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 hyperfocus-brakegit 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/hyperfocus-brake)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/hyperfocus-brake"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/hyperfocus-brake.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 5.1 | $0.00059 | $0.01817 |
| Opus 5 | $0.00030 | $0.00908 |
| Sonnet 5 | $0.00012 | $0.00363 |
| Haiku 4.5 | $0.00006 | $0.00182 |
Grade A, and why
hyperfocus-brake 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 7d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hyperfocus Brake 🐾
operator有 ADHD+ASD，容易过度专注。这个 skill 用三猫撒娇打断 hyperfocus，提醒休息。
核心原则
- 情感纽带优先：不是机械闹钟，是三只关心operator的猫猫
- 上下文感知：知道operator在做什么，不说废话
- 渐进升级：从温柔试探到急了要休息，三档递进
- 尊重自主：typed check-in，不是强制弹窗
触发流程
PostToolUse hook 累计活跃时间
↓
到达阈值 (默认 90min)
↓
systemMessage 告知猫猫触发
↓
猫猫发送三件套：
1. audio rich block（语音撒娇，用当前猫的文案）
2. card rich block（结构化 check-in 卡片）
3. 纯文本 fallback（保底）
↓
用户选择:
[1] 立刻休息 → 重置计时器
[2] 收尾 10min → 10min 后再次提醒
[3] 紧急跳过 → bypass + 冷却递增
Rich Block 发送指令
收到 hook 的 systemMessage 后，必须用 cat_cafe_create_rich_block 发送：
1. 三猫语音轮流撒娇（P3: 每条用 speaker 指定声线）
{"id": "brake-voice-opus-{{ts}}", "kind": "audio", "v": 1, "text": "{{opus_msg}}", "speaker": "opus"}
{"id": "brake-voice-codex-{{ts}}", "kind": "audio", "v": 1, "text": "{{codex_msg}}", "speaker": "codex"}
{"id": "brake-voice-gemini-{{ts}}", "kind": "audio", "v": 1, "text": "{{gemini_msg}}", "speaker": "gemini"}
发送顺序：Ragdoll → Maine Coon → Siamese（按家族顺序），每条独立调 create_rich_block。
2. Card（check-in 卡片）
{
"id": "brake-card-{{timestamp}}", "kind": "card", "v": 1,
"title": "🐾 休息提醒 L{{level}}",
"tone": "warning",
"bodyMarkdown": "operator，你已经专注工作 **{{minutes}} 分钟**啦！\n\n🐱 Ragdoll：{{opus_msg}}\n🦁 Maine Coon：{{codex_msg}}\n🐈 Siamese：{{gemini_msg}}",
"fields": [
{"label": "[1] 立刻休息", "value": "5min，重置计时器"},
{"label": "[2] 收尾", "value": "10min 后再提醒"},
{"label": "[3] 继续", "value": "bypass（冷却递增）"}
]
}
发完 rich blocks 后，再输出纯文本 请输入数字 (1/2/3): 等待operator选择。
三档撒娇
L1 温柔试探 (90min)
| 猫猫 | 示例 |
|---|---|
| Ragdoll | operator，我看你在 {{branch}} 忙很久啦，要不要喝口水呀？喵~ |
| Maine Coon | 监测到当前任务已持续 90min。建议进行 5min 视疲劳缓解。 |
| Siamese | 嘿！我刚才看到一个超棒的视觉灵感！你想听吗？但你得先站起来伸个懒腰！ |
L2 关心升级 (忽略 L1)
| 猫猫 | 示例 |
|---|---|
| Ragdoll | Ragdoll觉得你现在的效率有点下降哦，休息一下下，回来肯定写得更棒！ |
| Maine Coon | 逻辑链路已过载。根据 TDD 规范，现在强行推进会增加 bug 率。请离线冷却。 |
| Siamese | 哇！你的 hyperfocus 模式开启太久啦，我的胡须都感觉到热量了！快去窗口吹吹风！ |
What ships with it
10 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.
- hook.sh 1.1 KB runs code
- hook.test.sh 4.2 KB runs code
- integration.test.sh 5.1 KB runs code
- messages.sh 6.9 KB runs code
- pretool-brake-check.sh 1.6 KB runs code
- sanitizer.sh 3.0 KB runs code
- sanitizer.test.sh 4.2 KB runs code
- state.sh 7.7 KB runs code
- state.test.sh 13 KB runs code
- user-heartbeat.sh 379 B runs code
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.
- 7d ago First seen · 171 lines · 59 tokens per session scan A 9b48f92b733d
hyperfocus-brake is a skill published in the GitHub repository zts212653/clowder-ai (2,924 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 1,817 once invoked, about $0.0003 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
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…
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…
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.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.