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/source-auditnpx skills add zts212653/clowder-ai --skill source-auditgit 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/source-audit)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/source-audit"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/source-audit.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 | $0.00095 | $0.03986 |
| Opus 5 | $0.00048 | $0.01993 |
| Sonnet 5 | $0.00019 | $0.00797 |
| Haiku 4.5 | $0.00010 | $0.00399 |
Grade A, and why
source-audit 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source Audit
Why This Is a Skill
F218 的事故不是模型凭空幻觉，而是外部不可靠信息源污染：多篇博客互引看起来像"多方验证"，但最终回到同一个营销来源。这个 skill 把"这东西靠谱吗？"绑到引用外部 claim 的动作上，补 WebSearch 和 deep-research 之间的中档。
Trigger
准备把外部 claim 写进回复、research、PPT、ADR、spec 或 review 结论时，命中任一特征就跑：
- 数字 / 百分比 / x 倍增长 / benchmark 排名
- 因果归因（"失败是因为..."）或趋势判断
- 模型能力对比、论文结论、医学/金融/法律等高风险主题
- 来源会进入长期文档，影响后续猫的判断链
不触发：只回答低风险常识；只引用官方文档原文且不外推；已经按 deep-research 跑完整多源调研。
L0 判断力镜头：先换坐标系，再查细节
这两副镜头来自家里的 Magic Words，不是给审计再加一套平行术语，也不能凭感觉代替证据。 它们负责产生可证伪的反事实；一手来源、baseline、干预和 holdout 负责裁决。
第一性原理 / 数学之美
先把论文去品牌化并缩成最小问题：
- 它声称原系统缺少什么能力，而不是缺少哪个作者命名的模块？
strongest_cheap_alternative是什么：强模型直接做、一句静态 prompt、短规则、 deterministic tool、retrieval / cache，还是一次人工配置？- 实验是否在独立证据上击败了这个替代物？
- 如果没有，claim ceiling 降到“自动搜索 / elicitation / 工程集成”，不得写成 “获得新能力 / 证明自进化必要”。
补锅匠 failure-mode audit
看到连续局部机制、多个 fallback 或“再加一个 evaluator / generator / memory”时，不逐块 验完就默认整条路线合理。做一次有边界的同类审计：
- 写出这些补丁共同在代偿的原始 failure mode；
- 区分真实世界约束与论文自己引入的坐标系；
- 问一个更直接的表示、契约或静态策略能否同时删掉多层；
- 对保留的每一层写明“去掉后哪条已观测证据会坏”；
- 若作者只证明每块都能工作、没证明原问题存在或整套不可约，保留 source validity， 但下调 non-triviality 与 decision fit。
禁止把 Magic Word 当作否定论文的结论。“这像补锅匠”只能触发 failure-mode hypothesis；
没有替代方案、ablation 或证据边界，就不能写 reject。
Claim Ledger
先列 claim，再逐条审：
| Claim | Metric / comparator | Strongest cheap alternative / claim ceiling | Inputs / raw outputs / reproduction | Scope / denominator / exclusions | Lifecycle cost / unknowns | 原始来源 | Source verdict | Non-triviality verdict | Decision fit | Provenance |
|---|---|---|---|---|---|---|---|---|---|---|
| ... | ... | ... | paper/config/data/checkpoint + transcript/failure/tail + run status | ... | ... | paper / official / vendor blog / media / forum | ... | ... | ... | ... |
八问 Checklist
这八问是按 claim 取用的 menu，不是逐项补齐的流水线：1/2/6/7 通常适用；3/8 在 claim 依赖方法或测量时使用；4/5 只在 claim 涉及实验、复现、稳定性或模型输出时触发。无对应 artifact 的传闻不要先造一轮实验审计，直接沿来源链和决策边界收敛。
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 · 219 lines · 95 tokens per session scan A be69b98d0c2a
source-audit is a skill published in the GitHub repository zts212653/clowder-ai (2,880 stars, last pushed yesterday), licensed MIT. It adds 95 tokens to every session and 3,986 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.
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…