Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/tonyhzk/chrome-agent-skill/browser-chrome-agent)<a href="https://agentmods.dev/skills/tonyhzk/chrome-agent-skill/browser-chrome-agent"><img src="https://agentmods.dev/badge/skills/tonyhzk/chrome-agent-skill/browser-chrome-agent/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/tonyhzk/chrome-agent-skill/browser-chrome-agent"><img src="https://agentmods.dev/badge/skills/tonyhzk/chrome-agent-skill/browser-chrome-agent.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 | $0.00100 | $0.03277 |
| Opus 5 | $0.00050 | $0.01639 |
| Sonnet 5 | $0.00020 | $0.00655 |
| Haiku 4.5 | $0.00010 | $0.00328 |
Grade A, and why
browser-chrome-agent 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 9d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Chrome Agent
通过 WebSocket 与 Chrome 扩展通信，控制用户浏览器执行自动化操作。
前置条件
- Chrome 浏览器已安装 Browser MCP 扩展
- 本技能默认分发修改版插件：
assets/目录内仅包含修改版插件，支持所有文档中列出的功能（包括get_html、snapshot_file等增强功能） - 扩展安装包位于
%当前SKILL文件父目录%/assets/目录 - 安装方式：Chrome 地址栏输入
chrome://extensions/，开启「开发者模式」，解压Browser_MCP_1_3_4_modified.zip后通过「加载已解压的扩展程序」安装
- 本技能默认分发修改版插件：
- 扩展已点击 Connect 建立连接
- 推荐安装 persistent-shell-skill — 持久终端会话技能，用于在 Claude Code 中保持服务器持续运行
启动服务器
服务器需要持续运行并通过 stdin 接收 JSON 命令。
方式一：持久化终端技能（Claude Code 推荐）
需要 持久化终端 技能：
- 创建名为
browser-ws的后台会话 - 在会话中执行：
python3 %当前SKILL文件父目录%/scripts/server.py --port 9009 - 等待几秒后读取输出，确认服务器启动和扩展连接
方式二：手动终端运行
没有持久化终端技能时，让用户在终端中手动直接运行：
python3 %当前SKILL文件父目录%/scripts/server.py --port 9009
启动后在同一终端中逐行输入 JSON 命令即可。
服务器启动后输出 [server] WebSocket 服务器已启动，扩展连接后输出 [server] Chrome 扩展已连接。
发送命令
逐行输入 JSON 命令：
{"action": "navigate", "params": {"url": "https://example.com"}}
如果使用持久化终端，向 browser-ws 会话发送命令后等待 5-10 秒读取结果。
可用操作
| action | params | 说明 |
|---|---|---|
navigate |
{"url": "..."} |
导航到 URL |
go_back |
{} |
后退 |
go_forward |
{} |
前进 |
click |
{"ref": "s1e5"} 或 {"x": 500, "y": 100} |
点击元素（支持 ref 或坐标） |
hover |
{"ref": "s1e5"} |
悬停元素 |
type |
{"ref": "s1e5", "text": "...", "submit": false} |
输入文本 |
select_option |
{"ref": "s1e5", "values": ["..."]} |
选择下拉选项 |
drag |
{"startRef": "s1e5", "endRef": "s1e8"} |
拖拽 |
press_key |
{"key": "Enter"} |
按键 |
get_coordinates |
{"ref": "s1e5"} |
获取元素坐标位置 |
find_element |
{"keyword": "搜索"} |
通过关键字搜索元素，返回匹配的 ref 列表 |
find_and_locate |
{"keyword": "搜索", "index": 0} |
搜索元素并立即获取坐标（解决 ref 过期问题） |
get_text |
{} 或 {"max_length": 5000} |
获取页面纯文字内容 |
wait |
{"time": 2} |
等待（秒） |
screenshot |
{} 或 {"savePath": "全路径"} |
截图，传 savePath（必须是全路径）保存到文件，不传返回 base64 |
snapshot |
{} |
获取页面 ARIA 快照。默认只返回 URL+Title；传 snapshot_file 保存到文件；传 inline: true 直接返回快照内容；max_length 控制截断长度（默认从 config.json 读取，兜底 0 不截断） |
get_html |
{"savePath": "全路径"} |
获取页面完整 HTML 源码并保存到文件（savePath 必须是全路径，仅修改版插件可用） |
xpath_query |
{"xpath": "//h1"} |
对页面执行 XPath 查询，返回匹配元素的文本或 HTML。可选 save_path 保存完整结果到文件，max_length 控制单条显示长度（默认从 config.json 读取，兜底 500） |
get_console_logs |
{} |
获取控制台日志 |
list_tabs |
{} |
列出所有标签页（显示 id、标题、URL，* 标记活动页） |
new_tab |
{"url": "..."} |
打开新标签页（url 可选，默认 about:blank） |
switch_tab |
{"tabId": 123456} |
切换到指定标签页（tabId 从 list_tabs 获取） |
close_tab |
{"tabId": 123456} |
关闭指定标签页 |
status |
- | 查询连接状态 |
quit |
- | 关闭服务器 |
What ships with it
7 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.
- 9d ago First seen · 238 lines · 100 tokens per session scan A 911ab8227d14
browser-chrome-agent is a skill published in the GitHub repository Tonyhzk/chrome-agent-skill (19 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 100 tokens to every session and 3,277 once invoked, about $0.0005 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…