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 cafe3310/public-agent-skills --skill twitter-watchgit clone --depth 1 https://github.com/cafe3310/public-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/cafe3310/public-agent-skills/twitter-watch)<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/twitter-watch"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/twitter-watch/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/cafe3310/public-agent-skills/twitter-watch"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/twitter-watch.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 | $0.00018 | $0.00794 |
| Opus 5 | $0.00009 | $0.00397 |
| Sonnet 5 | $0.00004 | $0.00159 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
twitter-watch 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 11d 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.
What it actually says
twitter-watch
一个自动监控 Twitter 互动数据的 Agent 技能，旨在通过模拟真人行为获取最准确的推文表现指标。
工作原理与设计意图
为了确保抓取成功率并规避反爬虫机制，watch.py 脚本采用了以下设计：
- 自动配置: 脚本启动时会自动检查并确保
~/.agent-browser/config.json中配置了{"autoConnect": true}，这确保了 agent-browser 优先尝试连接用户已打开的真实浏览器。 - 强制有头模式: 所有命令均附带
--headed参数，确保浏览器界面可见，方便用户监控和必要时介入（如处理验证码）。 - 真实浏览器验证: 脚本会检查
navigator.userAgent。如果仍处于Headless模式或未建立连接，脚本将发出警示。 - 持久化会话: 使用
--session-name twitter-watch。如果用户已在浏览器登录，脚本将继承登录状态。 - 拟人化滚动与随机延迟: 模拟真实用户行为，触发推文动态加载。
使用方法
1. 对非技术用户的说明 (当用户询问如何使用时)
如果用户询问如何使用此功能，请务必提供以下简洁的操作指南：
Twitter 监控使用说明：
- 开启浏览器调试模式：在 Chrome 地址栏输入
chrome://inspect/#remote-debugging并回车，确保勾选 "允许远程调试"。- 准备环境：脚本会自动为您配置
agent-browser。在使用过程中，如果 Chrome 弹出“是否允许远程调试”提示，请务必点击**“允许”**。- 准备链接文件：将想要监控的 Twitter 链接放入文本文件（如
links.txt），每行一个。- 发送文件路径：将文件路径发送给我，我将自动抓取数据并生成
twitter_report.md报告。
2. 执行流程 (Agent 必读)
- 环境准备: 确保已安装
agent-browser和python3。 - 人工验证:
- 首先运行：
agent-browser --headed --session-name twitter-watch open https://www.google.com。 - 使用
ask_user确认用户已看到窗口并允许连接。
- 首先运行：
- 启动监控:
python3 skills/twitter-watch/scripts/watch.py links.txt
输出规范
1. 单条结果 (JSON)
文件名：output_<tweet_id>.json
包含 raw (原文) 和 val (数值) 字段。
2. 汇总报告 (Markdown)
文件名：twitter_report.md
包含操作系统信息、生成时间以及带有格式化数字的表格。
环境要求
- Python 3.6+
- Node.js & NPM
- agent-browser CLI
- Google Chrome 浏览器 (已启用远程调试)
What ships with it
3 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.
- 11d ago First seen · 65 lines · 18 tokens per session scan A bbfafdc66ea8
twitter-watch is a skill published in the GitHub repository cafe3310/public-agent-skills (253 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 794 once invoked, about $0.0001 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
preview-json
Render and preview JSON files in browser with syntax highlighting, collapsible tree view, and search.
preview-markdown
Render and preview Markdown files in browser with GitHub-flavored formatting and syntax highlighting.
preview-mermaid
Render and preview Mermaid diagrams in browser with support for flowcharts, sequence diagrams, class diagrams, and more.
playwright-best-practices
Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions…
firecrawl-search
Web search with full page content. Use when no URL is known: finding sources, articles, or news. For papers use firecrawl-research-index; for library, API, error, or bug questions use firecrawl-developer-index.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.