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 L-LesterYu/OpenClaw-hot-skills-zh --skill web-search-plus-zhgit clone --depth 1 https://github.com/L-LesterYu/OpenClaw-hot-skills-zhWrote 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/l-lesteryu/openclaw-hot-skills-zh/web-search-plus-zh)<a href="https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/web-search-plus-zh"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/web-search-plus-zh/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/l-lesteryu/openclaw-hot-skills-zh/web-search-plus-zh"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/web-search-plus-zh.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 | $0.00087 | $0.03084 |
| Opus 5 | $0.00044 | $0.01542 |
| Sonnet 5 | $0.00017 | $0.00617 |
| Haiku 4.5 | $0.00009 | $0.00308 |
Grade C, and why
web-search-plus-zh scanned grade C with 1 finding 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 9d 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.
Cloud metadata endpointhighServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
- 阻止云元数据端点（169.254.169.254、metadata.google.internal） How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Search Plus
不用纠结用哪个搜索引擎了，让技能替你选择。
本技能连接 7 个搜索提供商（Serper、Tavily、Querit、Exa、Perplexity、You.com、SearXNG），并为每次查询自动选择最佳引擎。购物问题？→ Google 结果。研究问题？→ 深度研究引擎。需要直接答案？→ AI 合成并附带引用。重视隐私？→ 自托管方案。
✨ 有什么不同？
- 直接搜 — 无需思考该用哪个提供商
- 智能路由 — 分析你的查询并自动选择最佳提供商
- 7 个提供商，1 个接口 — Google 结果、研究引擎、神经搜索、AI 问答带引用、RAG 优化和隐私优先，全部整合
- 只需 1 个密钥 — 从任意一个开始，以后再添加更多
- 免费选项 — SearXNG 完全免费（自托管）
🚀 快速开始
# 交互式设置（首次使用推荐）
python3 scripts/setup.py
# 或手动：复制配置文件并添加密钥
cp config.example.json config.json
向导会逐一介绍每个提供商、收集 API 密钥并配置默认设置。
🔑 API 密钥
只需 一个 密钥即可开始使用。以后可以添加更多提供商以获得更全面的覆盖。
| 提供商 | 免费额度 | 擅长 | 注册 |
|---|---|---|---|
| Serper | 2,500 次/月 | 购物、价格、本地、新闻 | serper.dev |
| Tavily | 1,000 次/月 | 研究、解释、学术 | tavily.com |
| Querit | 联系销售/免费额度不同 | 多语言 AI 搜索、国际资讯 | querit.ai |
| Exa | 1,000 次/月 | "类似 X"、创业公司、论文 | exa.ai |
| Perplexity | 通过 Kilo | 带引用的直接回答 | kilo.ai |
| You.com | 有限额度 | 实时资讯、AI/RAG 上下文 | api.you.com |
| SearXNG | 免费 ✅ | 隐私、多源、$0 费用 | 自托管 |
设置密钥：
# 方式 A：.env 文件（推荐）
export SERPER_API_KEY="你的密钥"
export TAVILY_API_KEY="你的密钥"
export QUERIT_API_KEY="你的密钥"
# 方式 B：config.json
{ "serper": { "api_key": "你的密钥" } }
🎯 什么时候用哪个提供商
| 我想... | 提供商 | 示例查询 |
|---|---|---|
| 查产品价格 | Serper | "iPhone 16 Pro Max 价格" |
| 查附近的餐厅/商店 | Serper | "我附近最好的披萨" |
| 了解某事的原理 | Tavily | "HTTPS 加密是怎么工作的" |
| 做深度研究 | Tavily | "2024 年气候变化研究" |
| 跨语言搜索/国际资讯 | Querit | "德国最新 AI 政策动态" |
| 查找类似 X 的公司 | Exa | "类似 Notion 的创业公司" |
| 查找研究论文 | Exa | "transformer 架构论文" |
| 获取带来源的直接答案 | Perplexity | "柏林这周末有什么活动" |
| 了解某事的最新状态 | Perplexity | "以太坊升级进展如何" |
| 获取实时信息 | You.com | "最新 AI 监管新闻" |
| 不被追踪地搜索 | SearXNG | 任何内容，私密搜索 |
专业提示： 正常搜索就好！自动路由能正确处理大多数查询。需要时用 -p provider 手动覆盖。
🧠 自动路由的工作原理
What ships with it
10 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.
- 9d ago First seen · 259 lines · 87 tokens per session scan C 5d3cc9f25b63
web-search-plus-zh is a skill published in the GitHub repository L-LesterYu/OpenClaw-hot-skills-zh (54 stars, last pushed 5mo ago), licensed MIT. It adds 87 tokens to every session and 3,084 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
web-search-plus
Unified search skill with Intelligent Auto-Routing. Uses multi-signal analysis to automatically select between Serper (Google), Tavily (Research), Querit (Multilingual AI Search), Exa (Neural), Perplexity (AI Answers), You.com (RAG/Real-time), and SearXNG (Privacy/Self-hosted) with confidence scoring.
web-search-plus
Unified search skill with Intelligent Auto-Routing. Uses multi-signal analysis to automatically select between Serper (Google), Tavily (Research), Exa (Neural), Perplexity (AI Answers), You.com (RAG/Real-time), and SearXNG (Privacy/Self-hosted) with confidence scoring.
tavily-search
Search the web using Tavily AI search API.
web-search
Search the web using DuckDuckGo, Tavily, Brave, Perplexity, or SearXNG for real-time information retrieval.
web-search-plus
Unified multi-provider web search and URL extraction skill with intelligent auto-routing across Serper, Brave, Tavily, Querit, Linkup, Exa, Firecrawl, You.com, SearXNG, SerpBase, and Keenable. Unified freshness/news filters, locale-aware defaults, spam/mirror filtering, and adaptive routing. Sends queries/URLs to the…
lc_tavily_search
A tool for real-time web searches using Tavily, a web-search service.