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 expert-panelgit 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/expert-panel)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/expert-panel"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/expert-panel.svg" alt="Measured on agentmods" 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 | $0.00113 | $0.02319 |
| Opus 5 | $0.00056 | $0.01159 |
| Sonnet 5 | $0.00023 | $0.00464 |
| Haiku 4.5 | $0.00011 | $0.00232 |
Grade A, and why
expert-panel 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 8d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expert Panel — 多猫专家辩论团
仅显式调用：这是高成本多猫编排能力。只有用户明确点名
expert-panel/ “专家辩论” / “多猫分析”时才启用；普通“帮我分析一下”由单猫先判断和回答。
定位：编排层，不是独立流程。 复用已有协作习惯，只添加三样东西：角色分配、WHY 链标准、交付链。
核心原则：结论不值钱，论证过程才值钱。
本 skill 只管三件事
- 角色分配：按视角分工，确保多元
- WHY 链标准：每个结论必须有证据 → 推理 → 结论（这是 expert-panel 的独有增量）
- 交付链：洞察卡片 + 语音 + 报告
其余规则不重写，直接遵循已有 skill。协作交接用五件套（What/Why/Tradeoff/Open/Next）。
角色分配
参与猫按视角分工。最少 2 猫，推荐 3 猫。
| 角色 | 视角 | 职责 |
|---|---|---|
| Analyst | 架构/技术 | 技术深度、架构对比、可借鉴点 |
| Assessor | 风险/成本 | 成本结构、合规风险、踩坑预警 |
| Strategist | 生态/趋势 | 行业定位、大图景、用户/人才视角 |
| Convergence Lead | 收敛+交付 | 默认 Analyst 兼任，可指定 |
最小执行骨架
Dispatch → Independent → Synthesis → Contributor Check → Delivery
不是刚性 Phase，是自然节奏。有分歧就讨论，没有就是共识，不演。
1. Dispatch — 分发独立调研
Convergence Lead 用 multi_mention 分发给各猫。
dispatch payload 只允许包含：
- operator的原始问题（一字不改）
- 该猫的角色和视角
- 范围（调研边界）
- 输出格式要求（WHY 链四格）
- 原始材料（如有，如operator发的文件/链接）
dispatch payload 禁止包含：
- Lead 自己的判断、倾向、provisional conclusion
- Lead 的拆题方式或 framing（各猫自己决定怎么拆）
- 其他猫的摘要或分析
Lead 自己的分析等其他猫回来后再发，或和其他猫同时出。
2. Independent — 独立调研 + 独立分析
每只猫独立完成调研和分析，互不可见。
调研分两档：
| 档位 | 何时用 | 方法 |
|---|---|---|
| Light（默认） | 日常分析、快速判断 | WebSearch + search_evidence + 已有知识 |
| Full | 高 stakes / operator说"调研" / 需要多源验证 | 启动 deep-research skill 完整流程 |
不确定用哪档 → 用 Light。Light 不够再升级。
独立性保护规则（从 collaborative-thinking Mode B 内联）：
- 禁止互看：每只猫独立完成，不预测他人观点
- 防锚定：有背景材料时，先形成自己想法再参考
- 标注不确定性：区分确信的结论和猜测
分析输出格式 — WHY 链四格：
每个核心判断必须有：
Evidence: 具体证据（案例/数据/事件 + 来源URL或引用）
Reasoning: 从证据到结论的逻辑链（为什么这个证据支持这个结论）
So what: 对我们意味着什么（行动含义）
Confidence: 确信 / 中等 / 猜测
禁止：
- 光给结论不给论证（"基于行业经验" 不是证据）
- Evidence 和 Reasoning 混在一起（拆开写）
3. Synthesis — 收敛
Convergence Lead 汇总所有猫的分析，产出收敛报告。
收敛必须包含（来自 collaborative-thinking Mode B Phase 4）：
- 各方观点摘要
- 共识区
- 分歧区（不抹平！各方理由都保留）
- Tradeoffs / 适用边界（结论在什么场景成立、什么场景不适用）
- Open Questions（待operator拍板）
- 行动项
4. Contributor Check — 原作者复核
各猫确认收敛报告没有误读自己的观点。（来自 collaborative-thinking Mode B Phase 5）
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.
- 8d ago First seen · 209 lines · 113 tokens per session scan A a84dd760625a
expert-panel is a skill published in the GitHub repository zts212653/clowder-ai (2,940 stars, last pushed today), licensed MIT. It adds 113 tokens to every session and 2,319 once invoked, about $0.0006 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.
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…