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 agentmods add skills/zts212653/clowder-ai/browser-previewnpx skills add zts212653/clowder-ai --skill browser-previewgit 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-preview)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/browser-preview"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/browser-preview.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 | $0.00072 | $0.02702 |
| Opus 5 | $0.00036 | $0.01351 |
| Sonnet 5 | $0.00014 | $0.00540 |
| Haiku 4.5 | $0.00007 | $0.00270 |
Grade A, and why
browser-preview scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w "%{http_code}" http://localhost:PORT How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Preview
Hub 内置了嵌入式浏览器面板(F120),可以直接预览运行中的 localhost 应用。猫猫写完前端代码不用让operator切浏览器看效果。
工作流
基础流程(端口发现 → 预览)
- 启动 dev server:交互 Terminal 可直接前台跑;要把页面交给operator跨回合查看时,猫的 invocation/
-p会话必须用仓库的 managed launcher:pnpm preview:process start --port PORT --cwd /absolute/project/path -- COMMAND [ARGS...]macOS 上它会把目标直接注册为一次性 user LaunchAgent;普通 detached child、nohup、setsid或 PTY 都不算独立托管。 - Hub 自动检测端口 → 弹出 toast 提示"检测到 localhost:xxxx 启动"
- 点击 Open Preview → 自动打开 browser panel 并加载页面
- 也可以手动:切到 workspace 的 Browser tab,输入
localhost:port按 Go
改代码 → HMR 热更新 → browser panel 内页面自动刷新,无需手动操作。
猫主动打开浏览器(Phase C — 必须掌握)
operator说过:"别手动让我输入,你最好打开浏览器,把页面放出来。"
猫应该主动替operator打开浏览器,不要等operator点 toast 或手动输 URL。
调用步骤(按顺序执行,不要跳步)
Step 1: 确认目标服务器在跑
若由猫启动,先用 managed launcher 启动/查状态:
pnpm preview:process start --port PORT --cwd /absolute/project/path -- COMMAND [ARGS...]
pnpm preview:process status --port PORT --cwd /absolute/project/path --json
→ 只有 status=running 才进入下步;unavailable/unmanaged/stopped 必须如实报告
→ macOS 跨回合展示还必须有 origin=launchd;origin=detached 只证明 launcher 已退出,
没证明脱离 invocation supervisor,不得承诺“回复后还会活着”
curl -s -o /dev/null -w "%{http_code}" http://localhost:PORT
→ 200/301/304 = 可以继续
→ 000/connection refused = 服务器没起来,先启动再说
Step 2: 调用 typed MCP
cat_cafe_preview_open({
port: PORT,
path: "/",
worktreeId: "当前 worktreeId(有就传)",
threadId: "当前 threadId(有就传)"
})
Step 3: 读返回的 deliveryStatus,再决定怎么报告
→ applied = Hub 前端真实接收并应用了(面板已打开)——只有这时才能说"已打开"
→ queued = 目标 thread 不在前台,已写入其 ThreadState;切到该 thread 自动揭示
→ blocked = presentation lock 等阻止了展示(看 deliveryReason)
→ unconfirmed = 没有任何 Hub 客户端确认送达(没连接 / 无匹配 client)——必须如实说"未能确认打开"
admission ≠ visible:
allowed: true只证明服务端受理了请求。报告"已打开"之前必须看到deliveryStatus: "applied"。
running ≠ durable:同一 invocation 内的
status: "running"只证明当前可达。macOS 只有origin: "launchd"才证明已经交给用户会话级服务管理;“确实跨回合存活”必须由后续 invocation 的 status/HTTP 探针或operator现场画面确认。
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.
- 5d ago First seen · 155 lines · 72 tokens per session scan A 9c77315a75ee
browser-preview is a skill published in the GitHub repository zts212653/clowder-ai (2,880 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 2,702 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
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.