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 opentiny/webmcp-sdk --skill wxtgit clone --depth 1 https://github.com/opentiny/webmcp-sdkWrote 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/opentiny/webmcp-sdk/wxt)<a href="https://agentmods.dev/skills/opentiny/webmcp-sdk/wxt"><img src="https://agentmods.dev/badge/skills/opentiny/webmcp-sdk/wxt/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/opentiny/webmcp-sdk/wxt"><img src="https://agentmods.dev/badge/skills/opentiny/webmcp-sdk/wxt.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 | $0.00068 | $0.01985 |
| Opus 5.5 | $0.00027 | $0.00794 |
| Sonnet 5.5 | $0.00014 | $0.00397 |
| Haiku 4.5 | $0.00007 | $0.00198 |
Grade A, and why
webmcp-cli-wxt 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 24d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WebMCP CLI (WXT 扩展桥接模式) Skill
本 Skill 指导 AI Agent 如何通过 @opentiny/webmcp-cli --mode wxt 与用户正在使用的真实 Chrome 浏览器(通过 Tiny Robot 扩展)进行双向通信与操控。
适用场景与特征
- 复用真实用户数据:直接在用户正在使用的浏览器窗口中工作,完美继承用户的登录态、Cookie、企业内网 SSO 会话、已有标签页,告别验证码和重新登录。
- 扩展与本地双向协同:
- 本地 Agent 可直接操控浏览器中的网页;
- 浏览器扩展在遇到需本地环境的任务时,可通过 WebSocket 桥接安全请求本地执行 bash 指令或选择目录。
- 高层子代理委托 (
agent run):除了单步交互,可直接将高层任务整包委托给扩展内的 Tiny Robot 自主多轮执行。 - 标识特征:
- 必须携带模式参数:
webmcp-cli --mode wxt <command>(或在终端设置环境变量export WEBMCP_MODE=wxt); - Tab ID 格式为 纯数字(Chrome Tab ID,如
1024); - 依赖用户已安装并启用 Tiny Robot 扩展。
- 必须携带模式参数:
安装
当 shell 终端提示找不到工具时执行:
npm install -g @opentiny/webmcp-cli
快速准备与前置排查
1. 认证 Token 与配对
CLI 与扩展之间通过 Token 进行安全鉴权,默认保存在 ~/.robot-wxt/bridge-token。
# 查看当前本地 Token(若扩展未连接,可将输出的 Token 配置到扩展设置中)
webmcp-cli --mode wxt token
# 将已有的扩展 Token 同步到本地
webmcp-cli --mode wxt token set <你的Token>
2. 后台守护进程(Daemon)
无需手动启动服务,执行任何 WXT 命令时 CLI 会自动拉起后台 WebSocket 桥接进程(监听 127.0.0.1:18999)。
如需手动释放端口或停止后台服务:
webmcp-cli --mode wxt stop
3. 连接异常排查
若执行命令报连接超时或等待扩展连接,请指导用户:
- 检查 Chrome 右上角是否已安装并启用 Tiny Robot 扩展;
- 确认扩展弹窗中的 Bridge Token 是否与
webmcp-cli --mode wxt token一致。
交互模式一:高层子代理委托 (agent run) — 推荐
对于复杂、跨步骤的开放式任务(如“帮我查一下上个月的订单并导出报表”、“把该商品加入购物车”),优先整包委托扩展自主执行,无需本地逐行编写点击代码:
# 委托扩展内的 Tiny Robot 自主执行
webmcp-cli --mode wxt agent run "帮我把购物车中的第一个商品结算"
# 限制最大步数自主执行
webmcp-cli --mode wxt agent run --max-steps 10 "搜索最新的 TinyVue 实战教程"
# 针对指定页签执行
webmcp-cli --mode wxt agent run --tab 1024 "审批当前页面的加班申请,意见填同意"
交互模式二:细粒度自主交互(标准流程)
1. 状态感知与标签页管理
# 查询当前活跃标签页与可用工具
webmcp-cli --mode wxt state
# 查询指定标签页(注意:WXT 模式下 Tab ID 必须为纯数字)
webmcp-cli --mode wxt state --tab 1024
# 标签页操作
webmcp-cli --mode wxt tabs open "https://console.cloud.example.com"
webmcp-cli --mode wxt tabs switch 1024
webmcp-cli --mode wxt tabs close 1024
webmcp-cli --mode wxt tabs back
webmcp-cli --mode wxt tabs forward
2. 页面元素感知与操作 page-agent-tool
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.
- 24d ago First seen · 189 lines · 68 tokens per session scan A f5a1e9a60875
webmcp-cli-wxt is a skill published in the GitHub repository opentiny/webmcp-sdk (121 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 1,985 once invoked, about $0.0003 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 2026-09-22.
Other skills, from other repositories
webmcp-cli-skill
A skill containing instructions for installing and running webmcp-cli, a command-line tool for letting AI agents interact with browser pages. It includes descriptions of specialised tools available on pages with injected WebMCP tools.
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.