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 deep-researchgit 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/deep-research)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/deep-research"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/deep-research.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 | $0.00102 | $0.03682 |
| Opus 5 | $0.00051 | $0.01841 |
| Sonnet 5 | $0.00020 | $0.00736 |
| Haiku 4.5 | $0.00010 | $0.00368 |
Grade A, and why
deep-research 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
两种模式:
- Mode A: 多源调研:Web 猫(网络搜索)+ Coder 猫(代码判断)+ GPT-5.2 Pro(审阅)= 三角验证
- Mode B: 云端模型咨询:本地猫总结背景 → operator发给云端模型 → 回填结果 → 本地猫综合
两种猫,各有分工
| Web 猫(Deep Research 模式) | Coder 猫(CLI/Clowder AI) | |
|---|---|---|
| 强项 | 搜 100+ 来源,有引用 | 读项目代码,跑测试 |
| 弱点 | 不了解我们的 codebase | 网络搜索深度有限 |
| 用途 | Step 2 并行调研 | Step 4 综合判断 |
不适用场景:
- 快速事实查询(直接用 WebSearch)
- 纯代码问题(用 Explore agent)
- 项目文档里已有答案
文件组织规范(铁律)
一个研究课题 = 一个子目录。只要产出超过 1 个文件,就必须建子目录,禁止在 project-research/ 平铺散落。
project-research/YYYY-MM-DD-{topic}/
├── prompt.md # Step 1 研究提示词(同时保留到 docs/prompts/ 的副本)
├── {provider}-response.md # Step 2 云端 deep research 原文
│ 例:claude-response.md / gemini-response.md / gpt-response.md
├── gpt-pro-review.md # Step 3 GPT Pro 审阅(可选)
├── {cat}-synthesis.md # Step 4 猫猫独立综合分析
│ 例:opus-synthesis.md / codex-synthesis.md / opus47-synthesis.md
├── {cat}-点评.md # 非代码猫的风格点评(如Siamese)
└── synthesis.md # 最终合并综合(如果有)
命名规则:
{topic}用英文 kebab-case(如finance-provider-stack、memory-architecture){provider}= 云端模型标识:claude/gemini/gpt/gpt-pro{cat}= 猫猫名:opus/opus47/codex/gemini-cat(避免和 provider 名冲突时加-cat)- 如果只有 1 个文件(如单次 Mode B 咨询),可以不建子目录,直接放
project-research/
Mode B 咨询归属:如果咨询是某个已有研究课题的一部分,文件放进该课题子目录(不另建目录)。
四步流程
Step 1 — 写 Prompt 并落盘
project-research/YYYY-MM-DD-{topic}/prompt.md
(同时复制一份到 docs/prompts/YYYY-MM-DD-{topic}-research-prompt.md,向后兼容)
模板见下方。写完再发,不要边写边发。
Step 2 — 三路并行 Web 调研
同一个 prompt →
Claude.ai Deep Research
Gemini Deep Research
ChatGPT Deep Research ← 可能先问澄清问题,答完后把 Q&A 追加到另外两路的 prompt
结果存:project-research/YYYY-MM-DD-{topic}/{provider}-response.md
Step 3 — GPT-5.2 Pro 审阅
输入三份报告 → 找逻辑漏洞、弱证据、三方分歧
存:project-research/YYYY-MM-DD-{topic}/gpt-pro-review.md(注意:Pro 是审阅者,不是调研者,不要让他搜索)
Step 4 — Coder 猫综合 + 决策
读全部四份文档 → 对照实际 codebase 验证 → 标注"直接可用/需验证/项目特殊约束"
如果多只猫并行综合,每只猫存自己的:{cat}-synthesis.md
最终合并版:synthesis.md → 和operator讨论 → 落到 ADR
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 · 316 lines · 102 tokens per session scan A 47e6151e5010
deep-research is a skill published in the GitHub repository zts212653/clowder-ai (2,924 stars, last pushed today), licensed MIT. It adds 102 tokens to every session and 3,682 once invoked, about $0.0005 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-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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…