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 sugarforever/01coder-agent-skills --skill tweet-insightgit clone --depth 1 https://github.com/sugarforever/01coder-agent-skillsWrote 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/sugarforever/01coder-agent-skills/tweet-insight)<a href="https://agentmods.dev/skills/sugarforever/01coder-agent-skills/tweet-insight"><img src="https://agentmods.dev/badge/skills/sugarforever/01coder-agent-skills/tweet-insight/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/sugarforever/01coder-agent-skills/tweet-insight"><img src="https://agentmods.dev/badge/skills/sugarforever/01coder-agent-skills/tweet-insight.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 | $0.00098 | $0.01764 |
| Opus 5 | $0.00049 | $0.00882 |
| Sonnet 5 | $0.00020 | $0.00353 |
| Haiku 4.5 | $0.00010 | $0.00176 |
Grade A, and why
tweet-insight 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tweet Insight
从推文出发,深度研读所有关联内容,然后用自己的话写一条原创分享帖。
核心理念
这不是翻译,不是摘要,而是"学习并分享"。就像读完一篇论文后跟朋友讲你学到了什么 - 你消化了内容,形成了自己的理解,用自己的方式讲出来。
具体步骤:
- 读原推 → 读引用推 → 读关联文章/论文 → 整理信息 → 确定主题和角度 → 成文 → 复审
工作流
Step 1: 收集推文
用户提供一条或多条推文 URL。
首选方案:Playwright MCP(推荐,能获取完整结构化内容)
- 用
browser_navigate打开推文 URL - 用
browser_snapshot获取页面快照,从中提取:- 推文全文
- 作者、发布时间、互动量(replies, reposts, likes, bookmarks, views)
- 引用推文(quoted tweet)区块 - 注意:引用推文的完整 URL 不会直接出现在快照中
- 如果有引用推文:点击引用推文区块的 link 元素,页面会跳转到引用推文页面,此时从 Page URL 获取完整链接,再用
browser_snapshot获取引用推文的完整内容 - 提取推文和引用推文中的所有外部链接(
t.co短链接指向的实际 URL)
备选方案:WebFetch + r.jina.ai(无 Playwright 时使用)
- 使用
WebFetch(URL 加https://r.jina.ai/前缀)抓取推文内容 - 注意:r.jina.ai 能获取推文文字和引用推文内容片段,但可能无法返回引用推文的完整 URL
- 如果引用推文 URL 缺失,请用户手动提供
Step 2: 深度阅读关联内容
推文里往往链接到更重要的内容。这一步是关键。
- 提取推文中所有外部链接(论文、博客、公告页、系统卡等)
t.co短链接必须先解析再使用:用 Playwrightbrowser_navigate跟随跳转,从跳转后的 Page URL 获取完整真实 URL。推文快照中显示的链接文本(如github.com/unslothai/unsl …)是被截断的,绝不能直接用于输出- 用 WebFetch(可加
r.jina.ai前缀)逐一抓取链接内容 - 对于 PDF:如果 WebFetch 无法获取或内容过大,提示用户下载后提供本地路径,用 Read 读取
- 对于长文档:重点关注摘要、结论、关键数据、惊人细节,不需要逐字复述
- 有价值的链接要收集起来:如果关联内容中有对读者有用的资源链接(指南、GitHub、notebook 等),记录其完整 URL,在最终输出中附上
Step 3: 整理信息
读完所有材料后,梳理:
- 这件事的本质是什么? - 用一句话概括核心事件或发现
- 关键数据和事实 - 提取最有冲击力的数字和对比
- 令人意外的细节 - 那些让你"等一下,真的吗?"的部分
- 实际影响 - 这对普通人/开发者/行业意味着什么
- 上下文和背景 - 为什么这件事现在发生,跟之前有什么不同
Step 4: 确定角度并成文
不要试图覆盖所有信息。选一个角度切入,像讲故事一样展开。
写作原则
- 开头直击要害 - 第一句话就让人知道发生了什么,并且想继续读
- 用具体数据说话 - 不说"大幅提升",说"从 42% 跳到 97%"
- 细节是灵魂 - 惊悚的、有趣的、反直觉的细节让内容有血有肉(比如"研究员当时正在公园里吃三明治")
- 结构用内容传达,不用编号 - 可以用分段、空行来组织,但避免教科书式的"一、二、三"
- 说人话 - 写给聪明但不一定了解这个领域的朋友看,不是写给专家
- 适当加入自己的判断 - 这个东西好不好、重要不重要、可信不可信,读者想听你怎么看
格式
- 默认输出为单条推文
- 引用链接放在开头文字之后 - 先用一两句话引入,然后放链接(这样既自然又能生成卡片),不要放在最前面(太突兀)也不要放在最后面(不生成卡片)
- 结构随内容而定 - 不要总是 1/ 2/ 3/ 4/ 的固定模式。有的内容适合分点,有的适合连续叙事,有的适合先讲故事再给数据。让内容本身决定形式
- 中文内容为主(除非原推是英文且用户未指定语言)
- 数据和专有名词保留英文原文
- 如果内容确实很长,建议用户考虑发 X Article
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 · 124 lines · 98 tokens per session scan A 4526e11ce16c
tweet-insight is a skill published in the GitHub repository sugarforever/01coder-agent-skills (134 stars, last pushed 2mo ago), licensed MIT. It adds 98 tokens to every session and 1,764 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…