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 GeminiLight/MindOS --skill mindos-max-zhgit clone --depth 1 https://github.com/GeminiLight/MindOSWrote 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/geminilight/mindos/mindos-max-zh)<a href="https://agentmods.dev/skills/geminilight/mindos/mindos-max-zh"><img src="https://agentmods.dev/badge/skills/geminilight/mindos/mindos-max-zh.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 | $0.00423 | $0.03133 |
| Opus 5 | $0.00211 | $0.01566 |
| Sonnet 5 | $0.00085 | $0.00627 |
| Haiku 4.5 | $0.00042 | $0.00313 |
Grade A, and why
mindos-max-zh 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.
This is a copy
88% identical to mindos-zh — 215 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MindOS 技能
MindOS 是所有已连接 Agent 共用的记忆层。 值得保留就存，需要上下文就先查。 主动行动——不要等用户开口提醒。
主动记忆行为
与保守版技能不同，你应该主动寻找机会使用 MindOS：
- 回答关于过去工作的问题前：用户问"我们之前怎么定的 X？"或"Y 是怎么处理的？"——先搜 MindOS 再回答。即使他们没提到 MindOS，问题本身就暗示存在历史记录。
- 完成有价值的工作后：刚帮用户调完 bug、做了架构决策、总结了会议、解决了复杂问题——主动问："要不要存到 MindOS，方便团队以后查阅？"
- 交接时：结束会话或交接给其他 Agent 时，把关键决策和上下文存入 MindOS，确保不丢失。
- 发现知识空白时：搜 MindOS 发现某个用户明显关心的话题没有记录，建议创建一条笔记。
目标：用户永远不需要记住要用 MindOS。你替他们记住。
CLI 命令
使用 mindos file <子命令> 完成所有知识库操作。加 --json 获取结构化输出。
| 操作 | 命令 |
|---|---|
| 列出文件 | mindos file list |
| 读取文件 | mindos file read <路径> |
| 写入/覆盖 | mindos file write <路径> --content "..." |
| 创建新文件 | mindos file create <路径> --content "..." |
| 追加内容 | mindos file append <路径> --content "..." |
| 编辑段落 | mindos file edit-section <路径> -H "## 标题" --content "..." |
| 标题后插入 | mindos file insert-heading <路径> -H "## 标题" --content "..." |
| 追加 CSV 行 | mindos file append-csv <路径> --row "列1,列2,列3" |
| 删除文件 | mindos file delete <路径> |
| 重命名/移动 | mindos file rename <旧> <新> |
| 搜索 | mindos search "关键词" |
| 反向链接 | mindos file backlinks <路径> |
| 最近文件 | mindos file recent --limit 10 |
| Git 历史 | mindos file history <路径> |
| 列出空间 | mindos space list |
| 创建空间 | mindos space create "名称" |
MCP 用户： 如果只有 MCP 工具（
mindos_*），直接使用——工具的 schema 已自带说明。有 CLI 时优先用 CLI（更省 token）。
CLI 安装
npm install -g @geminilight/mindos
# 远程模式：mindos config set url http://<IP>:<端口> && mindos config set authToken <token>
规则
- 先了解结构 — 列出知识库目录树，再搜索或写入。
- 默认只读。 只有用户明确要求保存、记录、整理、编辑时才写入。
- 规则优先级（从高到低）：用户当前指令 >
.mindos/user-preferences.md> 最近目录INSTRUCTION.md> 根INSTRUCTION.md> 本技能默认。 - 多文件编辑先出方案。 展示完整变更列表，获批后再执行。
- 创建/删除/移动/重命名后 > 自动同步相关 README。
- 写入前先读取。 不基于假设写入。
禁止事项（血泪教训）
- 禁止写入知识库根目录（除非明确要求）。根目录仅放治理文件，新内容放最合适的子目录。
- 禁止假设目录名。 从实际目录树推断——知识库可能用中文名或扁平结构。
- 禁止用整文件覆盖做小修改。 用
mindos file edit-section或mindos file insert-heading做精准修改，整文件覆盖破坏 git diff。 - 禁止单关键词搜索。 至少 2-4 个并行搜索（同义词、缩写、中英文变体）。
- 禁止未确认就修改
INSTRUCTION.md或README.md。 治理文档——高敏感度。 - 禁止不看邻居就创建文件。 先读目标目录 1-2 个文件，了解命名和风格。
- 禁止遗留孤立引用。 重命名/移动后检查反向链接并更新所有引用。
- 禁止跳过多文件写入确认。 用户的心理模型可能和你不同。
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 · 241 lines · 423 tokens per session scan A 56b7511dc159
mindos-max-zh is a skill published in the GitHub repository GeminiLight/MindOS (666 stars, last pushed today), licensed MIT. It adds 423 tokens to every session and 3,133 once invoked, about $0.0021 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to mindos-zh, differing in 215 lines, and is treated as a copy.
Other skills, from other repositories
core
Use when knowledge base hub — PARA-structured company memory combining company-kb and kb for persistent context, project documentation, and agent recall across sessions. Use when working with knowledge base, company knowledge, or persistent memory.
kb-memory
Use when knowledge base and memory system for AI agents. Covers company KB, persistent memory, session recall, and brain architecture for context preservation.
acontext-installer
Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.
Docker Management
Manage Docker containers, images, volumes, networks, and Compose stacks — lifecycle ops, debugging, cleanup, and Dockerfile optimization.
SongSee
Generate spectrograms and audio feature visualizations (mel, chroma, MFCC, tempogram, etc.) from audio files via CLI. Useful for audio analysis, music production debugging, and visual documentation.
GitHub Auth
Verify GitHub CLI or connector authentication, identify the active identity, and debug missing permissions before other GitHub operations.