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 azusachino/harus-skills --skill playwright-verifygit clone --depth 1 https://github.com/azusachino/harus-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/azusachino/harus-skills/playwright-verify)<a href="https://agentmods.dev/skills/azusachino/harus-skills/playwright-verify"><img src="https://agentmods.dev/badge/skills/azusachino/harus-skills/playwright-verify/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/azusachino/harus-skills/playwright-verify"><img src="https://agentmods.dev/badge/skills/azusachino/harus-skills/playwright-verify.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 | $0.00076 | $0.01490 |
| Opus 5.5 | $0.00030 | $0.00596 |
| Sonnet 5.5 | $0.00015 | $0.00298 |
| Haiku 4.5 | $0.00008 | $0.00149 |
Grade A, and why
playwright-verify 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 18d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright verify
State the behavior as a Playwright spec, run it headless through the project's make e2e, and keep the spec as the project's regression check.
Keep everything in source: settings in playwright.config.ts, checks and probes in spec files, setup and runs behind Make targets. Do not verify with one-off commands or logic typed on a command line; anything worth running belongs in one of those files, where the next person or agent can rerun it.
The practices below follow Playwright's best practices; the deliberate departures are listed under Limits.
Fit
A project fits when it serves its web UI from a dev or preview server that starts without interaction, on local or fixture data. Headless Chromium needs no display: it runs over plain SSH on a Mac with no console session. A desktop or mobile shell (Tauri, Compose, Android) is out of scope, though its web frontend alone may fit.
Add it to a project
- Add
@playwright/testas a dev dependency with the project's package manager, so its lockfile pins the version. Each Playwright version needs its own Chromium build; choose a version another project already uses to skip a download. - Copy the templates from
assets/:playwright.config.tsnext to the web app'spackage.json,e2e/smoke.spec.tsande2e/probe.spec.tsinto itse2e/, ande2e.mknext to the project'sMakefile. - Set the values marked
EDIT: the dev command and its port in the config, and in the smoke spec the first route and a landmark it must show. - In the
Makefile, setE2E_DIRto the web app's directory and addinclude e2e.mk. It definese2e,e2e-probeande2e-install. - Run
make e2e-installonce, thenmake e2e. - Add
test-results/andplaywright-report/to the web app's.gitignore. - Mention
make e2ein the project's own instructions, so an agent finds it without this skill.
When the app needs more than one server, seeded data, or checks after the run, give the lifecycle to a project script that starts everything, exports E2E_BASE_URL, and runs the checks; the config then starts no server of its own. felicia's admin E2E harness works this way.
What ships with it
4 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.
- 18d ago First seen · 59 lines · 76 tokens per session scan A b88fc921bfbe
playwright-verify is a skill published in the GitHub repository azusachino/harus-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 76 tokens to every session and 1,490 once invoked, about $0.0003 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 2026-10-01.
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…