Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/kevintsai1202/teaching-site-skillsnpx agentmods add skills/kevintsai1202/teaching-site-skills/web-visual-verificationWrote 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/kevintsai1202/teaching-site-skills/web-visual-verification)<a href="https://agentmods.dev/skills/kevintsai1202/teaching-site-skills/web-visual-verification"><img src="https://agentmods.dev/badge/skills/kevintsai1202/teaching-site-skills/web-visual-verification/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/kevintsai1202/teaching-site-skills/web-visual-verification"><img src="https://agentmods.dev/badge/skills/kevintsai1202/teaching-site-skills/web-visual-verification.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 | $0.00185 | $0.02966 |
| Opus 5 | $0.00093 | $0.01483 |
| Sonnet 5 | $0.00037 | $0.00593 |
| Haiku 4.5 | $0.00018 | $0.00297 |
Grade A, and why
web-visual-verification 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 10d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Visual Verification
Schema authority: when verifying that data renders correctly, the source-of-truth field names come from
_shared/domain-primitives.md. E.g. assertingunit.illustrations.length >= 1matches §11's Coverage Floor.Reference implementation:
d:/GitHub/ai-workshop/scripts/verify-*.mjsfor production verify-script patterns (multi-viewport, console-error capture, screenshot-on-fail).
This skill produces Playwright-based runtime verification scripts that drive the actual rendered site and answer "does it behave correctly?". The skill emerged from a teaching-website project but applies to any static or dynamic web UI.
When to Invoke
- After any interaction-layer change (Stage 4 interactions, sidebar logic, theme, zoom).
- After any visual asset change (Stage 5 — illustrations, screenshots).
- After any layout / CSS change ("the sidebar collapsed weirdly", "the modal lost its backdrop").
- Before tagging a release or handing off a corporate edition.
- When the user asks "did that change break anything else?".
Do NOT invoke for file/data consistency checks (use web-content-audit).
The Four Script Roles — Use the Right One
Every Playwright script in this skill has exactly one of these jobs. Mixing roles produces unmaintainable scripts.
| Role | Prefix | Has assertions? | Outputs | When to use |
|---|---|---|---|---|
| Verify | verify-*.mjs |
Yes (assert.*) |
Pass/fail + screenshots | Default — runtime regression check |
| Capture | capture-*.mjs |
No | Screenshots only | Need visual evidence without judgement (design review, change log) |
| Diagnose | diagnose-*.mjs |
No (but logs heavily) | Console dump + DOM tree + screenshots | When a verify failed and you need to figure out why |
| Probe | check-*.mjs, find-*.mjs |
Targeted, often ad-hoc | Console output | Quick CLI: "does this string appear?", "where is element X?" |
The discipline: a verify script must fail loudly. A capture script must never fail (it's just evidence). A diagnose script is exploratory. A probe is a one-liner replacement for browser devtools.
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.
- 10d ago First seen · 258 lines · 185 tokens per session scan A 55d29c67b726
web-visual-verification is a skill published in the GitHub repository kevintsai1202/teaching-site-skills (49 stars, last pushed 3mo ago), licensed MIT. It adds 185 tokens to every session and 2,966 once invoked, about $0.0009 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
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…