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 rich-messaginggit 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/rich-messaging)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/rich-messaging"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/rich-messaging/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/zts212653/clowder-ai/rich-messaging"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/rich-messaging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.02907 |
| Opus 5 | $0.00036 | $0.01453 |
| Sonnet 5 | $0.00014 | $0.00581 |
| Haiku 4.5 | $0.00007 | $0.00291 |
Grade A, and why
rich-messaging 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 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.
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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rich Messaging
你可以发送富媒体消息——语音、图片、卡片、清单、代码 diff、交互选择。不只是打字！
不只是对话：定时任务唤醒你后，你依然拥有全部 rich block 能力——发图、发语音、发 HTML 面板、发交互选择，都可以。
首次使用
每个 session 首次发 rich block 前，先调 get_rich_block_rules 获取完整字段规格。
本 skill 只给决策指引和最小示例，细则在 MCP 工具里。
默认触发：Chat 内可见交付
统一判断不是用户有没有说“富文本”，而是：用户是否要在当前 Clowder AI Chat 里直接看到、听到或操作结果。 命中时，生成一个本地文件或贴源码路径都不算完成；产物必须进入 rich block 或 Browser panel。不要求用户说出“富文本”这个实现词。
| 用户真正要的交付 | 默认执行面 |
|---|---|
| 自包含 HTML、demo、图表、计算器、小交互 | html_widget |
| 已有截图、图片、设计稿或多图对比 | media_gallery |
| 复杂 localhost 页面、多组件或多页面应用 | browser-preview |
| 需要新生成一张图片 | image-generation，生成后仍要发布回 Chat |
反例：讨论 HTML 渲染原理、修改 index.html、review 一段前端源码，不等于要求可视交付，不应自动发 rich block。灰例“做完整页面让我看”默认走 browser-preview，不是把完整应用硬塞进 html_widget。
默认触发：长结构化汇报
当你想发一堆文字、日志、步骤，或回复已经有 3+ 结构化信号（列表、表格、代码块、diff、状态字段、行动项）时，默认用 1-2 句自然语言摘要 + cat_cafe_create_rich_block。纯长 Markdown 只在 rich block 不适合或工具不可用时使用，并说明原因。
八种 Rich Block 一览
| Kind | 什么时候用 | 关键字段 |
|---|---|---|
| audio | 打招呼、表达情感、庆祝、鼓励、定时播报 | text（短句口语化） |
| card | 状态报告、决策摘要、review 结论 | title + tone |
| checklist | 待办、验证步骤、行动项 | items |
| diff | 代码修改建议、重构对比 | filePath + diff |
| file | 发送已有文件、文档、音视频成片；video/* 可内联播放 |
url + fileName |
| media_gallery | 发送已有图片（头像、照片）、截图、设计稿、多图对比 | items (url) |
| interactive | 让用户选方案、勾选项、确认操作 | interactiveType + options (id+label) |
| html_widget | 你写的 HTML 直接挂上去：图表、计算器、CSS 动画、数据面板 | html（完整 HTML/JS/CSS 代码字符串） |
最小工作示例
语音（audio）
{"id": "a1", "kind": "audio", "v": 1, "text": "喵，恭喜完成了喵！"}
卡片（card）
{"id": "c1", "kind": "card", "v": 1, "title": "Review 通过", "tone": "success", "bodyMarkdown": "0 P1 / 0 P2，放行合入。"}
清单（checklist）
{"id": "cl1", "kind": "checklist", "v": 1, "title": "下一步", "items": [{"id": "i1", "text": "跑测试"}, {"id": "i2", "text": "开 PR"}]}
Diff
{"id": "d1", "kind": "diff", "v": 1, "filePath": "src/foo.ts", "diff": "- old line\n+ new line", "languageHint": "typescript"}
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 Changed · +12 lines · -36 tokens per session 022db7e41a48
- 9d ago First seen · 193 lines · 108 tokens per session scan A 1d823f095960
rich-messaging is a skill published in the GitHub repository zts212653/clowder-ai (2,940 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 2,907 once invoked, about $0.0004 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.