Borrowing it
Nothing to install: this file belongs to clxzl/claude-code-best-practice-cn. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/clxzl/claude-code-best-practice-cn/main/.claude/skills/agent-browser/SKILL.mdgit clone --depth 1 https://github.com/clxzl/claude-code-best-practice-cnWrote 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/clxzl/claude-code-best-practice-cn/agent-browser)<a href="https://agentmods.dev/skills/clxzl/claude-code-best-practice-cn/agent-browser"><img src="https://agentmods.dev/badge/skills/clxzl/claude-code-best-practice-cn/agent-browser/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/clxzl/claude-code-best-practice-cn/agent-browser"><img src="https://agentmods.dev/badge/skills/clxzl/claude-code-best-practice-cn/agent-browser.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 | $0.00125 | $0.01966 |
| Opus 5.5 | $0.00050 | $0.00786 |
| Sonnet 5.5 | $0.00025 | $0.00393 |
| Haiku 4.5 | $0.00013 | $0.00197 |
Grade A, and why
agent-browser 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 1mo 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
使用 agent-browser 进行浏览器自动化
核心工作流
每个浏览器自动化都遵循以下模式：
- 导航：
agent-browser open <url> - 快照：
agent-browser snapshot -i（获取元素引用如@e1、@e2） - 交互：使用引用进行点击、填写、选择
- 重新快照：在导航或 DOM 变更后，获取新的引用
agent-browser open https://example.com/form
agent-browser snapshot -i
# 输出：@e1 [input type="email"]，@e2 [input type="password"]，@e3 [button] "Submit"
agent-browser fill @e1 "[email protected]" agent-browser fill @e2 "password123" agent-browser click @e3 agent-browser wait --load networkidle agent-browser snapshot -i # 检查结果
## 基本命令
```bash
# 导航
agent-browser open <url> # 导航（别名：goto，navigate）
agent-browser close # 关闭浏览器
# 快照
agent-browser snapshot -i # 带引用的交互元素（推荐）
agent-browser snapshot -i -C # 包含光标交互元素（带有 onclick、cursor:pointer 的 div）
agent-browser snapshot -s "#selector" # 限定到 CSS 选择器范围
# 交互（使用快照中的 @引用）
agent-browser click @e1 # 点击元素
agent-browser fill @e2 "text" # 清除并输入文本
agent-browser type @e2 "text" # 输入文本（不清除）
agent-browser select @e1 "option" # 选择下拉选项
agent-browser check @e1 # 勾选复选框
agent-browser press Enter # 按键
agent-browser scroll down 500 # 滚动页面
# 获取信息
agent-browser get text @e1 # 获取元素文本
agent-browser get url # 获取当前 URL
agent-browser get title # 获取页面标题
# 等待
agent-browser wait @e1 # 等待元素出现
agent-browser wait --load networkidle # 等待网络空闲
agent-browser wait --url "**/page" # 等待 URL 匹配模式
agent-browser wait 2000 # 等待毫秒数
# 捕获
agent-browser screenshot # 截图到临时目录
agent-browser screenshot --full # 全页面截图
agent-browser pdf output.pdf # 保存为 PDF
常见模式
表单提交
agent-browser 打开 https://example.com/signup
agent-browser 截图 -i
agent-browser 填写 @e1 "Jane Doe"
agent-browser 填写 @e2 "[email protected]"
agent-browser 选择 @e3 "California"
agent-browser 勾选 @e4
agent-browser 点击 @e5
agent-browser 等待网络空闲 --load networkidle
带状态持久化的身份验证
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.
- 1mo ago First seen · 219 lines · 125 tokens per session scan A 58e028de6320
agent-browser is a skill published in the GitHub repository clxzl/claude-code-best-practice-cn (138 stars, last pushed 5mo ago), licensed MIT. It adds 125 tokens to every session and 1,966 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
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
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
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.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…