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 l0s3r-Q/browser-test-mcp --skill skillgit clone --depth 1 https://github.com/l0s3r-Q/browser-test-mcpWrote 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/l0s3r-q/browser-test-mcp/skill)<a href="https://agentmods.dev/skills/l0s3r-q/browser-test-mcp/skill"><img src="https://agentmods.dev/badge/skills/l0s3r-q/browser-test-mcp/skill/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/l0s3r-q/browser-test-mcp/skill"><img src="https://agentmods.dev/badge/skills/l0s3r-q/browser-test-mcp/skill.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 | $0.00119 | $0.02026 |
| Opus 5 | $0.00060 | $0.01013 |
| Sonnet 5 | $0.00024 | $0.00405 |
| Haiku 4.5 | $0.00012 | $0.00203 |
Grade A, and why
browser-test 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 7d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
browser-test：浏览器自动化测试（Playwright × browser-use 共生）
核心心智模型
两个开源项目共生在一个 MCP server 里，共用同一个浏览器实例（playwright 启动 chromium 带 CDP 调试端口，browser-use 通过 CDP 连接）：
┌─ 意图层 ─────────────────────────────────────────────┐
│ 你用自然语言描述"测试什么" │
├──────────────────────────────────────────────────────┤
│ AI 层（browser_* 工具，browser-use 官方 16 个） │
│ · 探索未知页面、理解页面结构、AI 智能体自主完成任务 │
│ · retry_with_browser_use_agent：AI 全自主跑复杂流程 │
├──────────────────────────────────────────────────────┤
│ 精确层（pw_* 工具，Playwright 官方 43 个） │
│ · 确定性操作：选择器点击/填表/选择/拖拽/上传 │
│ · 断言：文本/可见性/URL/元素数量（测试核心） │
│ · 等待：元素/URL/加载状态/接口响应 │
│ · 调试：截图/trace/网络请求记录/JS 求值 │
├──────────────────────────────────────────────────────┤
│ 共享会话：同一 chromium，同一页面，随时切换两层 │
└──────────────────────────────────────────────────────┘
工具选择决策（重要）
| 场景 | 用哪层 | 理由 |
|---|---|---|
| 打开页面、点击、填表、选择、拖拽 | pw_* |
确定性，选择器直接定位 |
| 断言测试结果（文本/可见/URL/数量） | pw_assert_* |
返回 PASS/FAIL，可写进测试报告 |
| 等待异步渲染/接口返回 | pw_wait_* |
显式等待，避免 flaky |
| 不知道页面结构/元素选择器 | browser_get_state |
返回交互元素清单+索引 |
| 页面复杂、AI 自主探索完成流程 | retry_with_browser_use_agent |
browser-use Agent 智能体，最后手段 |
| 截图给用户看 | pw_screenshot |
返回图片可直接展示 |
| 定位 flaky 问题 | pw_trace_start + pw_trace_stop |
生成 trace.zip 用 Trace Viewer 回放 |
| 登录态复用 | pw_save_storage_state + pw_load_storage_state |
一次登录，多次测试 |
| 验证接口调用 | pw_wait_for_response / pw_network_requests |
状态码+响应体 |
标准测试工作流（跑一轮 UI 测试）
1. pw_navigate(url) → 打开被测页面
2. pw_get_title / pw_get_url → 确认页面就绪（或 pw_wait_for_selector）
3. pw_fill(selector, value) → 填表单
4. pw_click(selector) → 触发交互
5. pw_wait_for_url / pw_wait_for_response / pw_wait_for_selector
→ 等待结果出现（网络/渲染）
6. pw_assert_text / pw_assert_url / pw_assert_visible / pw_assert_count
→ 断言，记录 PASS/FAIL
7. （可选）pw_screenshot → 留证
8. 汇总 PASS/FAIL 报告给用户
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.
- 7d ago First seen · 107 lines · 119 tokens per session scan A 16914bb7d9ae
browser-test is a skill published in the GitHub repository l0s3r-Q/browser-test-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 2,026 once invoked, about $0.0006 per session on Opus 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.
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…