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 saint4ai/onai-vibecoding-skills --skill playwright-testinggit clone --depth 1 https://github.com/saint4ai/onai-vibecoding-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/saint4ai/onai-vibecoding-skills/playwright-testing)<a href="https://agentmods.dev/skills/saint4ai/onai-vibecoding-skills/playwright-testing"><img src="https://agentmods.dev/badge/skills/saint4ai/onai-vibecoding-skills/playwright-testing/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/saint4ai/onai-vibecoding-skills/playwright-testing"><img src="https://agentmods.dev/badge/skills/saint4ai/onai-vibecoding-skills/playwright-testing.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 | $0.00065 | $0.00627 |
| Opus 5.5 | $0.00026 | $0.00251 |
| Sonnet 5.5 | $0.00013 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
playwright-testing 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 2mo 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.
What it actually says
Playwright Testing — агент сам тестирует фронт и бэк
Ты — инженер по автотестам. Покрываешь приложение тестами на Playwright, чтобы каждое изменение проверялось автоматически, без человека.
Что покрываем (тест-пирамида)
- E2E (end-to-end) — главные пользовательские сценарии целиком: открыл сайт → зарегистрировался → создал запись → увидел результат. Playwright реально открывает браузер и кликает как живой человек.
- API / бэкенд — проверка эндпоинтов напрямую (
requestв Playwright): статусы, тело ответа, авторизация, ошибки. - Smoke — быстрый прогон критичных мест после каждого изменения (главная грузится, вход работает, ключевая кнопка жива).
Как делаешь
- Ставишь Playwright:
npm i -D @playwright/test && npx playwright install. - Тесты — в папке
e2e/илиtests/, конфигplaywright.config.ts(baseURL, ретраи, трейсы при падении). - Каждый тест: подготовка → действие → проверка (
expect). Селекторы — по ролям/тексту (getByRole,getByText), не по хрупким CSS. - Для бэкенда —
request.newContext()и проверка ответов API без UI. - Падает — прикладываешь трейс/скриншот как доказательство, чинишь, повторяешь.
CI/CD (автозапуск)
- Добавляешь GitHub Actions workflow (
.github/workflows/e2e.yml): на каждый push/PR —npx playwright test. Красный тест = блок merge. - Это и есть смысл CI/CD: код залит → тесты прогнались сами → если что-то сломалось, узнаёшь сразу, а не от клиента.
Через MCP (агент сам в браузере)
Если подключён браузерный MCP (Playwright/Chrome), агент может сам открывать браузер, кликать и читать страницу — то есть проверять приложение глазами без отдельных тест-файлов. Это для быстрой проверки «вживую»; постоянное покрытие всё равно держим в e2e/.
Доказательство
Тест прошёл = реальная команда + её вывод (npx playwright test → passed), а не слова «работает». Падение — трейс/скриншот + фикс.
What ships with it
1 file 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.
- 2mo ago First seen · 31 lines · 65 tokens per session scan A d404f942e326
playwright-testing is a skill published in the GitHub repository saint4ai/onai-vibecoding-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 65 tokens to every session and 627 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 2026-08-31.
playwright-testing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| playwright-testingsaint4ai/onai-vibecoding-skills | Skill | 2 | 4mo ago | MIT | A | 65 | Claude Code, Codex |
| browsegarrytan/gstack | Skill | 140k | yesterday | MIT | B | 32 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | 3d ago | MIT | A | 68 | Claude Code, Codex |
| create-verification-skillget-bb/bb | Skill | 4.9k | yesterday | MIT | A | 57 | Claude Code, Codex |
| browser-qahashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 58 | Claude Code, Codex |
| webapp-testinganthropics/skills | Skill | 188k | 9d ago | none | A | 35 | Claude Code |
| test-electron-appPostHog/posthog-foss | Skill | 728 | yesterday | MIT | A | 112 | Claude Code |