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 metago-ai/metagolifeform --skill metago-fabric-guidegit clone --depth 1 https://github.com/metago-ai/metagolifeformWrote 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/metago-ai/metagolifeform/metago-fabric-guide)<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-fabric-guide"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-fabric-guide/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/metago-ai/metagolifeform/metago-fabric-guide"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-fabric-guide.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 | $0.00084 | $0.00886 |
| Opus 5.5 | $0.00034 | $0.00354 |
| Sonnet 5.5 | $0.00017 | $0.00177 |
| Haiku 4.5 | $0.00008 | $0.00089 |
Grade A, and why
metago-fabric-guide 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 2d 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.
What it actually says
MetaGO Fabric 产品功能指南
适用边界（先读这一条）
本技能描述的是 MetaGO Fabric（v1.0.1）产品的桌面端功能。 当前运行实例若是 DeepSeek Harness，则下列快捷键与界面元素未必适用—— 回答前必须先确认用户所在平台，不确定时如实说明"以下为 Fabric 产品的操作方式， 当前平台可能不同"，不得直接把 Fabric 的快捷键当作当前平台的答案。
核心功能速查
快捷键
| 快捷键 | 功能 |
|---|---|
| Ctrl+K | 命令面板（搜索所有命令、技能、功能） |
| Ctrl+Shift+V | 全局语音按住说话（按下录音，松开转写，支持中文） |
MetaGO 工具箱（⚡ 按钮，右下角）
右下角 ⚡ 按钮点击展开分类菜单：
工具组
- 场景模板 — 预设 5 个常用场景（审查代码/写报告/架构评审/测试生成/深度调研），点击自动填入提示词
- 后台任务 — 显示所有 subagent/织工的运行状态（🟡运行中/🟢已完成/🔴失败）
- Hooks 事件总线 — 配置钩子（PostToolUse 自动跑 UDGK 门禁等），查看 hook 执行记录
- Checkpoint 时间线 — 会话时间线，支持从任意节点回滚
市场组
- 技能市场 — 浏览核心 metago-* 技能，点击直接在输入框填入 /技能名 启用
- 角色市场 — 浏览可用的智能体角色预设（元构生命体/傻瓜工坊/标准等）
- 会话检索 — 全局搜索历史会话（支持中文全文检索）
治理组
- 治理面板 — 权限模式查看 + MCP 连接状态 + 审批历史
语音输入（metago-voice）
- 输入框左侧有麦克风按钮，按住说话（按下开始录音，松开自动转写）
- Ctrl+Shift+V 全局快捷键
- 以
/开头的语音内容自动发送（语音指令直达） - 基于硅基流动 SenseVoiceSmall 模型
桌面端专属
- 系统托盘：关闭窗口后隐藏到托盘继续运行（不退出）
- 系统通知：织工完成/上下文压缩/审批请求时弹出 Windows 通知
- 局域网共享：设置中开启后，手机可通过局域网 IP 访问
回答纪律
- 先确认平台：用户问"按什么快捷键"时，先判断他当前在 Fabric 还是别的平台
- 区分事实与推测：本技能里写的快捷键是 Fabric 的事实；对其他平台只能是推测
- 不确定就说不确定：宁可说"当前平台请以实际界面为准"，也不给错答案
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.
- 2d ago First seen · 65 lines · 84 tokens per session scan A f6ae73cd8a78
metago-fabric-guide is a skill published in the GitHub repository metago-ai/metagolifeform (5 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 886 once invoked, about $0.0003 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 2026-10-25.
Other skills, from other repositories
peon-ping-toggle
Toggle peon-ping sound notifications on/off. Use when user wants to mute, unmute, pause, or resume peon sounds during a Claude Code session. Also handles config changes like volume, pack rotation, categories — any peon-ping setting.
backup-restore
Verify a vault backup, prove it restores, or restore it to a folder of the user's choosing. Use when the user says 'restore my backup', 'test my backups', 'are my backups any good', or after data loss. Never overwrites the live vault. Not for taking a backup (backup-now); not for scheduling (backup-setup).
setup
Run first-time Dex onboarding: build the vault structure, capture the user profile and configure MCPs. Use when System/.onboarding-complete is absent or the user says 'set up Dex', 'start onboarding'. Not for the post-onboarding tour; use getting-started. Not for a mid-life role change; use reset.
next-action
Use when the user wants a next-action recommendation based on current state — reads handoff/git/lessons/STATE and proposes top-3 by impact. Trigger: '/next', 'what should I do next', 'next action'. Proposes only, never executes.
wecom
An administration tool for WeCom, Tencent's workplace messaging platform, including its company department tree and app messages.
lov-canonical-store
A central file and command-line workflow for maintaining one deduplicated vocabulary list as the source for other apps.