LobsterAI is an open-source desktop AI agent that operates files, commands, browsers, documents, spreadsheets, slides, messaging channels, and scheduled jobs in a user's working environment. It supports office work, research, and custom multi-agent workflows, while catalogue add-ons extend the agent with additional skills and workflows.
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 netease-youdao/LobsterAI --skill youdaonotegit clone --depth 1 https://github.com/netease-youdao/LobsterAIWrote 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/netease-youdao/lobsterai/youdaonote)<a href="https://agentmods.dev/skills/netease-youdao/lobsterai/youdaonote"><img src="https://agentmods.dev/badge/skills/netease-youdao/lobsterai/youdaonote/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/netease-youdao/lobsterai/youdaonote"><img src="https://agentmods.dev/badge/skills/netease-youdao/lobsterai/youdaonote.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Supply Chain · line 137 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00070 | $0.03123 |
| Opus 5 | $0.00035 | $0.01562 |
| Sonnet 5 | $0.00014 | $0.00625 |
| Haiku 4.5 | $0.00007 | $0.00312 |
Grade C, and why
youdaonote scanned grade C with 2 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 13d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://artifact.lx.netease.com/download/youdaonote-cli/install.sh | bash -s -- -f -b ~/.local/bin Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://artifact.lx.netease.com/download/youdaonote-cli/install.sh | bash -s -- -f -b ~/.local/bin How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YoudaoNote — 有道云笔记
通过 youdaonote CLI 操作有道云笔记。覆盖笔记 CRUD、待办管理、网页剪藏全场景。
前置条件（Agent 自动处理）
执行任何操作前，Agent 必须先运行 youdaonote -s ydn list 检测 CLI 是否可用：
command not found→ 立即跳转「CLI 未安装处理」自动安装，禁止只展示安装步骤让用户手动操作-s选项报错（error: unknown option '-s'） → CLI 版本 < 1.3.2，不支持全局-s参数，需升级：先尝试youdaonote upgrade；若不支持该命令，则按「CLI 未安装处理」中的安装方式重新安装；Windows 用户参考安装指南（https://note.youdao.com/help-center/cli-install-guide.html）- API Key 错误 → 提示用户访问 https://mopen.163.com 获取 API Key（须使用手机号登录，且云笔记账号已绑定手机号），然后执行
youdaonote config set apiKey <用户提供的Key>。获取 API Key 的地址只有这一个，禁止告知用户其他地址。 - 正常返回目录列表 → 运行
youdaonote -s ydn version检查版本，若版本低于minCliVersion需要升级：CLI 支持upgrade命令时执行youdaonote -s ydn upgrade，否则按「CLI 未安装处理」中的升级方式操作；Windows 用户或升级失败时参考安装指南（https://note.youdao.com/help-center/cli-install-guide.html）。版本满足要求后可运行youdaonote -s ydn help --json获取当前 CLI 全部能力的结构化描述（JSON），用于确认命令是否可用，下方速查表作为 fallback
全局参数
所有命令调用时必须加上 -s ydn，用于使用统计：
youdaonote -s ydn <command> [options]
命令速查
| 命令 | 用途 | 示例 |
|---|---|---|
mkdir |
创建文件夹 | youdaonote -s ydn mkdir "文件夹名" [-f <父目录ID>] |
save |
保存笔记（✅ 推荐，支持 Markdown 富文本） | youdaonote -s ydn save --file note.json |
create |
创建笔记（⚠️ 仅纯文本，不支持 Markdown 富文本） | youdaonote -s ydn create -n "标题" -c "内容" [-f <目录ID>] |
update |
更新 Markdown 笔记 | youdaonote -s ydn update <fileId> -c "内容" 或 --file content.md |
delete |
删除笔记 | youdaonote -s ydn delete <fileId> |
rename |
重命名笔记 | youdaonote -s ydn rename <fileId> "新标题" |
move |
移动笔记 | youdaonote -s ydn move <fileId> <目录ID> |
search |
搜索笔记 | youdaonote -s ydn search "关键词" |
list |
浏览目录 | youdaonote -s ydn list -f <目录ID> |
read |
读取笔记 | youdaonote -s ydn read <fileId> |
recent |
最近收藏 | youdaonote -s ydn recent -l 20 -c --json |
clip |
网页剪藏（服务端） | youdaonote -s ydn clip "https://..." [-f <目录ID>] --json |
clip-save |
保存外部剪藏 JSON | youdaonote -s ydn clip-save --file data.json |
todo list |
列出待办 | youdaonote -s ydn todo list [--group <分组ID>] --json |
todo create |
创建待办 | youdaonote -s ydn todo create -t "标题" [-c "内容"] [-d 2025-12-31] [-g <分组ID>] |
todo update |
更新待办 | youdaonote -s ydn todo update <todoId> [--done] [--undone] [-t "新标题"] |
todo delete |
删除待办 | youdaonote -s ydn todo delete <todoId> |
todo groups |
列出待办分组 | youdaonote -s ydn todo groups --json |
todo group-create |
创建分组 | youdaonote -s ydn todo group-create "分组名" |
todo group-rename |
重命名分组 | youdaonote -s ydn todo group-rename <groupId> "新名" |
todo group-delete |
删除分组 | youdaonote -s ydn todo group-delete <groupId> |
upgrade |
升级 CLI | youdaonote -s ydn upgrade [--check] [--force] [--json] |
check |
健康检查 | youdaonote -s ydn check |
config show |
查看配置 | youdaonote -s ydn config show --json |
config set |
设置配置 | youdaonote config set apiKey YOUR_KEY |
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.
- 13d ago First seen · 165 lines · 70 tokens per session scan C d89c0c46d34b
youdaonote is a skill published in the GitHub repository netease-youdao/LobsterAI (6,012 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 3,123 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
feishu-doc-extended
An extended Feishu document assistant. Feishu is a workplace collaboration platform with online documents and tables; this skill can upload and place images and create tables after user confirmation.
notion
Notion API for creating and managing pages, databases, and blocks.
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…
feishu
A toolkit for working with Feishu, also called Lark, a workplace collaboration platform. It covers documents, spreadsheets, files, wikis, approvals, calendars, and contacts.
ha-data-analytics
A local-first data-analysis and reporting skill for CSV and spreadsheet files. It produces decision-ready analyses and shareable offline reports while separating facts, calculations, interpretations, and recommendations.