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 MadAppGang/magus --skill ui-playwrightgit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/madappgang/magus/ui-playwright)<a href="https://agentmods.dev/skills/madappgang/magus/ui-playwright"><img src="https://agentmods.dev/badge/skills/madappgang/magus/ui-playwright/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/madappgang/magus/ui-playwright"><img src="https://agentmods.dev/badge/skills/madappgang/magus/ui-playwright.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 | $0.00049 | $0.01125 |
| Opus 5.5 | $0.00020 | $0.00450 |
| Sonnet 5.5 | $0.00010 | $0.00225 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
ui-playwright 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 1mo 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI tests with Playwright
Objective: a UI test suite that fails when a user-visible behaviour breaks and stays green across runs. The contract is the Storybook story set and the spec; the implementation is not an input.
Inputs and outputs
| Input | Where it comes from |
|---|---|
Story files (*.stories.tsx) |
CONTRACT_PATHS — every exported story is a state to test |
| Spec | SPEC_PATH — flows, error text, limits |
| Test dir and config | TEST_DIR, playwright.config.* if present |
Output: *.spec.ts files under TEST_DIR, a playwright.config.ts if none exists, page
objects under TEST_DIR/pages/, fixtures under TEST_DIR/fixtures/.
Workflow
- Map stories to tests. For each story export write one test named
<Component> · <story> · <expected outcome>. A story with no test is a gap; a test with no story or spec line is an implementation test — delete it. - Locate by role, then label, then test id.
getByRole('button', { name: 'Save' })first;getByLabel,getByTextnext;getByTestIdonly when the element has no accessible name, and then record the id as a contract the component must keep. Never locate by CSS class or DOM position. - Page objects for flows, not for single components. A page object exposes actions
(
login(user),openOrder(id)) and readable state (errorText()); it holds locators, nothing else. Component tests call the component directly through@playwright/experimental-ct-react(or the framework's CT package) with props from the story. - Fixtures own setup and teardown. Auth, seeded data, and viewport live in
test.extendfixtures; a test body is arrange-act-assert only. - Stub the network at the boundary.
page.route()for third-party and backend calls in component and flow tests; assert the request shape when the spec defines it. E2E tests against a real backend run in a separate project with its own tag. - Assert observable outcomes. Rendered text,
toBeVisible,toHaveValue,toHaveAttribute('aria-invalid', 'true'), URL, emitted network request. Never assert on internal state, store shape, or that a handler was called. - Snapshots are for layout regressions only. One
toHaveScreenshot()per story state,maxDiffPixelRatioset explicitly, masks for dates and avatars, stored per platform. A snapshot never replaces a behavioural assertion. - Every state from the guardrails is a test. Default, hover, focus, disabled, loading, invalid, empty — if the story exists, the test exists; if the story is missing, report it as a contract gap rather than skipping the state.
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.
- 1mo ago First seen · 86 lines · 49 tokens per session scan A 145ae4a2147d
ui-playwright is a skill published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 1,125 once invoked, about $0.0002 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 2026-09-15.
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".
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.
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…