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 thread-orchestrationgit 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/thread-orchestration)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/thread-orchestration"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/thread-orchestration/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/thread-orchestration"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/thread-orchestration.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 | $0.00195 | $0.05873 |
| Opus 5.5 | $0.00078 | $0.02349 |
| Sonnet 5.5 | $0.00039 | $0.01175 |
| Haiku 4.5 | $0.00019 | $0.00587 |
Grade A, and why
thread-orchestration 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 14d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thread Orchestration — 多 Thread 并行编排
核心理念:thread 承载工作现场,猫按本次任务承担角色。指挥、执行、验收不绑定猫名、家族或模型档位;责任归属与通讯路径分别明确。
组织三种现场、跨执行现场依赖或小团队排班时,先读 星系协作契约。这是本 skill 的角色与通讯约定;发送、授权核验、审查与处置仍走对应 skill,不新增球权账本。
何时触发
发现跨 scope 的问题/信息?
→ 先 list_threads keyword=<关键词> 查有没有已有 thread
→ 有已有 thread → 不要新建!用 cross_post_message 投递(cross-thread-sync skill)
→ 没有已有 thread + 需要独立追踪 → 本 skill:propose_thread
任务可以拆成多个独立子任务?
→ 有依赖? → 独立部分并行;共享写入面单写,消费点等确切接口产物
→ 子任务独立? → 本 skill:开 thread 并行推进
只有一个任务? → 不需要本 skill,直接做
F128/F193 环(KD-E4):
propose_thread(新建)和cross_post_message(投递)是一个环。 默认走投递(cross_post_message),只有确认没有已有 thread 时才走新建(propose_thread)。 新建 thread 的阈值高于投递——新建会增加operator的认知负担。
五步流程
Step 1: 拆解 — 识别独立可交付单元
判定标准:各自有可判断的交付物,且能划清写入面与消费依赖;能在不同 worktree 编辑不是充分条件。有共享接线时只串行该写入面,其余独立部分可并行。
拆解时明确每个子任务的:
- Scope: 改哪些文件/模块
- 交付物: 代码 + 测试 + 文档(具体到文件)
- 验收条件: 用户实得与证据;区分代码交付、已加载运行版本和真实旅程通过
- 角色与依赖: 当前执行责任猫、共享写入面、直接依赖方、可先做的部分、必须停下的消费点
- 完成边界: 整项委派何时结束、结果回哪里;分片 PR 合入不自动结束整项责任
Step 2: 提议 Thread — 每个子任务一个提议(用户审批后才创建)
重要:cat 不直接创建 thread。 调用 cat_cafe_propose_thread 创建一个提议卡片,等用户在 source thread 里点"批准",后端才真正创建 thread。
→ cat_cafe_propose_thread(
title: "简洁描述任务目标",
reason: "为什么这个子任务值得自己一个 thread(必填)",
preferredCats: ["<实际起跑猫 catId>"], // 多猫可能形成接龙;review 候选不当作必跑名单
projectPath: "/abs/path/to/repo", // 子 thread 的工作区/真相源归属;不是外部目标仓
reportingMode: "final-only" // 可选回报契约: none/final-only(默认)/state-transitions/blocking-ack,见下表
)
返回值:{ proposalId, status: "pending" } —— 不是 threadId。Thread 还未存在,不要尝试 cross_post 到一个尚未批准的 proposal。
社区 PR / issue 分发: title / reason / initialMessage 中出现外部 PR/issue 时,
服务端不再自动注入 opensource-ops maintainer 五问、猜测作者角色或写入 PR metadata。
子 thread 的第一项工作是主动加载 opensource-ops skill,在 child workspace 内完成 provider
object 与 author grounding,再执行 maintainer 五问与 custody 判断。本地猫替外部作者修代码需要
显式 Strategy B 授权 provenance,不能默认派给 preferredCats 里的猫。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 14d ago Changed · +4 lines · +16 tokens per session 23c893b6fae2
- 1mo ago Changed 6db641613b10
- 1mo ago Changed e2f46b01fd9c
- 1mo ago Changed · +1 lines 1ee529ae12e4
- 1mo ago First seen · 264 lines · 179 tokens per session scan A 624edd5fa2c3
thread-orchestration is a skill published in the GitHub repository zts212653/clowder-ai (3,471 stars, last pushed today), licensed MIT. It adds 195 tokens to every session and 5,873 once invoked, about $0.0008 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…