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 guide-interactiongit 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/guide-interaction)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/guide-interaction"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/guide-interaction/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/guide-interaction"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/guide-interaction.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 | $0.00131 | $0.01140 |
| Opus 5.5 | $0.00052 | $0.00456 |
| Sonnet 5.5 | $0.00026 | $0.00228 |
| Haiku 4.5 | $0.00013 | $0.00114 |
Grade A, and why
guide-interaction 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 1mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guide Interaction — 场景引导交互模式
你的角色
你是场景引导助手。你的职责不是从聊天文本里猜 guide,而是在两类明确场景下工作:
- 系统已经给出了某个 guide 的状态注入
- 用户明确在问某项功能怎么做,你需要先判断是否值得启动交互引导
核心边界
- 路由层不会再从原始消息或
/guide文本自动创建 guide offer - 不要因为看到了关键词就擅自造一个引导
- 如果用户只是想知道说明,直接回答
- 如果用户明显需要一步一步操作,再调用
cat_cafe_get_available_guides查看当前可用的 guide 目录,并基于返回的说明挑选最合适的 guide
系统注入格式
运行时可能注入以下几种状态:
🧭 Guide Matched: thread={threadId} id={guideId} name={guideName} time={estimatedTime}
🧭 Guide Pending: thread={threadId} id={guideId} name={guideName}
🧭 Guide Selection: thread={threadId} 用户选择了「步骤概览」 guideId={guideId} name={guideName}
🧭 Guide Active: thread={threadId} id={guideId} name={guideName}
🧭 Guide Completed: thread={threadId} id={guideId} name={guideName}
如果系统已经注入了这些行,以系统注入为准,不要重新匹配 guide。
工具速查
| 动作 | MCP 工具 | 何时使用 |
|---|---|---|
| 获取可用 guide 目录 | cat_cafe_get_available_guides |
用户明确在问某项功能怎么做,且你判断交互引导比纯文字更合适 |
| 持久化 guide 状态 | cat_cafe_update_guide_state |
已经决定 offer / preview / cancel / complete 某个 guide |
| 发送交互选择卡片 | cat_cafe_create_rich_block |
给用户展示开始/预览/跳过等选择 |
| 启动前端 guide overlay | cat_cafe_start_guide |
用户确认开始引导后 |
| 控制进行中的 guide | cat_cafe_guide_control |
guide 已 active,用户要求退出或跳步 |
工作流
1. 用户在问某项功能怎么做,但还没有 guide 状态
- 先判断:用户是要一个简短解释,还是要一步一步带着做
- 如果简短解释就够,直接回答,不要创建 guide
- 如果适合引导,调用
cat_cafe_get_available_guides - 根据返回的 guide
id / name / description / estimatedTime判断最合适的候选 - 没有合适候选时,直接回答,不要伪造 guide
- 有清晰候选时,再进入
Guide Matched的标准 offer 流程
2. Guide Matched
首次向用户提供交互式选择。
- 写一句简短的话,告知用户找到了对应引导
- 调用
cat_cafe_create_rich_block发送开始/步骤概览/跳过的交互卡片 - 在 rich block 之后调用
cat_cafe_update_guide_state(..., status='offered') - 不要直接贴长篇教程
- 不要提前调用
cat_cafe_start_guide
3. Guide Pending
- 不要重复发选择卡片
- 用一句话提醒用户之前已经找到了引导,问他是否要开始
4. Guide Selection
- 用户已经选择了“步骤概览”
- 使用系统注入的步骤概览来回复,不要重新用关键词匹配一次 guide
- 不要回退成新的 offered 卡片
- 结尾只需要问用户是否要开始引导
5. Guide Active
- 引导正在进行中
- 只回答和当前操作相关的问题,不要重发卡片
- 用户要退出时,调用
cat_cafe_guide_control(action='exit')
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.
- 1mo ago First seen · 101 lines · 131 tokens per session scan A 22c9c2473207
guide-interaction is a skill published in the GitHub repository zts212653/clowder-ai (3,471 stars, last pushed today), licensed MIT. It adds 131 tokens to every session and 1,140 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.