What it does
Self-healing browser harness that enables LLMs to complete any task
- Connects Instruction files the AI reads
- Account or key No key found in README or SKILL.md
- Category 其他
给作者:在 README 中加徽章
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/browser-use-browser-harness-js)相似的 Skill
同类工作,排序与 Skill 列表相同
| 本项 browser-harness-js | llmfit | claude-video | VideoCaptioner | claude-cookbooks | |
|---|---|---|---|---|---|
| 作者 | browser-use | AlexsJones | bradautomates | WEIFENG2333 | anthropics |
| Skill 数 | 1 | 1 | 1 | 1 | 4 |
| GitHub 星标 | 500 | 39,018 | 20,999 | 16,544 | 54,763 |
| 最近代码更新 | 2026年11月11日 | 2026年11月16日 | 2026年9月25日 | 2026年9月12日 | 2026年11月5日 |
| 许可证 | MIT | MIT | MIT | GPL-3.0 | MIT |
Skill 和 MCP 有什么不同
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
适用的应用
开发者未说明 · SKILL.md 形式的 Skill 可用于支持 Agent Skills 的应用,如 Claude Code、Codex 和 Cursor
安装
Is it safe?
- Who made it
GitHub account browser-use (organization), 1 years old
- Use and upkeep
★ 500 stars · code last changed 2026年11月11日
- Any scripts?
6 scripts that can run on a computer: sdk/browser-harness-js, sdk/gen.ts, sdk/generated.ts, sdk/repl.ts and 2 more
- Uses the internet?
Scripts that go online: sdk/browser-harness-js, sdk/repl.ts, sdk/session.ts, sdk/generated.ts
- Changes machine-wide settings?
No hooks or writes to machine settings found
Checked automatically from the repo files at commit c92722e (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
Option 1Upload to claude.ai (web and app)
Uploading to claude.ai would fail: the description is over 200 characters (560). Use "Let the AI install it" instead
Option 1让 Claude Code 帮你安装
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /browser-harness-js,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
ChatGPT 桌面应用
ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
Option 1让 ChatGPT 帮你安装
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Option 2自己放入文件夹
把 cdp 文件夹放到 ~/.agents/skills/cdp
~ 是你的主文件夹($HOME)
For Terminal users
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
打开终端
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
把 skill 文件夹复制到 ~/.agents/skills
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
安装之后
- ChatGPT 桌面应用:打开侧边栏中的 Skills,确认 Skill 已出现
- 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
- Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
网页版和手机版 ChatGPT
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Option 1让 Codex 帮你安装
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
For Terminal users
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
打开终端
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
把 skill 文件夹复制到 ~/.agents/skills
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
重新打开 Codex 并提出相关任务,Codex 会列出这个 skill
Option 1让 Cursor 帮你安装
复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 browser-harness-js
Checked against official docs 2026年11月12日 · Source: cursor.com
For Terminal users
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
打开终端
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
把 skill 文件夹复制到 ~/.cursor/skills
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
在 Cursor 的 Agent 聊天中输入 / 并选择 browser-harness-js
Option 1Let the AI install it
适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
For Terminal users
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
查看原始 SKILL.md
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
显示前 8,000 个字符 · 在 GitHub 打开完整文件
---
name: cdp
description: Drive Chrome via the DevTools Protocol from JavaScript. Run JS snippets through the `browser-harness-js` CLI — it auto-spawns a long-lived bun HTTP server holding a fully-typed CDP `Session`, and every call (`browser-harness-js 'await session.Page.navigate(...)'`) executes against the same persistent connection. Session, active target, and globals survive across calls. Use when the user wants to automate, script, or inspect a Chrome browser via CDP — single tab or multi-tab, attach to existing Chrome or to a new one launched with --remote-debugging-port.
---
# CDP — `browser-harness-js` skill
Custom codegen'd CDP SDK (every method from browser_protocol.json + js_protocol.json gets a typed wrapper) plus a tiny HTTP server that holds one persistent CDP `Session`. The `browser-harness-js` CLI auto-starts the server on first use and forwards JS snippets to it.
