Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/bushuhui/skills/brave-search)<a href="https://agentmods.dev/skills/bushuhui/skills/brave-search"><img src="https://agentmods.dev/badge/skills/bushuhui/skills/brave-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/bushuhui/skills/brave-search"><img src="https://agentmods.dev/badge/skills/bushuhui/skills/brave-search.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 | $0.00088 | $0.01126 |
| Opus 5 | $0.00044 | $0.00563 |
| Sonnet 5 | $0.00018 | $0.00225 |
| Haiku 4.5 | $0.00009 | $0.00113 |
Grade A, and why
brave-search scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sv --connect-timeout 5 "https://api.search.brave.com/res/v1/web/search?q=test&count=1" \ How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brave Search Skill
通过 Brave Search API 进行网页搜索和新闻搜索。
环境
- API Key 从环境变量
BRAVE_API_KEY读取(已在 ~/scripts/shell_conf 配置) - 支持代理:自动读取
HTTPS_PROXY/HTTP_PROXY
搜索脚本
# 基础搜索
python3 scripts/brave_search.py "query"
# 限制结果数
python3 scripts/brave_search.py "query" -n 5
# 搜新闻
python3 scripts/brave_search.py "AI agent" --news
# 时间过滤:pd=过去一天, pw=过去一周, pm=过去一月, py=过去一年
python3 scripts/brave_search.py "LLM benchmark" --freshness pw
# 指定国家
python3 scripts/brave_search.py "量化交易" --country CN
# 批量搜索(多关键词)
python3 scripts/brave_search.py "placeholder" --queries "query1" "query2" "query3"
# 翻页
python3 scripts/brave_search.py "query" --offset 10
输出 JSON 数组,每条含 title, href, body, age。
使用流程
- 分析用户需求,拆解为搜索关键词(中英文各一组效果更好)
- 运行
brave_search.py搜索 - 从结果中挑选最相关的 URL
- 用
web_fetch抓取正文获取详细内容 - 整合信息回复用户
与 deep-research 配合
本 skill 可作为 deep-research 的搜索后端替代 DuckDuckGo:
- Brave API 质量更高、更稳定
- 支持时间过滤和国家过滤
- 有
age字段标注结果时效性
网络问题排查
⚠️ Brave API 端口 443 可能不可达:在某些网络环境下 api.search.brave.com:443 连接超时(Connection timed out)。诊断方法:
curl -sv --connect-timeout 5 "https://api.search.brave.com/res/v1/web/search?q=test&count=1" \
-H "X-Subscription-Token: ${BRAVE_API_KEY}" 2>&1 | grep "connect"
如果显示 Connection timed out,说明该端口不可达。回退方案:
- 使用
web-accessskill 的 CDP 浏览器通过 Bing/Google 搜索 - 或直接使用 GitHub Search API(无需外部搜索)
注意事项
- 免费 API 限制:每月 2000 次请求,每秒 1 次
- 单次最多返回 20 条结果
- 批量搜索自动间隔 0.5 秒避免频率限制
⚠️ 代理依赖(关键)
api.search.brave.com 在国内无法直连,必须通过代理访问。即使 API Key 已配置,没有代理会导致 Connection timed out。
可用性诊断
# 检查代理是否生效
source ~/scripts/shell_conf
curl -sI --connect-timeout 5 "https://api.search.brave.com/" \
-H "X-Subscription-Token: ${BRAVE_API_KEY}"
# 返回 HTTP 200/403 = 通,Connection timed out = 需要切代理
兜底方案
Brave 不可用时,按以下优先级降级:
- CDP + Bing/Google 搜索 — 通过
cdp-cli.mjs打开 Bing 页面,用 JS 提取搜索结果中的链接(见 web-access skill) - DuckDuckGo HTML —
curl https://html.duckduckgo.com/html/?q=query解析 HTML 结果 - Jina Reader —
curl "https://r.jina.ai/<URL>"作为单页抓取兜底
What ships with it
1 file 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.
- 11d ago First seen · 112 lines · 88 tokens per session scan A 9f0b02cc07fe
brave-search is a skill published in the GitHub repository bushuhui/skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 88 tokens to every session and 1,126 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…