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 laborany/laborany --skill rss-news-aggregatorgit clone --depth 1 https://github.com/laborany/laboranyWrote 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/laborany/laborany/rss-news-aggregator)<a href="https://agentmods.dev/skills/laborany/laborany/rss-news-aggregator"><img src="https://agentmods.dev/badge/skills/laborany/laborany/rss-news-aggregator/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/laborany/laborany/rss-news-aggregator"><img src="https://agentmods.dev/badge/skills/laborany/laborany/rss-news-aggregator.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 | $0.00049 | $0.02181 |
| Opus 5.5 | $0.00020 | $0.00872 |
| Sonnet 5.5 | $0.00010 | $0.00436 |
| Haiku 4.5 | $0.00005 | $0.00218 |
Grade A, and why
优质资讯 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 2mo 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
优质资讯 - RSS 资讯聚合工具
从全球 92 个高质量技术博客采集最新的 AI/科技资讯，支持多维度过滤和智能质量评估。
✨ 功能特性
- 多源聚合：从 92 个精选 RSS 源（HN Popularity Contest 2025）采集资讯
- 智能过滤：支持关键词搜索、自然语言查询、主题分类、时间范围、精准来源筛选
- 质量评估：基于来源权威性、内容质量、时效性自动评分排序（0-100 分）
- 双格式输出：Markdown（便于编辑）+ HTML（Linear 简约风格 + 卡片布局）
- 实时更新：直接从 RSS feeds 获取，分钟级时效性
🚀 快速开始
方式 1：获取最近 3 天的所有资讯
python scripts/fetch_rss.py --days 3 --output /tmp/raw.json
python scripts/filter_content.py --input /tmp/raw.json --output /tmp/filtered.json
python scripts/generate_report.py --input /tmp/filtered.json --output-dir docs/news
方式 2：搜索特定主题
# 搜索 "Claude" 相关资讯
python scripts/fetch_rss.py --days 7 --output /tmp/raw.json
python scripts/filter_content.py --input /tmp/raw.json --query "Claude" --output /tmp/filtered.json
python scripts/generate_report.py --input /tmp/filtered.json --output-dir docs/news
方式 3：精准过滤特定来源
# 只获取 Simon Willison 和 Gary Marcus 的文章
python scripts/fetch_rss.py --days 3 --sources "simonwillison.net,garymarcus.substack.com" --output /tmp/raw.json
python scripts/filter_content.py --input /tmp/raw.json --output /tmp/filtered.json
python scripts/generate_report.py --input /tmp/filtered.json --output-dir docs/news
📋 使用流程
步骤 1：获取 RSS 数据
python scripts/fetch_rss.py [选项]
选项：
--days N：获取最近 N 天的资讯（默认 3 天）--sources "source1,source2"：只获取指定来源（可选）--output FILE：输出 JSON 文件路径
步骤 2：过滤和评分
python scripts/filter_content.py [选项]
选项：
--input FILE：输入 JSON 文件（来自步骤 1）--query "关键词"：搜索查询（可选）--sources "source1,source2"：过滤特定来源（可选）--min-quality N：最低质量分数 0-100（可选）--output FILE：输出 JSON 文件路径
步骤 3：生成报告
python scripts/generate_report.py [选项]
选项：
--input FILE：输入 JSON 文件（来自步骤 2）--output-dir DIR：输出目录（默认docs/news）--format md|html|both：输出格式（默认 both）
步骤 4：查看报告
- Markdown：
docs/news/rss-news-YYYY-MM-DD.md - HTML：在浏览器中打开
docs/news/rss-news-YYYY-MM-DD.html
📊 数据源分类
What ships with it
8 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.
- 2mo ago First seen · 240 lines · 49 tokens per session scan A f0aa563c4556
优质资讯 is a skill published in the GitHub repository laborany/laborany (86 stars, last pushed 5mo ago), licensed MIT. It adds 49 tokens to every session and 2,181 once invoked, about $0.0002 per session on Opus 5.5. 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.
优质资讯 compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| 优质资讯laborany/laborany | Skill | 86 | 5mo ago | MIT | A | 49 | Claude Code, Codex |
| bencium-impact-designerbencium/bencium-marketplace | Skill | 484 | 1mo ago | MIT | A | 56 | Claude Code |
| tauri-updaterluochang212/skill-zoo | Skill | 124 | yesterday | MIT | A | 53 | Claude Code, Codex |
| tts-voicefuyuxiang/echo-agent | Skill | 1.0k | yesterday | none | A | 29 | Claude Code, Codex |
| web-extractfuyuxiang/echo-agent | Skill | 1.0k | yesterday | none | A | 26 | Claude Code, Codex |
| maps-poifuyuxiang/echo-agent | Skill | 1.0k | yesterday | none | A | 32 | Claude Code, Codex |
| text-toolsfuyuxiang/echo-agent | Skill | 1.0k | yesterday | none | A | 21 | Claude Code, Codex |