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 ademdeniz/playwright-mcp --skill write-playwright-testgit clone --depth 1 https://github.com/ademdeniz/playwright-mcpWrote 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/ademdeniz/playwright-mcp/write-playwright-test)<a href="https://agentmods.dev/skills/ademdeniz/playwright-mcp/write-playwright-test"><img src="https://agentmods.dev/badge/skills/ademdeniz/playwright-mcp/write-playwright-test/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/ademdeniz/playwright-mcp/write-playwright-test"><img src="https://agentmods.dev/badge/skills/ademdeniz/playwright-mcp/write-playwright-test.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 | $0.00097 | $0.01279 |
| Opus 5.5 | $0.00039 | $0.00512 |
| Sonnet 5.5 | $0.00019 | $0.00256 |
| Haiku 4.5 | $0.00010 | $0.00128 |
Grade A, and why
write-playwright-test 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 9d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write a Playwright test from a verified flow
Goal: a spec that drops into the user's repo, passes on the first run, and reads like their existing tests. Verified behavior is the input — never assert something you did not see in the browser or the scenario.
1. Learn the repo before writing anything
If you can read the project, check (quickly — skim, don't audit):
playwright.config.*→testDir,baseURL, projects,testIdAttribute- Two or three existing specs → naming,
test.describeuse, tag style (@smokein titles vs{ tag: '@smoke' }), assertion style - Page objects (
pages/,page-objects/,pom/,*.page.ts) → class shape, how locators are exposed (getters, readonly fields, methods) - Custom fixtures (
fixtures/,test.extend) → import path, available fixtures, any pre-authenticated fixture - Auth setup (
storageState,global-setup,auth.setup.ts)
Follow what the repo does. If it has page objects, add methods to the existing one or create a new one in the same style — don't inline selectors. If it has a logged-in fixture, use it instead of re-doing login. If there is no repo to read, use the defaults in section 4 and say so.
2. Map the verified steps to Playwright
| Verified step | Playwright Test |
|---|---|
navigate to /path |
await page.goto('/path') (relative when baseURL is set) |
| fill field | await page.getByLabel('Email').fill('…') |
| click | await page.getByRole('button', { name: 'Sign in' }).click() |
| select option | await page.getByLabel('Country').selectOption({ label: 'Canada' }) |
| press key | await page.getByRole('searchbox').press('Enter') |
| wait for text | nothing — the following expect auto-waits |
| URL contains | await expect(page).toHaveURL(/\/dashboard/) |
| text visible | await expect(page.getByText('Welcome back')).toBeVisible() |
| element hidden | await expect(locator).toBeHidden() |
| field value | await expect(locator).toHaveValue('2') |
| element count | await expect(locator).toHaveCount(3) |
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.
- 9d ago First seen · 100 lines · 97 tokens per session scan A f96f062da5fb
write-playwright-test is a skill published in the GitHub repository ademdeniz/playwright-mcp (3 stars, last pushed 4d ago), licensed MIT. It adds 97 tokens to every session and 1,279 once invoked, about $0.0004 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 2026-10-19.
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).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
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.
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.
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…