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 cklxx/elephant.ai --skill browser-usegit clone --depth 1 https://github.com/cklxx/elephant.aiWrote 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/cklxx/elephant.ai/browser-use)<a href="https://agentmods.dev/skills/cklxx/elephant.ai/browser-use"><img src="https://agentmods.dev/badge/skills/cklxx/elephant.ai/browser-use.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 | $0.00036 | $0.02072 |
| Opus 5 | $0.00018 | $0.01036 |
| Sonnet 5 | $0.00007 | $0.00414 |
| Haiku 4.5 | $0.00004 | $0.00207 |
Grade A, and why
browser-use 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 8d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
browser-use
通过 @playwright/cli daemon 连接用户真实 Chrome 浏览器(extension 模式),复用已登录的 session。
Tab 跨调用持久化 — daemon 进程常驻,tab、cookies、登录状态在多次调用间存活。
前置条件
- Chrome 安装了 Playwright MCP Bridge 扩展
.env中配置了ALEX_BROWSER_BRIDGE_TOKEN(从扩展弹窗复制)
核心概念
- Daemon 持久会话:首次调用自动启动 daemon(
open --extension),后续所有调用复用同一会话 - Snapshot → ref → 操作:
snapshot获取页面无障碍树,每个元素有ref(如e44),用click/fill/type操作该 ref - 不抢前台:extension 模式连接已有 Chrome,不会弹出新窗口或抢占焦点
- Token 节省:snapshot 输出到文件(
.playwright-cli/目录),不灌入 stdout
调用
# 首次打开 — 连接 Chrome 扩展(自动启动 daemon)
python3 skills/browser-use/run.py open
# 导航到 URL(自动确保 session 存在)
python3 skills/browser-use/run.py navigate --url https://x.com
# 获取页面快照(无障碍树 + 元素 ref)
python3 skills/browser-use/run.py snapshot
# 点击元素(ref 来自 snapshot)
python3 skills/browser-use/run.py click --ref e44
# 填充输入框(定位到 ref 再填入文本)
python3 skills/browser-use/run.py fill --ref e100 --text "hello world"
# 输入文本到当前焦点元素
python3 skills/browser-use/run.py type --text "search query" --submit true
# 悬停
python3 skills/browser-use/run.py hover --ref e50
# 下拉选择
python3 skills/browser-use/run.py select --ref e80 --value "option1"
# 截图
python3 skills/browser-use/run.py screenshot --filename page.png
python3 skills/browser-use/run.py screenshot --ref e44 --filename element.png
python3 skills/browser-use/run.py screenshot --full_page true --filename full.png
# 按键
python3 skills/browser-use/run.py press_key --key Enter
python3 skills/browser-use/run.py press_key --key "Control+a"
# 导航
python3 skills/browser-use/run.py go_back
python3 skills/browser-use/run.py go_forward
python3 skills/browser-use/run.py reload
# 执行 JavaScript
python3 skills/browser-use/run.py evaluate --function '() => document.title'
python3 skills/browser-use/run.py evaluate --function '(el) => el.textContent' --ref e44
# 执行 Playwright 代码
python3 skills/browser-use/run.py run_code --code 'async (page) => await page.title()'
# Tab 管理(跨调用持久!)
python3 skills/browser-use/run.py tabs # 列出所有 tab
python3 skills/browser-use/run.py tab_select --index 0 # 切换到 tab 0
python3 skills/browser-use/run.py tab_new --url https://... # 新开 tab
python3 skills/browser-use/run.py tab_close --index 1 # 关闭 tab
# 调试
python3 skills/browser-use/run.py console # 查看 console 日志
python3 skills/browser-use/run.py network # 查看网络请求
python3 skills/browser-use/run.py pdf # 导出 PDF
# 关闭会话
python3 skills/browser-use/run.py close
What ships with it
2 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.
- 8d ago First seen · 186 lines · 36 tokens per session scan A e9f87b6f220c
browser-use is a skill published in the GitHub repository cklxx/elephant.ai (11 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 2,072 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…