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 Jackychen-12/AI-Search --skill publicgit clone --depth 1 https://github.com/Jackychen-12/AI-SearchWrote 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/jackychen-12/ai-search/public)<a href="https://agentmods.dev/skills/jackychen-12/ai-search/public"><img src="https://agentmods.dev/badge/skills/jackychen-12/ai-search/public/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/jackychen-12/ai-search/public"><img src="https://agentmods.dev/badge/skills/jackychen-12/ai-search/public.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 | $0.00000 | $0.01579 |
| Opus 5.5 | $0.00000 | $0.00632 |
| Sonnet 5.5 | $0.00000 | $0.00316 |
| Haiku 4.5 | $0.00000 | $0.00158 |
Grade C, and why
public 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 1mo 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://aisearches.cc/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
所有端点返回 JSON，直接 `curl` 或 `fetch` 即可，无需鉴权。 This is a copy
97% identical to AI-Search — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Search Skill
"AI 圈一天发太多东西，等我反应过来已经过气了——干脆让 Agent 帮我每天扫一遍。"
让支持 SKILL.md 的 Agent 用最自然的中文一句话拿到 AI 行业每日资讯。无需 API Key、无需配 MCP server。
它能做什么
| 能力 | 说明 |
|---|---|
| 拉今日/指定日期的日报 | 当天新收录的全部资讯，按模型/产品/行业/论文/技巧分类汇编 |
| 拉 AI 每日必读 | AI 从当天内容中精选的 3-5 条 + 推荐理由 |
| 按分类拉条目 | 只看模型发布、只看论文、只看行业动态 |
| 关键词/公司搜索 | "OpenAI 最近发的"、"Qwen 相关"、"RAG 论文" |
| 查看数据源状态 | 哪些来源今天更新了、哪些没有 |
怎么触发
直接用自然语言问，Agent 会自动匹配：
今天 AI 圈有什么新东西
看一下最新的 AI 日报
5 月 30 号的 AI 日报
最近的 AI 论文有哪些
看下模型发布动态
最近 OpenAI 有什么发布
Qwen 相关的资讯
AI 每日必读
有哪些新的开源模型
数据来源有哪些
API 端点
基础 URL：https://aisearches.cc/api/v1
所有端点返回 JSON，直接 curl 或 fetch 即可，无需鉴权。
资讯
| 端点 | 说明 | 示例 |
|---|---|---|
/items.json |
全量条目（最新 500 条） | curl $BASE/items.json | jq length |
/category/ai-models.json |
模型发布/更新 | 只看大模型相关 |
/category/ai-products.json |
产品发布/更新 | 只看产品发布 |
/category/industry.json |
行业动态 | 融资、政策、市场 |
/category/paper.json |
论文研究 | arXiv、博客深度文章 |
/category/tip.json |
技巧与观点 | 教程、评测、观点 |
日报
| 端点 | 说明 |
|---|---|
/daily/latest.json |
最新一天的日报（含当天全部条目） |
/daily/2026-06-01.json |
指定日期日报 |
/daily/index.json |
所有可用日期列表（用于遍历） |
其他
| 端点 | 说明 |
|---|---|
/digest.json |
AI 每日必读（3-5 条精选 + 推荐理由） |
/stories.json |
事件脉络：同一事件跨源聚合，含进展时间轴、信源印证数、状态（new/developing/settled），适合回答“XX 事件有什么进展” |
/sources.json |
数据来源列表（名称 + 条目数） |
/meta.json |
抓取元数据（时间、各源条目数、失败源） |
/github-trending.json |
GitHub AI 趋势：Trending + 热门论文代码 + 世界模型新项目，含赛道（Agent 框架 / 编程 Agent / MCP · Skills / AI 应用 / 世界模型 · 具身 / 学术研究 / 模型 · 基建 / 教程 · 资源）、今日/本周/本月新增 Star、相关报道，适合回答“最近 GitHub 上什么 Agent 项目最火” |
数据结构
每条资讯的字段：
{
"id": "rss:openai-abc123",
"title": "OpenAI 发布 GPT-5",
"summary": "OpenAI 今日宣布推出 GPT-5，在推理能力上较前代提升显著...",
"source": "OpenAI",
"sourceUrl": "https://openai.com/blog/gpt-5",
"category": "ai-models",
"publishedAt": "2026-06-01T12:00:00Z",
"firstSeen": "2026-06-01T22:17:00Z",
"aiNote": "GPT-5 在推理和多模态能力上大幅提升，定价策略引发行业关注",
"heat": 1500,
"origin": "rss:openai",
"image": "https://..."
}
What ships with it
6 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.
- 1mo ago Changed 4e1c09c00956
- 1mo ago Changed · +1 lines f442dec461c5
- 2mo ago First seen · 143 lines · 0 tokens per session scan C 103e3e80cf35
public is a skill published in the GitHub repository Jackychen-12/AI-Search (116 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,579 tokens. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). It is 97% identical to AI-Search, differing in 3 lines, and is treated as a copy.
public compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| publicJackychen-12/AI-Search | Skill | 116 | today | MIT | C | 0 | Claude Code, Codex |
| newshubRobinZorro86/newshub-skill | Skill | 2 | 3mo ago | MIT | A | 79 | Codex |
| xcloud-docker-deployAsif2BD/xCloud-Docker-Deploy-Skill | Skill | 18 | 4mo ago | none | B | 70 | Claude Code, Codex |
| pr-review-triagecobusgreyling/loop-engineering | Skill | 12k | today | MIT | A | 35 | Claude Code |
| saas-builderixartz/SaaS-Boilerplate | Skill | 7.5k | 7d ago | MIT | A | 75 | Claude Code, Codex |
| trigger-authoring-taskstriggerdotdev/trigger.dev | Skill | 17k | 5d ago | Apache-2.0 | A | 115 | Claude Code, Codex |
| dependency-triagecobusgreyling/loop-engineering | Skill | 12k | today | MIT | A | 25 | Claude Code |