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 films-searchgit 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/films-search)<a href="https://agentmods.dev/skills/netease-youdao/lobsterai/films-search"><img src="https://agentmods.dev/badge/skills/netease-youdao/lobsterai/films-search/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/films-search"><img src="https://agentmods.dev/badge/skills/netease-youdao/lobsterai/films-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.01446 |
| Opus 5 | $0.00026 | $0.00723 |
| Sonnet 5 | $0.00010 | $0.00289 |
| Haiku 4.5 | $0.00005 | $0.00145 |
Grade A, and why
films-search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- films-search — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Films Search Skill
搜索影视资源（电影、电视剧、动漫），通过实时爬虫深度抓取资源页面，从各网盘平台获取公开分享的资源链接。
前置条件
- web-search skill（必需，用于搜索发现资源页面）
命令
搜索资源
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" search "关键词" [选项]
选项：
| 参数 | 说明 | 默认值 |
|---|---|---|
--pan <type> |
筛选网盘类型: quark, baidu, aliyun, uc, all |
all |
--quality <q> |
筛选画质: 4k, 1080p, 720p, all |
all |
--limit <n> |
每个平台最大结果数 | 5 |
--engine <e> |
搜索引擎: deep, web |
deep |
引擎说明：
deep（默认，推荐）— web-search 搜索发现资源页面 + JavaScript 深度抓取提取网盘链接和提取码，结果最准确web— 仅从 web-search 搜索引擎摘要中提取链接（速度快，但准确率较低，不做深度抓取）
示例：
# 搜索所有平台的资源（默认使用深度搜索）
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" search "流浪地球2"
# 只搜夸克网盘 4K 资源
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" search "流浪地球2" --pan quark --quality 4k
# 限制结果数量
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" search "流浪地球2" --limit 10
# 使用浅层搜索（不深度抓取页面）
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" search "流浪地球2" --engine web
Windows 系统使用 PowerShell 脚本：
powershell -File "$SKILLS_ROOT/films-search/scripts/film-search.ps1" search "流浪地球2" --pan quark
热门推荐
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" hot "2025年热门电影"
本质上是以推荐类关键词调用搜索，返回相关网盘资源。
解析跳转链接
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" resolve "https://example.com/goto/xxx"
当搜索结果中的链接需要二次跳转时，用此命令解析出真实网盘地址。
Agent 使用流程
- 用户说「帮我找 XXX 电影」→ 执行
search "XXX" - 解析返回的 JSON，提取网盘链接
- 按网盘类型和画质分组呈现给用户
- 如果结果中有提取码 (
extractCode)，一并展示给用户 - 如果结果中有
pageUrl但没有直接url，用resolve命令获取真实地址
示例对话：
用户：帮我找一下流浪地球2的夸克网盘资源，要4K的
Agent：
- 执行
search "流浪地球2" --pan quark --quality 4k- 从 JSON 结果中取出匹配项
- 返回：标题 + 画质 + 夸克网盘链接 + 提取码（如有）
输出格式
所有命令输出 JSON，结构如下：
{
"success": true,
"data": {
"query": "流浪地球2",
"total": 5,
"results": [
{
"title": "资源标题",
"pan": "quark",
"url": "https://pan.quark.cn/s/xxx",
"quality": "4K",
"extractCode": "ab12",
"source": "deep-search",
"pageUrl": "https://example.com/resource/123"
}
]
}
}
What ships with it
4 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.
- 12d ago First seen · 153 lines · 51 tokens per session scan A 7e0f9c2eff69
films-search is a skill published in the GitHub repository netease-youdao/LobsterAI (6,012 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 1,446 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
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.writing-hive-skills
Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to create, scaffold, add, or package a new skill for a Hive agent.