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 sailingnaturali/claude-skills --skill webapp-e2egit clone --depth 1 https://github.com/sailingnaturali/claude-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/sailingnaturali/claude-skills/webapp-e2e)<a href="https://agentmods.dev/skills/sailingnaturali/claude-skills/webapp-e2e"><img src="https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/webapp-e2e/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/sailingnaturali/claude-skills/webapp-e2e"><img src="https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/webapp-e2e.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 | $0.00096 | $0.01724 |
| Opus 5 | $0.00048 | $0.00862 |
| Sonnet 5 | $0.00019 | $0.00345 |
| Haiku 4.5 | $0.00010 | $0.00172 |
Grade A, and why
webapp-e2e scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **A dev server**: start it (`npm run dev`), then **poll for readiness with a `fetch(url)` that How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
End-to-end test a web app change in a real browser
When a change touches behavior a unit test can't reach — a rendered page, an interactive
control, a component that only misbehaves once mounted and talking to a real backend — verify it
in a real browser before opening the PR. This is about verifying the app works, distinct
from recording a demo GIF of it (record-web-gif) and from any SignalK-server-specific harness
(signalk-server-e2e).
0. Use the repo's bundled chromium, not the MCP/system browser
Drive the browser through @playwright/test's own chromium from a scratch script — not a
system-provided or MCP browser, which usually wants a system Chrome that's often absent on a
headless box and is the wrong version anyway. Install where you run the check:
npm i -D @playwright/test && npx playwright install chromium
A throwaway e2e.mjs is right for one-off verification; a committed *.spec.ts under the repo's
test dir is right when the check should run in CI. Prefer @playwright/test's expect +
auto-waiting locators over raw page.waitForSelector — they retry until the condition holds,
which kills most flakiness.
1. Point it at the app
- A dev server: start it (
npm run dev), then poll for readiness with afetch(url)that returns 200 before asserting — that's the primary gate. "Process started" ≠ "app serving"; racing the firstgotois the top source of flaky first runs.page.goto(url, { waitUntil: "networkidle" })is a fallback for the page load — don't rely on it for readiness of an app that holds a socket open (a live SignalK UI, any SSE/WebSocket stream): idle never fires and the goto hangs. - A live URL:
page.goto(url)directly. Keep destructive interactions out of production. - An isolated component (a plugin config panel, a design-system widget) that has no page of its own: mount it in a tiny host page and load that. See §3.
2. Drive it and assert like a user
Assert on what a user would observe, through the public surface — rendered text, control state, and the network calls a working feature makes:
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 · 127 lines · 96 tokens per session scan A 9070670df642
webapp-e2e is a skill published in the GitHub repository sailingnaturali/claude-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 96 tokens to every session and 1,724 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (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
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…