Clowder AI is a self-hosted workspace where AI agents from different model families work together as a persistent team, retaining identities, shared evidence, and memory across tasks. It is for people who want to coordinate multiple AI agents without repeatedly rebuilding their context.
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 zts212653/clowder-ai --skill browser-automationgit clone --depth 1 https://github.com/zts212653/clowder-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/zts212653/clowder-ai/browser-automation)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/browser-automation"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/browser-automation.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 86 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00133 | $0.02152 |
| Opus 5 | $0.00067 | $0.01076 |
| Sonnet 5 | $0.00027 | $0.00430 |
| Haiku 4.5 | $0.00013 | $0.00215 |
Grade A, and why
browser-automation 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation
这是家里的上层浏览器路由 skill。
它只做三件事：
- 判断这次任务该不该用浏览器
- 选择合适的浏览器后端
- 把任务转给更具体的 skill / ref，而不是在这里重复厂商文档
执行前四问
在真正打开浏览器前，先回答这四个问题：
- 真的需要浏览器吗？ 如果只是读文档、抓纯文本、做搜索，不要默认上浏览器。
- 目标是 localhost 还是外部网站？
localhost→browser-preview；外部网站才留在本 skill。 - 这只猫的客户端能力是什么？
MCP 原生、CLI-only、是否有
webfetch、是否能跑 shell、是否有 VL。 - 这次任务的 session 属于谁？ 是匿名访问、猫自己的浏览器会话、还是接手人类已登录会话。
什么时候用
- 目标是外部网站，需要真实浏览器执行 JS、登录、点按钮、下载、截图
- 猫没有
webfetch，或者webfetch不足以完成交互 - 需要在
agent-browser/Playwright MCP/Playwriter/PinchTab之间做路由 - 需要明确“这类浏览器任务的默认打法是什么”
不要用在这里
localhost页面预览、HMR、给operator看效果 → 用browser-preview- 本地 WebApp 的确定性测试、Console、截图、回归验证
→ 用
webapp-testing - 简单网页抓取、官方文档阅读、搜索结果整理 → 优先用更轻量的搜索 / fetch 工具，不要先上浏览器
- 已有领域专用浏览器 skill 的任务 → 专用 skill 优先
默认路由顺序
- 先问：真的需要浏览器吗？ 如果只是读文档、抓纯文本、做搜索，不要默认上浏览器。
- 目标是 localhost 吗？
是 →
browser-preview - 目标是本地 WebApp 验证吗？
是 →
webapp-testing - 客户端已经有稳定可用的 Playwright MCP 吗？
是 →
refs/playwright-mcp.md（MCP ID:playwright） - 需要接手人类已登录的 Chrome、复杂 iframe、多 tab 调试吗？
是 → 用
claude-in-chromeMCP（工具前缀mcp__claude-in-chrome__*），参考refs/playwriter.md - 这是 CLI 型猫，没 webfetch / 没 VL，但能跑命令吗？
是 →
refs/agent-browser.md（MCP ID:agent-browser，社区 wrapper，使用前先做本机验活） - 需要长驻 daemon、持久 session、HTTP-first 服务吗？
是 →
refs/pinchtab.md（MCP ID:pinchtab，优先 native binarypinchtab mcp，不要默认相信 npm wrapper）
路由矩阵
| 场景 | 默认 | MCP ID | 状态 |
|---|---|---|---|
| 本地前端页面预览 | browser-preview |
— | 独立 skill |
| 本地 WebApp 测试 / 回归 | webapp-testing + Playwright |
playwright |
已接入 |
| MCP 原生客户端的常规网页自动化 | Playwright MCP |
playwright |
✅ 已接入 — npx @playwright/mcp@latest |
| 已登录 Chrome、iframe-heavy、手工接管 | claude-in-chrome |
claude-in-chrome |
✅ 已接入 — Chrome 扩展管理，无需手动启动 |
| CLI 型猫、没 webfetch / 没 VL | agent-browser |
— (CLI 工具) | ✅ 可用 — npm i -g agent-browser，通过 Bash tool 调 CLI |
| 服务化浏览器、持久化 session、重复批任务 | PinchTab |
pinchtab |
✅ 已接入 — native binary pinchtab mcp（外网 URL 用 eval 导航，见 ref） |
What ships with it
4 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 · 150 lines · 133 tokens per session scan A a77fd62b4292
browser-automation is a skill published in the GitHub repository zts212653/clowder-ai (2,940 stars, last pushed today), licensed MIT. It adds 133 tokens to every session and 2,152 once invoked, about $0.0007 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…