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 ChanningLua/prax-agent --skill ai-news-dailygit clone --depth 1 https://github.com/ChanningLua/prax-agentWrote 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/channinglua/prax-agent/ai-news-daily)<a href="https://agentmods.dev/skills/channinglua/prax-agent/ai-news-daily"><img src="https://agentmods.dev/badge/skills/channinglua/prax-agent/ai-news-daily/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/channinglua/prax-agent/ai-news-daily"><img src="https://agentmods.dev/badge/skills/channinglua/prax-agent/ai-news-daily.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.02262 |
| Opus 5 | $0.00017 | $0.01131 |
| Sonnet 5 | $0.00007 | $0.00452 |
| Haiku 4.5 | $0.00003 | $0.00226 |
Grade A, and why
ai-news-daily scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
每日 AI 简报 Pipeline
一条命令从抓取到送达。把 browser-scrape、knowledge-compile、Notify 三个技能串成闭环。适合挂 prax cron。
触发条件
用户说:
- "跑今天的 AI 日报 / ai-news-daily"
- "生成 X 推文摘要推到飞书"
或 prax cron 调度到期。
重要 — 不要递归 shell out:你已经被这个 skill 触发了。直接按下面的 Step 1-6 自己执行,不要再 python -m praxdaily run-now / prax prompt "..." / prax cron run 之类把同样的事情又派出去 —— 那会无限递归 + 把 permission-mode 重置回默认。autocli / Bash 命令直接用 Bash 工具跑就行。
前置条件(不满足就停)
先验证:
autocli doctor→ 全绿(浏览器抓取依赖).prax/notify.yaml存在且包含目标通道(默认daily-digest)——没配就明确告诉用户先配,不要继续抓- 当前时间合理(不要对凌晨 3 点的时间跑"今日"简报,除非用户说明)
验证失败:返回一条简要说明即可停止,不要继续。
Pipeline 步骤
变量
DATE = 今天的日期(YYYY-MM-DD,按用户本地时区)
VAULT = .prax/vault/ai-news-hub/$DATE
Step 1:准备目录
mkdir -p $VAULT $VAULT/raw
Step 1.6:解析推送通道(新增 — 0.5.5 起)
读 .prax/notify.yaml 取通道名,绝不硬编码 "daily-digest"。挑选规则(按优先级):
- 若
.prax/cron.yaml里当前 job 的notify_channel在notify.yaml中存在 → 用它 - 否则取
notify.yaml.channels第一个wechat_personal类型的通道 - 否则取
notify.yaml.channels任意第一个通道 - 都没有 → 在 Step 6 的汇报里明确告诉用户"未推送(无可用通道)",但 wiki 已落盘的事实仍要写
把选中的 channel 名字记成 CHANNEL,给 Step 5 用。
Step 1.5:加载源配置(新增 — 0.5.4 起)
读 .prax/sources.yaml,若不存在或字段缺失就用 DEFAULTS 兜底。配置完整 schema:
# 每个 source 都是可选 enable / 可改 limit
sources:
- id: twitter # 已知 id:twitter / zhihu / bilibili / hackernews
enabled: true
limit: 50 # autocli 抓取条数(拉得多但下面只过滤前 N 条)
top_n: 10 # 关键词过滤后保留 top N(按平台原生热度)
- id: zhihu
enabled: true
limit: 30
top_n: 10
- id: bilibili
enabled: true
limit: 20
top_n: 5
- id: hackernews
enabled: true
limit: 20
top_n: 10
# 关键词过滤:必须命中 include 之一,且不命中任何 exclude
keywords:
include: [AI, LLM, GPT, Claude, 模型, 智能体, agent, RAG, 推理, 微调, transformer]
exclude: [] # 比如 [广告, 推广] 用来去噪
DEFAULTS = 上面这份完整配置(即 .prax/sources.yaml 不存在时的行为,跟 0.5.4 之前完全一致)。
GUI 用户通常通过 praxdaily Sources 屏写这个文件,命令行用户也可以手写。
Step 2:抓取(browser-scrape 的风格)
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.
- 10d ago First seen · 208 lines · 34 tokens per session scan A 448cf5e79735
ai-news-daily is a skill published in the GitHub repository ChanningLua/prax-agent (272 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 2,262 once invoked, about $0.0002 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
daily-sales-standup
Your daily sales co-pilot. Reviews your pipeline, surfaces overdue follow-ups and at-risk deals, generates today's priorities, and kicks off the right skills.
magazine-web-ppt
For marketing and gtm work: bind launches, campaigns, events, and brand plans to growth and pipeline outcomes. Built around the core query "annual-marketing-plan", with GTM strategy lead judgment, buyer-ready proof, and this outcome: approve launch plan, campaign budget, or GTM motion.
html-ppt-zhangzara-broadside
OpenDesign's product-launch announcement and press narrative — the headline, the proof points, and the call to action. Built as a decision-grade marketing & GTM deck for press, community, prospects.
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
deck-guizang-editorial
OpenDesign's FY26 marketing plan: brand-to-pipeline — audience, offer, channel mix, and the launch calendar that ties creative to growth. Built as a decision-grade marketing & GTM deck for CMO, growth lead, founder.
drug-design
End-to-end drug discovery pipeline orchestration. Deterministic Python script that auto-chains structure prediction, pocket detection, de novo design, docking, scoring, and ADMET filtering into reproducible workflows.