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 dublyo/saas-skills --skill playwright-website-testergit clone --depth 1 https://github.com/dublyo/saas-skillsWrote 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/dublyo/saas-skills/playwright-website-tester)<a href="https://agentmods.dev/skills/dublyo/saas-skills/playwright-website-tester"><img src="https://agentmods.dev/badge/skills/dublyo/saas-skills/playwright-website-tester/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/dublyo/saas-skills/playwright-website-tester"><img src="https://agentmods.dev/badge/skills/dublyo/saas-skills/playwright-website-tester.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 | $0.00088 | $0.01412 |
| Opus 5 | $0.00044 | $0.00706 |
| Sonnet 5 | $0.00018 | $0.00282 |
| Haiku 4.5 | $0.00009 | $0.00141 |
Grade A, and why
playwright-website-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 11d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright Website Tester
Operating Rule
Use the Playwright plugin, not the Chrome extension connector. Treat the browser context as fresh and separate from the user's existing Chrome profile. If a site requires authentication, tell the user they may need to log in from scratch inside the Playwright-controlled browser; never ask them to paste passwords or 2FA codes into chat.
Skip Lighthouse by default. Focus on Playwright-observable evidence: page behavior, console messages, failed network requests, accessibility snapshots, screenshots, desktop/mobile layout, and user-flow results.
Required References
Read references/report-template.md before producing a substantial QA report.
Use scripts/website_qa_checklist.py when planning deep or repeated QA. The path uses ${CLAUDE_SKILL_DIR} (this skill's own directory); if that variable is not set, substitute the absolute path to this skill's scripts/ folder.
python3 "${CLAUDE_SKILL_DIR}/scripts/website_qa_checklist.py" --depth deep --auth unknown
Playwright Plugin Surface
Use these Playwright plugin tools when available.
Observation and setup:
browser_tabs- create/select/close/list tabs. Use a new tab for fresh checks.browser_navigate/browser_navigate_back- move to the target URL and between routes.browser_resize- switch desktop and mobile viewport sizes.browser_snapshot- inspect accessible structure and interactive elements.browser_take_screenshot- capture visual evidence for findings and the report.browser_console_messages- collect console errors/warnings.browser_network_requests- list browser-visible requests and failures.browser_network_request- inspect a specific request when needed.browser_wait_for- wait for text/state to settle before re-checking console and network.
Interaction (to exercise real flows):
browser_click- activate links, buttons, and controls.browser_type/browser_fill_form- enter text and complete forms.browser_select_option- choose values in dropdowns/selects.browser_press_key- keyboard input and focus/keyboard-navigation checks.browser_hover- reveal hover menus and tooltips.browser_handle_dialog- accept or dismiss native dialogs and confirms.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 159 lines · 88 tokens per session scan A 89e3fedd1cf6
playwright-website-tester is a skill published in the GitHub repository dublyo/saas-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 1,412 once invoked, about $0.0004 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 2026-08-31.
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…