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/guide-interactionnpx 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.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 | $0.00131 | $0.01140 |
| Opus 5 | $0.00066 | $0.00570 |
| Sonnet 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 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 — 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.
- 4d 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 (2,880 stars, last pushed yesterday), licensed MIT. It adds 131 tokens to every session and 1,140 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…