A tweet that is known as a note_tweet are posts longer than 280 characters. xurl will return a JSON object with the longer content in .data.note_tweet.text, while .data.text is truncated to 280. In additional to articles for long form content, I would also like to search for note_tweet. There is no content filter to enable querying for these directly, so once again I will need to find a heuristic approach that works. Grok suggests: ("thread" OR "1/" OR "continued" OR "full story" OR "read more") min_faves:50 -is:retweet That suggestion doesn't feel right at first glance. There must be some better criteria for finding longer tweets with good substance.

To get more productive reading time out of X/Twitter, rather than rely on the algorithm, I'm going to use Hermes Agent to give me a daily morning report. ``` Every morning at 6 a.m. 1. Use `xurl --app hermes-agent-xurl search "is:verified has:links agent" -n 12` to fetch a list of articles as JSON 2. Produce a report with a 1 or 2 line summary per article Deliver the report on Slack without preview. ``` Coming from a coding background, one needs to become more comfortable with prompting Hermes in this way. Examining `~/.hermes/cron/jobs.json`, one will be a little taken aback at first, as Hermes rewrites the prompt. It removes certain details and it adds others. What the human believed to be important may not be what the agent believes to be important, so one develop a degree of confidence that the agent gets this correct. I certainly cannot argue against the result, which turned out to be correct. That's where the confidence ultimately comes from. I expect this technique to be fruitful. I will use jobs throughout the day to deliver exactly what I want to read, and this will replace the algorithm-manipulated doom scrolling.

Apparently the version 2 api doesn't support this same query syntax as the user interface. This works: xurl search "is:verified has:links agent" -n 20

① X を自動で操作（xurl） 「#AI副収入 で過去24時間 いいね100超え 全部取って」を1コマンドで頼める。 普段：ブラウザで検索→スクショ→Notion貼って明日また検索 Hermes だと： ・直近24h バズTOP20 を自動収集→毎朝Slackに配信 ・@○○のフォロワー300人 自己紹介抽出→「副収入興味あり」だけ抜く ・X 投稿予約も Typefully なしで Hermes に頼める X API（月100ドル）使わずに全部できる。 最初から入ってる（追加インストール不要）。

⎐كُـود⎐كوبِون⎐خـِصم⎐ ⎐ايهرب⎐ايهيرب اهرب ⊵GCA5893⊴ ⎐نون⎐ ⊵S3Q⊴ ⎐نمشي⎐ ⊵AABN⊴ ⎐باث▬اند▬بودي⎐ AB6K⊴ ⎐ناتشورال ⊴تاتش⎐ ⊵C37⊴ ⎐فوغا⎐كلوسـيت⎐ ⊵V1⊴ ⊴ماكـس ⊴ ⊵A9B⊴ ___ xuRL

【ご報告】 キャスト・スタッフ応募の方々にDM送らせていただきました。 ⚠　数名送れていない状態です　⚠ ●当アカウントをフォローしていない。 ●XURLが自身のものではなくホーム。※初 「フォーム送ったのに来てないよ！」って方がいましたら、DM頂けますと幸いです。

and i might as well give Percy the capability to monitor X for posts relating to monitored markets and memecoins, right? i bet plugging into the xurl skill simply for monitoring doesn't cost anything. i think the only costs are when the agent posts.

The @xai team has published a full setup guide on how to use the xurl skill, which allows your Hermes Agent to read and write to X on your behalf — posting, searching, pulling bookmarks, managing lists, and more — all through natural language.

So I set up a cron job that runs every morning at 9 AM. It uses xurl to scan X for keywords like "problem", "challenge", "struggling" combined with "AI", "Bitcoin", "LLM", "agent". Real-time signal detection.

母君のロイヤルサロン公式XURL x.com/datesama_TBSR

agents:// URI scheme unifies AI agent CLIs. Single grammar for CRUD: read as markdown, query threads by role/provider. xurl in Rust — forwards provider args via query params.

𝗦𝗶𝗺𝗽𝗹𝗲 𝗫 𝗢𝗽𝗲𝗻𝗖𝗹𝗮𝘄 𝗦𝗲𝘁𝘂𝗽 𝗚𝘂𝗶𝗱𝗲 Want your AI agent to help you monitor X, analyze bookmarks, draft posts, and manage your content workflow? Here’s a clean, step-by-step way to connect them: - Create an OpenClaw agent: Hostinger’s version is the easiest as it runs 24/7 without using your computer. - Go to the X Developer Console: Create a new app, and save your keys. Set permissions to Read Write, with callback URL: http://localhost:8080/callback - Tell your OpenClaw agent: “Update yourself, install the xurl X skill, and tell me what I need to configure.” - Complete the login (OAuth) on the machine running OpenClaw and test it by asking the agent to read your timeline, bookmarks, or a list. Pro tip: Have it review a saved list every morning, draft smart replies, or turn bookmarks into thread outlines. This setup turns your agent into a powerful content partner on X.

X公式のCLIがあったのか 【2026年3月版】xurl完全ガイド — X公式CLIツールのセットアップからAI自動投稿まで zenn.dev/ricrio/articles/xur…

x bot TODO: fix xurl mentions.read scope. zero engagement identity verified. this is a permissions bug not a feature request. #hermesagent

不过坦白的来说，codex app 太好用了，我自己用 xurl 的频率都越来越低了🤓

哇 xurl 能给已经有的 session 发消息哈？

codex是有官方的cc插件的方法吧，我自己使用的方法是用 @OnlyXuanwo 的xurl，让cc直接用xurl给Codex发消息

For folks using xurl to ingest tweets, I've found that tweets come in different forms, and if you want the full content you need to include the appropriate fields. For tweet id <T>: xurl --app <app-name> '/2/tweets/<T>?expansions=author_id&tweet.fields=text,note_tweet,attachments,author_id,conversation_id,created_at,entities,geo,id,in_reply_to_user_id,lang,public_metrics,referenced_tweets,reply_settings,source,withheld' This returns JSON. Hopefully, tweet.fields gives complete coverage of all possibilities. An ordinary tweet places the content in .data.text A note_tweet (exceeding the old 280 character limit) places the content in .data.note_tweet.text with .data.text containing a truncation. An article places the content in .data.article.plain_text

xurl、最近僕も乗り換えました。 自前でOAuth処理を書いてた頃が嘘みたいに楽で、Claude Codeに「xurlで叩いて」と言うだけで通るのが地味に効いてて。認証まわりの試行錯誤が消えたのは大きい。 公式が出してるの、安心感ありますね。