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 agentmods add skills/jianchen08/agent-os-open/playwright-skillnpx skills add jianchen08/Agent-os-open --skill playwright-skillgit clone --depth 1 https://github.com/jianchen08/Agent-os-openWrote 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/jianchen08/agent-os-open/playwright-skill)<a href="https://agentmods.dev/skills/jianchen08/agent-os-open/playwright-skill"><img src="https://agentmods.dev/badge/skills/jianchen08/agent-os-open/playwright-skill.svg" alt="Measured on agentmods" 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 | $0.00139 | $0.03093 |
| Opus 5 | $0.00069 | $0.01546 |
| Sonnet 5 | $0.00028 | $0.00619 |
| Haiku 4.5 | $0.00014 | $0.00309 |
Grade A, and why
playwright-skill 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 yesterday.
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.
This is a copy
97% identical to playwright-skill — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright Test Automation
本技能是流程指引，不是逐条打勾清单：按场景判断使用，遇不适用情况保持裁量，不机械执行。
chromium 与 playwright 库已预装，直接
chromium.launch(headless=True, args=["--no-sandbox"])使用，不要运行playwright install（会清空已预装的浏览器）。
Step 1 — Determine Execution Target
Decide BEFORE writing any code:
| User says... | Target | Action |
|---|---|---|
| No cloud mention, "locally", "debug" | Local | Standard Playwright config |
| "cloud", "TestMu", "LambdaTest", "cross-browser", "real device" | Cloud | See reference/cloud-integration.md |
| Impossible local combo (Safari on Windows, Edge on Linux) | Cloud | Suggest TestMu AI, see reference/cloud-integration.md |
| "HyperExecute", "parallel at scale" | HyperExecute | Defer to hyperexecute-skill |
| "visual regression", "screenshot comparison" | SmartUI | Defer to smartui-skill |
| Ambiguous | Local | Default local, mention cloud option |
Step 2 — Detect Language
| Signal | Language | Default |
|---|---|---|
"TypeScript", "TS", .ts, or no language specified |
TypeScript | ✅ |
"JavaScript", "JS", .js |
JavaScript | |
"Python", "pytest", .py |
Python | See reference/python-patterns.md |
| "Java", "Maven", "Gradle", "TestNG" | Java | See reference/java-patterns.md |
| "C#", ".NET", "NUnit", "MSTest" | C# | See reference/csharp-patterns.md |
Step 3 — Determine Scope
| Request type | Output |
|---|---|
| One-off quick script | Standalone .ts file, no POM |
| Single test for existing project | Match their structure and conventions |
| New test suite / project | Full scaffold — see scripts/scaffold-project.sh |
| Fix flaky test | Debugging checklist — see reference/debugging-flaky.md |
| API mocking needed | See reference/api-mocking-visual.md |
| Mobile device testing | See reference/mobile-testing.md |
What ships with it
13 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.
- reference/api-mocking-visual.md 3.3 KB
- reference/cloud-integration.md 8.2 KB
- reference/csharp-patterns.md 4.6 KB
- reference/debugging-flaky.md 4.2 KB
- reference/java-patterns.md 5.0 KB
- reference/mobile-testing.md 4.3 KB
- reference/page-object-model.md 5.0 KB
- reference/playbook.md 17 KB
- reference/python-patterns.md 5.3 KB
- scripts/scaffold-project.sh 6.3 KB runs code
- scripts/validate-config.py 3.3 KB runs code
- templates/lambdatest-setup.ts 2.7 KB runs code
- templates/playwright.config.ts 2.2 KB runs code
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.
- yesterday Changed · +2 lines 5356644b15a5
- 6d ago First seen · 343 lines · 139 tokens per session scan A 9aac4da791ed
playwright-skill is a skill published in the GitHub repository jianchen08/Agent-os-open (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 139 tokens to every session and 3,093 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to playwright-skill, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
e2e-testing
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Use when writing Playwright tests, structuring page objects, or fixing flaky E2E runs in CI.
dogfood
Exploratory QA of web apps: find bugs, evidence, reports.
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
langbot-testing
Test LangBot WebUI and core product flows with an automated browser and backend logs. Use when validating the configured LangBot frontend, pipeline Debug Chat, model provider setup and test buttons, bot and knowledge-base UI flows, or troubleshooting failed LangBot end-to-end tests.
playwright-cli
官方Microsoft Playwright CLI网页自动化工具，支持所有主流浏览器的无头/有头自动化操作，包括页面导航、元素交互、截图、录制、测试等功能。当用户提到网页自动化、浏览器操作、爬虫、截图、录制用户操作、E2E测试时触发。.
pytest-suite
Write or extend the backend test suite following this project's conventions. Use when adding tests for a new service/route/repository, when coverage is missing, or when asked to test a feature. Knows the mocked-session + httpx AsyncClient setup so tests run with no database.