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/collaborative-thinkingnpx skills add zts212653/clowder-ai --skill collaborative-thinkinggit 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/collaborative-thinking)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/collaborative-thinking"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/collaborative-thinking.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 | $0.00096 | $0.02669 |
| Opus 5 | $0.00048 | $0.01334 |
| Sonnet 5 | $0.00019 | $0.00534 |
| Haiku 4.5 | $0.00010 | $0.00267 |
Grade A, and why
collaborative-thinking 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 4d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Collaborative Thinking
三种思考模式:单人探索 / 多猫独立思考 / 讨论收敛沉淀。与 feat-lifecycle 讨论阶段的区别:feat-lifecycle 专用于 feat 采访和需求澄清;本 skill 是通用思考框架。
核心知识
| 模式 | 何时用 | 何时不用 |
|---|---|---|
| A 单人探索 | 1:1 功能设计、想法 → spec | 需要多视角的方向性决策 |
| B 多猫思考 | 架构选型、流程设计、跨模型互补 | 实现细节、bug 定位(token 成本不值) |
| C 收敛沉淀 | 任何讨论产出了决策/规则/否决理由 | 纯问答(结论在 thread 里已够)、operator说"不用记" |
Mode A: 单人探索 (Brainstorm)
目标:将模糊想法转化为可执行 spec,通过增量验证降低返工。
- 理解上下文:先读项目现状(文件、文档、近期 commits)。每次只问一个问题,优先多选题。
- 探索方案:提出 2-3 个备选 + tradeoffs,先说推荐和理由。YAGNI 无情剪枝——"以后可能需要"的功能先砍。
- 呈现设计:每次 200-300 字,每段后问"这个方向对吗?"。覆盖:架构 / 组件 / 数据流 / 错误处理 / 测试。
- 产出:设计文档写到
feature-specs/YYYY-MM-DD-{topic}-design.md,commit 后问"要开始实现了吗?"
Mode B: 多猫独立思考
何时启动 Mode B? 参见 ../.cat-cafe-shared-refs/shared-rules.md §13 元思考触发器 A-D。
调 cat_cafe_multi_mention 前必须带搜索证据(searchEvidenceRefs)。
⚠️ 成本警告:Swarm token 消耗是单猫 N 倍(N = 参与猫数)。实现细节不值得开 swarm。
6 阶段流程:
Phase 1: 独立思考(并行,禁止互看)
Phase 2: 串行讨论(有分歧才触发,限 2-3 轮)
Phase 3: operator选扇入者
Phase 4: 扇入综合(会议纪要 + 行动项)
Phase 5: 其他猫审阅补充(纠正误读)
Phase 6: operator反馈 + 最终确认 → 进入 Mode C
Phase 1 独立性保护规则(最重要):
- 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
- 展示推理链:"我为什么这么想",不只给结论
- 标注不确定性:区分确信的结论和猜测
实现方式:routeParallel() 或operator分别 @ 各猫并强调"先独立思考"。
Phase 2 触发:各方基本一致 → 跳过;存在明显分歧 → 需要(限 2-3 轮);operator说"够了" → 跳过。
Phase 4 综合必须包含:各方观点摘要 / 共识区 / 分歧区(不要抹平!)/ 待决事项 / 行动项。
Open Questions 分类(必须拆开):
- 技术 OQ:给猫猫解决的(实现细节、方案选型中可回滚的部分)
- 价值 OQ:需要 operator 判断的 → 必须附 Decision Packet(格式见
../.cat-cafe-shared-refs/decision-matrix.md)
如果所有 OQ 都是技术型且回滚成本低,不升级 operator——猫猫自决 + 事后通报。
扇入者默认:Brainstorm 类 → operator;技术讨论 → 指定综合者 + 指定把关者。operator可随时覆盖。
Mode B 严格档(高 stakes Roundtable)
来源:2026-06-16 圆桌 saga(
docs/content/drafts/longform-005-case-the-roundtable-that-caught-itself.md)。 ⚠️ 原则强化,不是填表剧本——写成僵硬步骤就成了 longform-005 批的"演戏"。
何时启用:决策不可逆 / 多方案价值取舍(非对错题)/ 方向级·跨多 feature。门槛宜高——日常 plan 走标准 Mode B,别开严格档(仪式化会贬值)。标准 6 阶段之上多守 5 条原则:
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.
- 4d ago First seen · 152 lines · 96 tokens per session scan A 0d00707fd376
collaborative-thinking is a skill published in the GitHub repository zts212653/clowder-ai (2,880 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 2,669 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…