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 web-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/web-search)<a href="https://agentmods.dev/skills/netease-youdao/lobsterai/web-search"><img src="https://agentmods.dev/badge/skills/netease-youdao/lobsterai/web-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/web-search"><img src="https://agentmods.dev/badge/skills/netease-youdao/lobsterai/web-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, 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 Tool Misuse · line 280 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Data Exfiltration · line 142 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 147 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Privilege Escalation · line 267 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00041 | $0.03813 |
| Opus 5 | $0.00020 | $0.01906 |
| Sonnet 5 | $0.00008 | $0.00763 |
| Haiku 4.5 | $0.00004 | $0.00381 |
Grade B, and why
web-search scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Linux: `sudo apt install chromium-browser` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
CONNECTION_ID=$(curl -s -X POST http://127.0.0.1:8923/api/browser/connect \ Copies of this mod
1 near-identical copy found in the catalogue:
- web-search — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 562 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Search Skill
When to Use This Skill
Use the web-search skill when you need:
- Current information - Events, news, or data after January 2025
- Latest documentation - Up-to-date framework/library docs (React 19, Next.js 15, etc.)
- Real-time data - Stock prices, weather, sports scores, etc.
- Fact verification - Check current status of projects, companies, or technologies
- Recent discussions - Community opinions, GitHub issues, Stack Overflow answers
- Product comparisons - Latest reviews and comparisons
- Troubleshooting - Search for specific error messages or solutions
Examples of when to use:
- User: "What are the new features in React 19?"
- User: "Search for the latest Next.js App Router documentation"
- User: "What's the current status of the Rust async project?"
- User: "Find recent discussions about Vue 3 performance"
How It Works
┌──────────┐ Bash ┌─────────┐ HTTP ┌──────────────┐ CDP ┌────────┐
│ Claude │───────────▶│ CLI.sh │───────────▶│ Bridge Server│──────────▶│ Chrome │
│ │ │ │ │ (localhost) │ Playwright│ │
└──────────┘ └─────────┘ └──────────────┘ └────────┘
│
▼
Google/Bing Search
Extract Results
Architecture:
- CLI Script - Simple bash interface for Claude
- Bridge Server - Express HTTP API (auto-started by Electron)
- Playwright Manager - Browser connection and session management
- Search Engine Layer - Google primary, Bing fallback
- Chrome Browser - Visible browser window (all operations transparent)
Basic Usage
Simple Search (Recommended)
IMPORTANT: Always use the $SKILLS_ROOT environment variable to locate the skill scripts. This ensures the skill works in both development and production environments.
What ships with it
21 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.
- DEPLOYMENT.md 4.7 KB
- examples/basic-search.md 7.7 KB
- IMPLEMENTATION.md 12 KB
- LICENSE.txt 1.1 KB
- package.json 734 B
- README.md 8.5 KB
- scripts/search.sh 15 KB runs code
- scripts/start-server.sh 7.5 KB runs code
- scripts/stop-server.sh 1.0 KB runs code
- scripts/test-basic.js 2.5 KB runs code
- scripts/test-search.js 4.1 KB runs code
- server/config.ts 2.0 KB runs code
- server/index.ts 23 KB runs code
- server/playwright/browser.ts 17 KB runs code
- server/playwright/manager.ts 7.4 KB runs code
- server/playwright/operations.ts 4.3 KB runs code
- server/search/bing.ts 4.7 KB runs code
- server/search/google.ts 7.5 KB runs code
- server/search/types.ts 655 B runs code
- TEST.md 8.2 KB
- tsconfig.json 520 B
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.
- 11d ago First seen · 562 lines · 41 tokens per session scan B 915daf3b656c
web-search is a skill published in the GitHub repository netease-youdao/LobsterAI (6,007 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 3,813 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, 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
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.