The SDK lives in the skill's `sdk/` directory. In the rest of this doc, `<skill-dir>` refers to wherever `npx skills add` installed the skill (Claude Code: `~/.claude/skills/cdp`; Cursor: `~/.cursor/skills/cdp`; other agents vary). The CLI should be on PATH as `browser-harness-js`.
## Setup (once, first use)
`npx skills add` drops the skill into your agent's skills directory but does NOT put the CLI on PATH. Before the first call, verify it's reachable and symlink it into any directory on your PATH if not:
```bash
# macOS (Apple Silicon + Homebrew)
command -v browser-harness-js >/dev/null || ln -sf <skill-dir>/sdk/browser-harness-js /opt/homebrew/bin/browser-harness-js
# macOS (Intel) / most Linux — may need sudo
command -v browser-harness-js >/dev/null || ln -sf <skill-dir>/sdk/browser-harness-js /usr/local/bin/browser-harness-js
# Linux without sudo (ensure ~/.local/bin is on PATH)
command -v browser-harness-js >/dev/null || { mkdir -p ~/.local/bin && ln -sf <skill-dir>/sdk/browser-harness-js ~/.local/bin/browser-harness-js; }
```
The CLI auto-installs `bun` on first run if it's missing (the server is Bun-native). Set `BROWSER_HARNESS_SKIP_BUN_INSTALL=1` to opt out.
## How to use
Just run `browser-harness-js '<JS>'`. The first call spawns the server in the background; subsequent calls hit the same process and so reuse the same `session`, the same WebSocket to Chrome, and any globals you set.
```bash
browser-harness-js 'await session.connect()'
browser-harness-js 'await session.Page.navigate({url:"https://example.com"})'
browser-harness-js '(await session.Runtime.evaluate({expression:"document.title",returnByValue:true})).result.value'
```
Output is the **raw result content** — no `{ok,result}` envelope.
| Result type | stdout |
|---|---|
| string | bare text, no JSON quotes (e.g. `Example Domain`) |
| number / boolean | `42`, `true` |
| object / array (non-empty) | compact JSON (e.g. `{"frameId":"..."}`, `[1,2,3]`) |
| `undefined` / `null` / `""` / `{}` / `[]` | empty (no output) |
**Errors** go to **stderr**, exit code `1`. The CDP error message and JS stack are printed verbatim, e.g.:
```
Error: CDP -32602: invalid params
at _call (.../session.ts:117:33)
...
```
Detect failure with `if browser-harness-js '...'; then ...; else handle_error; fi` or by checking `$?`.
**Multi-line snippets via stdin (heredoc).** Important: a multi-statement snippet does NOT auto-return the last expression — write `return X` explicitly. Single-expression snippets passed as the first argument DO auto-return.
```bash
browser-harness-js <<'EOF'
const tabs = await listPageTargets();
globalThis.tid = tabs[0].targetId;
await session.use(globalThis.tid);
return globalThis.tid;
EOF
```
## CLI commands
| Command | Behavior |
|---|---|
| `browser-harness-js '<js>'` | Auto-start server if needed, eval the JS, print result. |
| `browser-harness-js <<EOF…EOF` | Same, code from stdin. |
| `browser-harness-js --status` | Print health JSON (uptime, connected, sessionId) or exit 1 if down. |
| `browser-harness-js --start` | Explicit start (no-op if already running). |
| `browser-harness-js --stop` | Graceful shutdown. Drops session state. |
| `browser-harness-js --restart` | Stop + start fresh. |
| `browser-harness-js --logs` | `tail -f` the server log (`/tmp/browser-harness-js.log`). |
Env vars: `CDP_REPL_PORT` (default `9876`), `CDP_REPL_LOG` (default `/tmp/browser-harness-js.log`).
