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 agentmods add skills/opentiny/webmcp-sdk/webmcp-cli-skillnpx skills add opentiny/webmcp-sdk --skill webmcp-cli-skillgit 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/webmcp-cli-skill)<a href="https://agentmods.dev/skills/opentiny/webmcp-sdk/webmcp-cli-skill"><img src="https://agentmods.dev/badge/skills/opentiny/webmcp-sdk/webmcp-cli-skill.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 | $0.00049 | $0.06112 |
| Opus 5 | $0.00024 | $0.03056 |
| Sonnet 5 | $0.00010 | $0.01222 |
| Haiku 4.5 | $0.00005 | $0.00611 |
Grade A, and why
webmcp-cli-skill 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 4d 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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WebMCP CLI Skill
本 Skill 为第三方 AI Agent 提供完整说明,介绍如何通过 Model Context Protocol(MCP)使用 webmcp-cli 与浏览器页面交互。
何时使用
- 需要与网页交互(点击元素、填写表单、滚动页面)时。
- 需要读取当前 DOM 结构并识别可交互元素时。
- 在已注入领域专用工具的页面上操作时(例如 Excalidraw 绘图工具)。
安装
用户环境通常都已经安装好 webmcp-cli 工具,当shell终端提示找不到工具时,才进行下面的安装:
npm install -g @opentiny/webmcp-cli
命令
1. 管理浏览器标签页 webmcp-cli tabs
所有子级命令如下:
webmcp-cli tabs open https://excalidraw.com # 打开新网页
webmcp-cli tabs close <tabid> # 关闭指定标签页
webmcp-cli tabs switch <tabid> # 切换到指定标签页
webmcp-cli tabs back # 当前标签页后退
webmcp-cli tabs back <tabid> # 指定标签页后退
webmcp-cli tabs forward # 当前标签页前进
webmcp-cli tabs forward <tabid> # 指定标签页前进
2. 查询浏览器当前状态 webmcp-cli state
它返回当前浏览器的导航元数据(url、title、activeTabid、webmcpTools、所有已打开页签),是确认当前页面有哪些可用工具(webmcpTools)的唯一方式。
注意:
state不返回页面 DOM 内容(没有content字段)。需要获取可交互元素或页面信息状态时,请显式调用page-agent-tool的browserState或searchTree动作。
webmcp-cli state
webmcp-cli state -t <targetId> # target a specific tab by its real Chrome target ID
输出示例:
{
"url": "https://www.baidu.com/",
"title": "百度一下,你就知道",
"activeTabid": "2EA73ED323E46E5E108D4E46DA4E4AA7",
"webmcpTools": [{ "name": "page-agent-tool" }, { "name": "baidu_search" }],
"tabs": [
{ "tabid": "2EA73ED323E46E5E108D4E46DA4E4AA7", "title": "百度一下,你就知道", "url": "https://www.baidu.com/" }
]
}
返回值中, tabs 属性值是浏览器当前打开的全部标签页的信息,其它属性为当前激活页面的URL、标题、已注入的 MCP 工具列表(webmcpTools)。
tabid是 真实的 Chrome target ID(UUID)。配合-t可指定某个标签页。
webmcpTools的值的数组中如果有 system-overview的工具,并且在本轮对话中,该域名下没有调用过它,那么一定要立即执行一下 。system-overview工具的返回值能指导后续的操作,比如会包含网站的模块 & 路由 & 页面工具 &使用规范等等内容。
webmcp-cli run system-overview '{}'
何时必须调用 state
| 时机 | 是否必须先 state |
说明 |
|---|---|---|
执行 tabs open 之前 |
否 | tabs open 是唯一可在未先 state 的情况下直接执行的命令 |
执行 tabs 之后 |
是 | 新页面加载并注入工具后,须用 state 获取新页面的 webmcpTools |
执行 run 之前 |
是 | 须先通过 state 确认工具列表,再用 browserState 或 searchTree 获取页面可交互元素 |
连续多次 run 之间 |
视情况 | 若需重新确认工具列表或当前页面,才需再次 state;仅获取 DOM 变化直接使用 page-agent-tool 相关 action 即可 |
What ships with it
8 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.
- domains/excalidraw.md 10 KB
- domains/publish-article-in-csdn.md 4.9 KB
- domains/publish-article-in-juejin.md 3.9 KB
- domains/publish-article-in-oschina.md 4.2 KB
- domains/publish-article-in-segmentfault.md 5.1 KB
- domains/publish-article-in-zhihu.md 4.8 KB
- domains/publish-article.md 3.7 KB
- package.json 174 B
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.
- 4d ago First seen · 376 lines · 49 tokens per session scan A dbd6fd9e1ecc
webmcp-cli-skill is a skill published in the GitHub repository opentiny/webmcp-sdk (117 stars, last pushed 9d ago), licensed MIT. It adds 49 tokens to every session and 6,112 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
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
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.
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.
web-browser
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.
traceway-setup
Analyze and instrument repositories for Traceway observability. Use when the user wants to plan, add, migrate, or verify Traceway or OpenTelemetry monitoring for backend, browser, full-stack, mobile or iOS, or AI-agent software, including project topology and user-approved setup-plan creation. Backends use OTLP/HTTP…