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 HK-hub/AgentSkills --skill aihotgit clone --depth 1 https://github.com/HK-hub/AgentSkillsWrote 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/hk-hub/agentskills/aihot)<a href="https://agentmods.dev/skills/hk-hub/agentskills/aihot"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/aihot/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/hk-hub/agentskills/aihot"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/aihot.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 | $0.00286 | $0.07144 |
| Opus 5.5 | $0.00114 | $0.02858 |
| Sonnet 5.5 | $0.00057 | $0.01429 |
| Haiku 4.5 | $0.00029 | $0.00714 |
Grade C, and why
aihot 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.
> **范围澄清**：这条 UA 要求**只针对 `/api/public/*` API 端点**。`/aihot-skill/{install.sh,SKILL.md,README.md}` 安装入口 nginx 上**特意豁免** UA 黑名单（设计前提就是给 `curl -fsSL ... | bash` 一行装用），用 default curl UA 直通 200。不要把"先决条件"误推广到所有 aihot.virxact.co Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: AI HOT (aihot.virxact.com) 中文 AI 资讯查询 Skill。当用户想知道"今天 AI 圈有什么"、"AI 日报"、"AI HOT"、"AI 资讯"、"AI 热点"、"最近 AI"、"OpenAI/Anthropic/Google 最近发布了什么"、"AI hot today"、"AI news today"、"看一下 AI 行业动态"、"今天有什么大模型发布"、"昨天 AI 圈"、" Copies of this mod
1 near-identical copy found in the catalogue:
- aihot — 98% identical, 437 lines differ
How it starts
The opening of the file, as written. The whole thing — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI HOT Skill
让 Agent 用最自然的中文查询拿到 aihot.virxact.com 上每天的 AI HOT 日报和全部 AI 动态，不需要打开浏览器。SKILL.md 标准格式，跨 Claude Code / Codex CLI / Cursor / Gemini CLI / OpenCode / 任何兼容平台可用。
线上：https://aihot.virxact.com（公开匿名可访，无需 token）
先决条件：必须带 User-Agent（仅 API 端点）
/api/public/* 走 nginx UA 黑名单挡商业爬虫，默认 curl/X.Y UA 会被 403 Forbidden。调 API 时所有 curl 都必须带浏览器 UA：
UA="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36"
# 之后所有调 API 的 curl 都加 -H "User-Agent: $UA"，例如：
curl -sH "User-Agent: $UA" "https://aihot.virxact.com/api/public/daily"
后面"工作流"章节的 curl 例子为了简洁默认你已经设了 $UA——实际调用必须加 -H "User-Agent: $UA"，不要忘。漏掉这一步会让你以为接口挂了，实际只是被 403 挡了。
范围澄清：这条 UA 要求只针对
/api/public/*API 端点。/aihot-skill/{install.sh,SKILL.md,README.md}安装入口 nginx 上特意豁免 UA 黑名单（设计前提就是给curl -fsSL ... | bash一行装用），用 default curl UA 直通 200。不要把"先决条件"误推广到所有 aihot.virxact.com 路径。
什么时候用
路由优先级（第一原则）：默认走精选
items?mode=selected——它是 AI HOT 每天精挑细选的"主菜单"，覆盖用户关心的事且数据新鲜。
- 仅当用户在话里明确说出"日报" 二字才走
daily（编辑成品，按 UTC 整日切片，跟"过去 24 小时 / 今天"等滚动窗口对不上）- 仅当用户明确说"全部 / 完整 / 所有 / 全量" 才走
mode=all（含未精选的次要条目，量大但杂）- "今天 AI 圈"、"过去 24 小时大新闻"、"最近 AI 圈有啥" 等宽问题 = 默认精选 + 时间窗（since），不要默认走日报或全部
这是为了对齐用户的语义优先级：精选是主菜单，日报和全部是用户特意点单的备选，不应抢默认。
| 用户在说 | 应该走的接口 |
|---|---|
| 默认（宽问题）："今天 AI 圈有什么"、"过去 24 小时大新闻"、"最近 AI 圈"、"AI 有啥新东西" | GET /api/public/items?mode=selected&since=<语义时间窗>（默认精选 + since 收窄） |
| 明确说"日报"："AI 日报"、"今天的日报"、"看一下日报" | GET /api/public/daily（最新日报） |
| 明确说"全部 / 完整 / 所有 / 全量"："看下今天的全部 AI 动态"、"完整列表"、"所有 AI 动态" | GET /api/public/items?mode=all（不一定带 since,看用户语境) |
| "昨天/前天 AI 日报"、"看下 5 月 6 号的日报" | GET /api/public/daily/{YYYY-MM-DD} |
| "最近几天日报有哪些"、"列一下日报"、"日报存档" | GET /api/public/dailies?take=N |
| "看下精选条目"、"AI HOT 精选" | GET /api/public/items?mode=selected |
| "最近的模型发布"、"AI 产品发布"、"AI 行业动态"、"AI 论文" | GET /api/public/items?mode=selected&category=...&since=<7d 前>（默认精选 + 类别） |
| "最近一周的 AI 动态"、"5 天前到现在的发布" | GET /api/public/items?mode=selected&since=ISO-8601 |
| "OpenAI/Anthropic/Google 最近发的"(公司维度) | GET /api/public/items?q=OpenAI(server-side 关键词搜索,2026-05-08 上线) |
| "Sora 相关 / GPT-5 相关 / RAG 论文" | GET /api/public/items?q=<关键词>(在 title + 中文 title + 中文 summary 三列匹配) |
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.
- 1mo ago First seen · 423 lines · 286 tokens per session scan C a7752c6a21ce
aihot is a skill published in the GitHub repository HK-hub/AgentSkills (6 stars, last pushed 2mo ago), licensed MIT. It adds 286 tokens to every session and 7,144 once invoked, about $0.0011 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, 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
spec-brainstorm
Conversational design workshop for substantial work. Interviews the human one question at a time, explores 2-3 approaches with trade-offs, and presents the design section by section for approval before writing only design.md, then stops. Combines requirements discovery with codebase research and architecture design.…
spec-plan
Write approved implementation plans in one of two modes. Explicit Inline mode creates a conversational plan for bounded work. Spec-backed Plan converts an approved design.md into plan.json. Both modes stop after producing their plan output. Trigger after atelier-orchestrator selects a mode, when the user asks to plan…
atelier-orchestrator
Skill routing and workflow orchestration. Selects Inline Plan or Spec-backed Plan, routes to the correct workflow skill, and manages transitions between phases. Use when starting any conversation or task to determine which planning mode and skill apply.
spec-implement
Continue an approved Spec-backed workflow when the user says "implement", "go", "start", or "do it". After Codex Plan Mode, persist the next missing design.md or plan.json artifact and stop. When both artifacts exist, execute plan.json with TDD and report between batches.
oracle-codebase-design
Shared vocabulary and principles for designing deep modules. Use when designing or changing a module's interface, deciding where a seam goes, handling untrusted input at the edges, choosing the level to test at, naming modules, or making code more testable. Also use when another skill needs the deep-module vocabulary.
code-commit
Generate and validate conventional commit messages following the conventionalcommits.org spec. Use whenever the user wants to commit code, mentions commit messages, git commit, or asks to create a commit. Triggers on "commit", "git commit", "conventional", or when reviewing commit message format.