## API surface inside snippets
These globals are pre-loaded — no imports needed:
- `session` — the persistent `Session`. Has every CDP domain mounted: `session.Page`, `session.DOM`, `session.Runtime`, `session.Network`, … 56 domains, 652 methods total.
- `listPageTargets()` — list real page targets via CDP's `Target.getTargets` (works on Chrome 144+ too), with `chrome://` and `devtools://` URLs filtered out. No args — uses the connected session.
- `detectBrowsers()` — scan OS-specific profile dirs for running Chromium-based browsers with remote debugging on. Returns `[{name, profileDir, port, wsPath, wsUrl, mtimeMs}]`, sorted by most recently launched.
- `resolveWsUrl(opts)` — resolve a WS URL from `{wsUrl}` | `{port, host?}` | `{profileDir}`. For the no-args auto-detect flow, call `session.connect()` directly instead.
- `CDP` — the generated namespaces (`CDP.Page`, `CDP.Runtime`, …) for type-name reference.
### Calling a CDP method
Every method takes a single object argument matching the CDP wire params; it resolves to the typed return value (no `result` envelope, no `id` correlation — handled for you).
```js
// no params
await session.DOM.enable()
// required params
await session.Page.navigate({ url: 'https://example.com' })
// all-optional params (object also optional)
await session.Page.captureScreenshot()
await session.Page.captureScreenshot({ format: 'png', quality: 80 })
// returns are stripped to the typed shape
const { root } = await session.DOM.getDocument()
const { nodeId } = await session.DOM.querySelector({ nodeId: root.nodeId, selector: 'h1' })
```
### Connecting
**Default: just call `session.connect()` with no args.** It auto-detects running Chromium-based browsers (Chrome, Chromium, Edge, Brave, Arc, Vivaldi, Opera, Comet, Canary) by scanning OS-specific profile dirs for a `DevToolsActivePort` file, ordered by most-recently-launched, and picks the first one whose WebSocket accepts. OS-agnostic — works on macOS, Linux, Windows.
```js
await session.connect() // auto-detect
```
Use `detectBrowsers()` first if you want to see what's available (or let the user pick) before connecting:
```js
const found = await detectBrowsers()
// [{ name: 'Google Chrome', profileDir, port, wsPath, wsUrl, mtimeMs }, ...]
```
**Explicit forms** — use these only when auto-detect picks the wrong browser, or when you already know where to connect:
| Form | When to use |
|---|---|
| `{ profileDir }` | Target a specific browser when several are running. Reads `<profileDir>/DevToolsActivePort` directly. |
| `{ wsUrl }` | You already have `ws://…/devtools/browser/<uuid>` (e.g. piped from elsewhere). |
```js
await session.connect({ profileDir: '/Users/<you>/Library/Application Support/Google/Chrome' })
await session.connect({ wsUrl: 'ws://127.0.0.1:9222/devtools/browser/<uuid>' })
```
Profile paths by OS — use these with `{ profileDir }`:
- macOS: `~/Library/Application Support/<Browser>` (e.g. `Google/Chrome`, `Comet`, `BraveSoftware/Brave-Browser`, `Arc/User Data`)
- Linux: `~/.config/<browser>` (e.g. `google-chrome`, `chromium`, `BraveSoftware/Brave-Browser`)
- Windows: `%LOCALAPPDATA%\<Browser>\User Data` (e.g. `Google\Chrome`, `Microsoft\Edge`, `BraveSoftware\Brave-Browser`)
Per-candidate WS-open timeout defaults to **5s** — live browsers answer with open/close within ~100ms, so 5s is already generous. The only case where 5s is too short is when Chrome is showing the **Allow** popup and waiting on the user to click. If you expect that, pass `timeoutMs: 30000`:
```js
await session.connect({ profileDir: '/Users/<you>/Library/Applicat讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
来自 GitHub
- GitHub 星标
- 500
- 开发者
- browser-use
- 许可证
- MIT
- 最近代码更新
- 2026年11月11日
- repo 中的 SKILL.md 文件(含译本和模板)
- 1