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 plain-languagegit 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/plain-language)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/plain-language"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/plain-language/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/plain-language"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/plain-language.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00154 | $0.02248 |
| Opus 5.5 | $0.00062 | $0.00899 |
| Sonnet 5.5 | $0.00031 | $0.00450 |
| Haiku 4.5 | $0.00015 | $0.00225 |
Grade A, and why
plain-language 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plain Language · 猫猫讲人话
这份技能管什么
家里曾把内部编号和实现过程直接交给没跟进的人，让他先补上下文才能判断； 猫冷读说“看懂了”，也没发现人的真实困惑。另一次，完整体验尚缺一段，却先请人开麦验收。 本 skill 把说明放回人的处境，帮助选择载体；不另建制作工具箱、审批门或每轮冷读工序。 原件和前后对照见 示例与证据，本轮有限观察见 试读记录。初版供试用，不宣称普遍有效。
简短事实回答直接答；已有明确格式就按那份委托制作，不为“讲人话”重新选一次。 共读、产品操作、对外文章分别由 learning-companion、 guide-interaction、tech-writing 主持； 本 skill 只在表达或载体确有缺口时补位。
从人眼前的问题开始
先用已有对话和实际记录判断：他需要知道发生了什么、作一个取舍、理解一个机制，还是亲手看效果。 人没有一直盯着工作是正常情况；把影响这一次理解的共同起点补在眼前，不要求先读历史。 已知的偏好、熟悉程度和输出要求直接用；只有缺失信息会改变交付时才澄清，不另做一轮采访。
按用户看得到的对象称呼这件事，例如“猫的执行记录页面”，而不是“Task1252 item5”。 必要术语首次出现时解释它在这里的意思，随后保持叫法稳定；编号、提交号和路径放到可回查的出处。 不能为了通俗把“已合入”“已加载”“已验证”“你现在可用”说成同一件事。优先说实际结果， 证据细节供回查，剩余缺口、影响和必要权限仍须在正文讲清。
短句、图和类比都为理解服务；保住因果、条件和观点归属，不把“讲人话”等同于越短越好。 例如“后台给页面的数据还不足以显示最早那段话”，比“first-output DTO pending”更适合人判断， 但不能据此编造完成比例或修复时长。
中途汇报与提问
正式需要 You 拍板时，要他判断的内容沿 决策包 准备。
从本次变化说起，按需要补齐以下信息，不机械填满固定栏目：
- 这件事是什么、到哪了：原来想得到什么，现在已经能做什么，还差哪一段；无新进展时照实说。
- 与你有关的影响：实际体验、时间或选择怎样受影响；技术检查结果要连回它能证明的用户结果。
- 确需你决定的事：只问会改变结果的取舍，讲清选项后果、猫的推荐与代价；猫能查或能自决的先做。
- 不回复会怎样、接着做什么：说明真实默认路径。新增权限、不可逆操作和尚未接受的范围不因沉默获准， 等许可的部分暂停，其他已授权工作继续。需人参与测试时，先确认我们已准备好，并说清他的操作和用途。
原始约定与当前实现不符时，先改工作或提问的前提。不能把缺少后台接线包装成“只差你开麦”， 也不能把已经得到的确认换个说法再问一遍。 汇报不是工程日志的重排；取对方这次需要的事实，不逐项复述内部流程。
形式跟着理解任务走
用户明确要求某种形式时尊重它；没有明确要求时，由当前内容和消费方式选择。 下面是用途路由，不是从文字逐级升级的排行榜，也不要求每次做多种版本。
| 人要做什么 | 合适的形式 | 实际制作与交付 |
|---|---|---|
| 知道进度、结果或判断一个取舍 | 自足的文字；长结构化对照可用卡片 | 短汇报直接文字；结构化产物按 rich-messaging |
| 看懂关系、位置或过程顺序 | 图解、Mermaid、SVG；配一句解释 | 能用可编辑图表达就直接画；需新位图才用 image-generation |
| 对比多项内容，或调变量观察影响 | 自包含 HTML、时间线、带滑块的解释 | 小组件用 rich-messaging 的 html_widget；明确变量、假设和变化，标清模拟数据 |
| 判断布局、点法或完整使用体验 | 可操作原型 | concept-demo-design；小型自包含体验稿用 html_widget，复杂 localhost 用 browser-preview |
| 不盯屏幕也要跟上 | 口播稿 | 重写可听正文；共读走 learning-companion；文件用 workspace-navigator 交到阅读入口 |
| 跟随时序、动作或连续变化，或明确要可播视频 | 讲解视频 | video-forge；已有产品宣传意图时按其导演入口；图解和分镜不冒充成片 |
What ships with it
2 files 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 · 107 lines · 154 tokens per session scan A f3437907c589
plain-language is a skill published in the GitHub repository zts212653/clowder-ai (3,471 stars, last pushed today), licensed MIT. It adds 154 tokens to every session and 2,248 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-13.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…