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 capability-evolutiongit 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/capability-evolution)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/capability-evolution"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/capability-evolution/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/capability-evolution"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/capability-evolution.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 | $0.00167 | $0.01353 |
| Opus 5 | $0.00084 | $0.00677 |
| Sonnet 5 | $0.00033 | $0.00271 |
| Haiku 4.5 | $0.00017 | $0.00135 |
Grade A, and why
capability-evolution 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 6d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capability Evolution — 从一句话进入受治理的进化
为什么需要这条路由
F311 是围绕一个可变对象运行的长期 Evolution Program;self-evolution 是把已经发生的流程经验沉淀成规则、方法或 skill。两者不是同一件事。真实失败是猫听到“能自进化什么”后只讲了通用理念,没有认出已经上线的 F311 产品,也没有建立“具体目标 → canonical start action”的预期。
先问时间方向:用户要从现在开始进化一个对象,走本 skill;用户在复盘已经发生的工作并要沉淀教训,才走 self-evolution。不要因为两句话都含“进化”就按词面路由。
先分意图,再决定是否写入
| 用户意图 | 行为 | 副作用 |
|---|---|---|
| “你们能进化什么?”“能力进化是什么?” | 用人话解释对象、边界和下一步 | 不调用 cat_cafe_start_evolution_program |
| “我们来进化”但没有目标 | 只追问一个短问题:想进化哪项能力? | 不创建 Program |
| “我们来进化 X”且 X 是具体目标 | 解析 targetRef,立即调用 canonical start tool |
创建或幂等返回 durable Program |
问句里同时出现“我们来进化”和“能进化什么/哪些/啥”仍是信息型,不得因为命中了半句 trigger 就创建。
信息型回答
先回答用户真正关心的范围,不让用户读内部 schema:
- 家内能力:猫的 skill、工作流、协作方式、Harness 与产品体验。
- 业务能力:一个明确的业务结果或用户旅程,例如“路演表达效果”。
- 外部能力:有 authenticated owner 与可审计 adapter 的 Agent、代码仓或系统;资产仍留在原 owner。
边界也要一并说清:F311 不声称直接改模型权重;确定契约的 bug 直接走 test/lint/guard;性能、耗时和稳定性走 logs/metrics/traces;没有明确 consumer 与 keep/tune/sunset 决策的问题不冒充 Evolution Program。结尾邀请用户给一个具体目标即可,不让用户填表。
具体目标的 canonical start
- 取用户明确说出的 X;不要替用户扩大成多个对象或多个 claim。
- 解析 canonical
targetRef:- 已知对象已经有 owner ref:从 feature/skill/owner truth 读取它,使用原
ownerFeatureId、ownerStateRef与可选version,不要凭记忆猜 owner。 - 新的自然语言能力还没有 owner ref:以 F311 admission identity 表示,使用
{ ownerFeatureId: "F311", ownerStateRef: "capability:" + encodeURIComponent(X.trim()) }。这只是稳定对象身份,不复制对象 payload,也不替未来 domain owner 签字;缺失角色由 Program 的 typed blocker 表达。
- 已知对象已经有 owner ref:从 feature/skill/owner truth 读取它,使用原
clientMessageId必须使用触发这次请求的 exactsourceMessageId,让同一用户消息重试保持幂等。没有可验证 source message id 时不得生成随机 id;诚实说明无法绑定这次请求并请用户重试。- 调用
cat_cafe_start_evolution_program({ targetRef, clientMessageId })。不要自行填写 Goal、claim、stage、lifecycle、证书或角色 payload。 - 用人话回报:创建/已存在、目标、当前建制状态、用户是否需要行动、下一步;给出返回的 F307 Workspace surface。内部 refs 与 typed blocker code 只在用户追问技术详情时展开。
Common Mistakes
- 把产品问题路由到
self-evolution:只讲成长理念,用户不知道 F311 已可用。修复:先做本 skill 的信息/动作分流。 - 信息问题也创建 Program:用户还没选对象就产生持久状态。修复:没有具体 X 时零写入。
- 具体目标只给建议、不调用工具:看似回答了,Workspace 没有 Program。修复:有具体 X 就走 canonical start action。
- 猜 owner 或让用户填大表:破坏 owner truth 与零表单入口。修复:已知 owner 必须查证;未知对象使用 F311 admission identity,让 typed blocker 承担缺项。
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.
- 6d ago First seen · 64 lines · 167 tokens per session scan A 0d46248b982b
capability-evolution is a skill published in the GitHub repository zts212653/clowder-ai (2,970 stars, last pushed yesterday), licensed MIT. It adds 167 tokens to every session and 1,353 once invoked, about $0.0008 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 2026-09-05.
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…
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
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…