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/lancewillett/ai-plugins/playwright-ui-checknpx skills add lancewillett/ai-plugins --skill playwright-ui-checkgit clone --depth 1 https://github.com/lancewillett/ai-pluginsWrote 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/lancewillett/ai-plugins/playwright-ui-check)<a href="https://agentmods.dev/skills/lancewillett/ai-plugins/playwright-ui-check"><img src="https://agentmods.dev/badge/skills/lancewillett/ai-plugins/playwright-ui-check.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 5.1 | $0.00094 | $0.04340 |
| Opus 5 | $0.00047 | $0.02170 |
| Sonnet 5 | $0.00019 | $0.00868 |
| Haiku 4.5 | $0.00009 | $0.00434 |
Grade C, and why
playwright-ui-check scanned grade C with 2 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 5d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
The captured username/password stay inside this process's memory — never written to disk, never printed. The visible login runs in a fresh `--profile-dir` (default `/tmp/authed-session-<timestamp>`) so a real prompt fire Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
The model is **auth once, attach many**: a human completes one visible login, a headless browser stays alive on a Chrome DevTools Protocol (CDP) port, and each run attaches to that same browser over CDP. `curl` and fresh How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright UI check
Drive a real browser against a site behind a login wall — HTTP Basic Auth, an SSO gateway, or a session cookie — and run repeatable checks (UI smoke tests, keyboard and click flows, screenshots, DOM assertions) without logging in again on every run.
The model is auth once, attach many: a human completes one visible login, a headless browser stays alive on a Chrome DevTools Protocol (CDP) port, and each run attaches to that same browser over CDP. curl and freshly launched browser profiles get a 401; a long-lived, already-authenticated browser process does not.
When to use
- The page needs a login your script can't drive — a Basic Auth prompt, an SSO redirect, 2FA.
- You'll run more than one check against the same origin and don't want to re-auth each time.
- You need real-browser behavior — JavaScript, keyboard, clicks, modals — not just an HTTP client.
- You want deterministic CLI/Node scripts rather than an interactive browser tool.
Skip it if an unauthenticated curl or a single fresh Playwright launch already reaches the page.
The model in one paragraph
Browser auth is held in the running browser process, not on disk. HTTP Basic Auth in particular lives in memory and is dropped on relaunch, so re-launching a saved profile re-prompts or fails with ERR_INVALID_AUTH_CREDENTIALS. The fix is to keep one authenticated browser process alive and reuse it: log in once, prime the origin's credential cache, expose a CDP port, and have every later run connectOverCDP and reuse the existing context. The unit of reuse is the process, not the profile directory.
Prerequisites
- Node.js and Playwright available (
npm i -D playwright, or reuse an existing install andrequire()it by absolute path if your script lives outside that install). When your scripts only ever drive the Chrome already on the machine,npm i playwright-coregives the same API without downloading browser bundles. - Chrome or Chromium.
- Pick an unused CDP port per session (e.g.
9333) and a fresh, unique profile directory per session. Both matter — see Troubleshooting. - Prefer an existing repository helper when one exists. It usually encodes the site's login and readiness behavior better than a new generic script.
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.
- 5d ago First seen · 239 lines · 94 tokens per session scan C cf274a99e009
playwright-ui-check is a skill published in the GitHub repository lancewillett/ai-plugins (2 stars, last pushed 20d ago), licensed MIT. It adds 94 tokens to every session and 4,340 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
browse
Fast headless browser for QA testing and site dogfooding. (gstack).
playwright-dev
Explains how to develop Playwright - add APIs, MCP tools, CLI commands, and vendor dependencies.
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…
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.
playwright-cli
官方Microsoft Playwright CLI网页自动化工具，支持所有主流浏览器的无头/有头自动化操作，包括页面导航、元素交互、截图、录制、测试等功能。当用户提到网页自动化、浏览器操作、爬虫、截图、录制用户操作、E2E测试时触发。.
playwright-screen-recording
Record browser test videos with Playwright for PR review and bug fix verification.