A 1677e2f4469f
qa-tester is a skill published in the GitHub repository mrhinkle/VibeCoding-a-Website (11 stars, last pushed 4mo ago), licensed MIT. It adds 92 tokens to every session and 3,016 once invoked, about $0.0005 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
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
solopi-ai
通过 SoloPi 的机器可读 CLI 编译和执行 AI 验证计划，管理签名端侧 ExecuTorch 决策模型、持久设备池、无人值守任务、安卓设备、应用、动作、配置、用例步骤与交互录制、回放及性能历史、动态 Agent、批量与重复执行、性能监控、压力测试和证据。适用于需求/AC 到 Result Judge 三态结论、cloud/on-device 决策切换、模型发布门禁，以及 generation 租约的多设备 CI 执行。.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
local-frontend-check
Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.
pr-integration-test
Design, implement, and validate Intelligent Terminal integration tests for a target pull request or regression. Use when asked to add PR integration tests, convert a bug fix into E2E coverage, prove existing behavior still works, map tests to the release checklist, or verify E2E reports mark checklist cases complete.