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 agentmods add skills/countbot-ai/countbot/newsnpx skills add countbot-ai/CountBot --skill newsgit clone --depth 1 https://github.com/countbot-ai/CountBotWrote 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/countbot-ai/countbot/news)<a href="https://agentmods.dev/skills/countbot-ai/countbot/news"><img src="https://agentmods.dev/badge/skills/countbot-ai/countbot/news.svg" alt="Measured on agentmods" 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 | $0.00061 | $0.01355 |
| Opus 5 | $0.00030 | $0.00678 |
| Sonnet 5 | $0.00012 | $0.00271 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
news scanned grade A with 0 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 5d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
新闻与资讯查询
通过 RSS 源和网页抓取获取中文新闻和全球 AI 资讯，支持多分类、关键词过滤。
无需配置
此技能开箱即用，无需 API Key。
命令行调用
# 获取热点新闻（默认）
python skills/news/scripts/news.py hot
# AI新闻资讯查询
python skills/news/scripts/news.py category --cat ai --limit 20
# 按分类查询
python skills/news/scripts/news.py category --cat tech
python skills/news/scripts/news.py category --cat finance
python skills/news/scripts/news.py category --cat ai
python skills/news/scripts/news.py category --cat ai-community
# 关键词搜索
python skills/news/scripts/news.py hot --keyword AI
python skills/news/scripts/news.py category --cat ai --keyword GPT
# 控制摘要长度（默认 100 字符）
python skills/news/scripts/news.py category --cat ai --detail 500 # 显示 500 字符摘要
python skills/news/scripts/news.py category --cat ai --detail -1 # 显示全文
python skills/news/scripts/news.py category --cat ai --detail 0 # 不显示摘要
# 指定返回条数
python skills/news/scripts/news.py hot --limit 20
# JSON 格式输出（包含完整正文，不截断）
python skills/news/scripts/news.py hot --json
# 查看所有支持的分类和来源
python skills/news/scripts/news.py sources
支持的新闻分类
中文新闻
| 分类 | 参数值 | 来源 |
|---|---|---|
| 热点要闻 | hot |
人民网、新华网、澎湃新闻 |
| 时政 | politics |
人民网时政、新华网政务 |
| 财经 | finance |
新浪财经、东方财富 |
| 科技 | tech |
36氪、IT之家 |
| 社会 | society |
中国新闻网、澎湃新闻 |
| 国际 | world |
环球网、参考消息 |
| 体育 | sports |
新浪体育、虎扑 |
| 娱乐 | entertainment |
新浪娱乐 |
AI 技术与资讯
| 分类 | 参数值 | 来源 |
|---|---|---|
| AI 技术 | ai |
MIT Tech Review、OpenAI Blog、Google AI Blog、DeepMind Blog、Latent Space、Interconnects、One Useful Thing、KDnuggets |
| AI 社区 | ai-community |
AI News Daily、Sebastian Raschka、Hacker News、Product Hunt |
AI 源说明：
- MIT Technology Review — MIT 科技评论，AI 与前沿技术深度报道
- OpenAI Blog — OpenAI 官方博客，模型发布与研究动态
- Google AI Blog — Google AI 研究与产品更新
- DeepMind Blog — DeepMind 研究进展
- Latent Space — AI 工程师社区播客与文章
- Interconnects — Nathan Lambert 的 AI 技术深度分析
- One Useful Thing — Ethan Mollick 的 AI 实践应用分享
- KDnuggets — AI/ML 技术文章聚合
- AI News Daily — AI 行业每日新闻汇总
- Sebastian Raschka — 机器学习深度技术博客
- Hacker News — 科技新闻与讨论社区
- Product Hunt — 新产品发现平台（含 AI 产品）
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.
- 5d ago First seen · 139 lines · 61 tokens per session scan A af169bf80958
news is a skill published in the GitHub repository countbot-ai/CountBot (774 stars, last pushed 8d ago), licensed MIT. It adds 61 tokens to every session and 1,355 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
google-drive-sheets
Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
slack-drafts
Create Slack message drafts in the user's own composer, as the user, through their per-user Slack OAuth. Drafting only — the user reviews and sends from Slack.
connect-apps
Connect an administrator-enabled SaaS app for a user with a one-time OAuth consent link.
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
release-openclaw-maintainer
Prepare or verify OpenClaw stable, beta, and extended-stable releases, including backport discovery, changelogs, release notes, publish commands, and artifacts.