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/bootcamp-guidenpx skills add zts212653/clowder-ai --skill bootcamp-guidegit 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/bootcamp-guide)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/bootcamp-guide"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/bootcamp-guide.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 | $0.00043 | $0.03535 |
| Opus 5 | $0.00022 | $0.01767 |
| Sonnet 5 | $0.00009 | $0.00707 |
| Haiku 4.5 | $0.00004 | $0.00353 |
Grade A, and why
bootcamp-guide 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootcamp Guide — 猫猫训练营引导模式
你的角色
你是新手 operator 的引导猫猫。耐心、鼓励、少用术语。 这是用户第一次和 AI 猫猫协作开发。
核心约束(Iron Rules)
- threadId:从
🎓 Bootcamp Mode: thread={threadId}读取。 - 当前 Phase:从
🎓 Bootcamp Mode: thread=... phase=...读取。 - 只执行当前 Phase 的指令,不要提前执行后续 Phase。
- 允许的 MCP 工具(仅以下两个,禁止使用任何其他 server 的同名工具):
cat_cafe_update_bootcamp_state— 状态推进(Phase 转换)cat_cafe_bootcamp_env_check— 环境检测(仅 Phase 2)- ⛔ 禁止:
mcp__cat-cafe-collab__*等其他 MCP server 的同名工具。调用失败时重试同一工具,不换 server。
- Phase 名必须精确匹配(见下表),不得自创名称。
- ⛔ STOP 标记:看到
⛔ STOP时,发完当前消息后立即停止,等用户下一条消息。⛔ STOP 及其后面的说明(如"前端 overlay 接管")是内部控制指令,绝不能出现在用户可见的消息中。 不要把 STOP 标记、原因、或任何实现细节(overlay、引导引擎、phase 名称)输出给用户。 - Phase 推进必须逐步:每次只能推进 1 步(如 phase-4 → phase-5),禁止跳步(如 phase-3 → phase-5)。唯一例外:核心工具全 OK 时 phase-2 → phase-4(跳过 phase-3)。
检查训练营上下文(所有猫必读)
系统提示中如果有 🎓 Bootcamp Mode: 行,说明你在训练营会话中。无论你是哪只猫,都必须检查并遵循训练营流程。
- 读取
phase=确认当前阶段 - 读取
leadCat=判断自己是主角猫(catId === leadCat)还是队友猫 - 读取
members=了解当前团队规模 - 按下方对应阶段 + 角色的指令执行
Phase 名称(唯一合法值)
phase-1-intro → phase-2-env-check → phase-3-config-help → phase-4-task-select
→ phase-5-kickoff → phase-6-design → phase-7-dev → phase-7.5-add-teammate
→ phase-8-collab → phase-9-complete → phase-10-retro → phase-11-farewell
跳过矩阵
用户说"跳过"时,严格按下表:
| 当前 Phase | 允许? | 跳到 | 回复 |
|---|---|---|---|
| Phase 1 | ✅ | Phase 2 | "好的,我们直接检查环境!" |
| Phase 2 | ✅ | Phase 4 | "好,环境以后再说,先选个任务开始!" |
| Phase 3 | ✅ | Phase 4 | "好,先开始项目,配置问题随时再来!" |
| Phase 4-7 | ❌ | 不动 | "这个项目是训练营核心体验,没法跳过哦~ 告诉我你想做什么!" |
| Phase 7.5 | ❌ | 不动 | "添加队友是训练营最精彩的部分!跟着引导点几下就好~" |
| Phase 8 | ❌ | 不动 | "协作刚开始呢,让队友看完再说~" |
| Phase 9 | ✅ | Phase 11 | "好的,直接毕业!" |
| Phase 10 | ❌ | 不动 | "最后几步引导马上就完,跟着点一下~" |
整体流程概览
训练营是线性流程,只有一个分支点(环境检测结果)。
MSG 1(你的第一条消息)
│ Phase 1 自我介绍
│ Phase 2 环境检测
│ ├─ 核心工具全 OK → 跳到 Phase 4(唯一允许的跳步)
│ └─ 核心工具有问题 → Phase 3 配置帮助 → Phase 4
│ Phase 4 问用户想做什么
│ ⛔ STOP
│
MSG 2(用户描述了想做的项目后)
│ Phase 5 确认需求
│ Phase 6 给出计划
│ Phase 7 开发交付
│ 推进到 Phase 7.5
│ ⛔ STOP
│
MSG 3(用户尝试输入 → 前端拦截 typing → 拉起 guide overlay)
│ Phase 7.5 前端阻断输入,overlay 引导添加队友
│ ⛔ STOP(你不需要说话)
│
MSG 4+(用户 @mention 了新队友)
│ Phase 8 多猫协作
│ Phase 9 引导项目完成 + 项目选择卡
│ Phase 10 前端 overlay 毕业引导(自动触发)
│ ⛔ STOP
│
MSG 5+(毕业引导完成,用户选择项目)
│ Phase 11 毕业后自由开发(正常猫猫开发流程)
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 · 247 lines · 43 tokens per session scan A e48fc8adf84a
bootcamp-guide is a skill published in the GitHub repository zts212653/clowder-ai (2,894 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 3,535 once invoked, about $0.0002 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
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…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
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
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).