<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: rickye26</title><link>https://news.ycombinator.com/user?id=rickye26</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sun, 27 Sep 2026 01:09:55 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=rickye26" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by rickye26 in "Plan mode is dead"]]></title><description><![CDATA[
<p>My workflow is very similar. But I just ask agents to write design in html instead of markdown, due to its richer layout and better interactivity. When the design is about UI or anything related to graphics, this approach is extremely efficient.<p>I also found that having the design reviewed by multiple agents has very little marginal value. The review agent will always find something to improve, but mostly it’s just nit and not anything super important.<p>I used to let Claude just upload the html design doc to Claude artifacts for me to review. Recently I switched to codex and started to use my own tool <a href="https://github.com/hyperlogue/r3" rel="nofollow">https://github.com/hyperlogue/r3</a> to complete this workflow.</p>
]]></description><pubDate>Sat, 26 Sep 2026 20:15:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=49860141</link><dc:creator>rickye26</dc:creator><comments>https://news.ycombinator.com/item?id=49860141</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49860141</guid></item><item><title><![CDATA[New comment by rickye26 in "Show HN: r3, A local alternative to Claude Artifacts"]]></title><description><![CDATA[
<p>Hi HN, author here. r3 is a tool originally built for reviewing code changes and design doc. I recently revamped it to better support html artifacts, similar to claude artifacts, but running locally and for all agents. This reflects a shift in my daily workflow: I now prefer html design doc over markdown for its richer layout and interactivity. I'd love to hear your thoughts on it!</p>
]]></description><pubDate>Sat, 26 Sep 2026 16:47:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=49858270</link><dc:creator>rickye26</dc:creator><comments>https://news.ycombinator.com/item?id=49858270</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49858270</guid></item><item><title><![CDATA[Show HN: r3, A local alternative to Claude Artifacts]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/hyperlogue/r3">https://github.com/hyperlogue/r3</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49858152">https://news.ycombinator.com/item?id=49858152</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Sat, 26 Sep 2026 16:36:19 +0000</pubDate><link>https://github.com/hyperlogue/r3</link><dc:creator>rickye26</dc:creator><comments>https://news.ycombinator.com/item?id=49858152</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49858152</guid></item><item><title><![CDATA[New comment by rickye26 in "Show HN: Saggar, a Mac terminal that keeps sessions and your attention organized"]]></title><description><![CDATA[
<p>This looks really cool, especially on the remote control part. I've experienced exactly the same problem, but ended up building my own tool through an opposite architectural approach than Saggar.<p>The main difference is that I want to keep my existing workflow in Kitty and tmux/zellij. Since all of them provide solid remote control protocol, I wrote captain-miao (<a href="https://github.com/hyperlogue/captain-miao" rel="nofollow">https://github.com/hyperlogue/captain-miao</a>) which is a standalone TUI app that runs inside these terminals, observing the agent sessions, managing tabs and windows, and allow me to quickly jump to the exact window/tab that needs my attention. The sessions are still native windows/panes inside the terminal/multiplexer that I configured and polished for years.<p>One difficulty I found when trying to expanding the agent support beyond claude code and codex, many agents don't provide a good way to inject hooks to listen to the session status change. wondering how Saggar solves this problem. do it infer state from the screen buffer?</p>
]]></description><pubDate>Mon, 17 Aug 2026 18:06:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=49335164</link><dc:creator>rickye26</dc:creator><comments>https://news.ycombinator.com/item?id=49335164</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49335164</guid></item><item><title><![CDATA[Show HN: captain-miao – herding coding agents in your terminal (kitty/zellij)]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/hyperlogue/captain-miao">https://github.com/hyperlogue/captain-miao</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49223143">https://news.ycombinator.com/item?id=49223143</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 08 Aug 2026 16:11:19 +0000</pubDate><link>https://github.com/hyperlogue/captain-miao</link><dc:creator>rickye26</dc:creator><comments>https://news.ycombinator.com/item?id=49223143</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49223143</guid></item><item><title><![CDATA[New comment by rickye26 in "Show HN: R3 – Review locally and send structured feedback to your coding agent"]]></title><description><![CDATA[
<p>I built r3 to scratch my own itch when reviewing long design doc and planning doc from AI. The chat interface is inherently bad at tracking multiple pieces of feedback across different parts of a document, so I created a lightweight local web UI to streamline the review process.<p>I have been using it on my own projects for two weeks, and it has made design review much easier. I thought others working with AI coding agents might find it useful too.<p>Previously <a href="https://news.ycombinator.com/item?id=48855670">https://news.ycombinator.com/item?id=48855670</a>. Resubmit as lots of significant improvements have been made and I consider it's near the stable state.<p>I'd love to hear what you think and any feedback you have!</p>
]]></description><pubDate>Mon, 20 Jul 2026 02:59:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=48973902</link><dc:creator>rickye26</dc:creator><comments>https://news.ycombinator.com/item?id=48973902</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48973902</guid></item><item><title><![CDATA[Show HN: R3 – Review locally and send feedback back to your coding agent]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/hyperlogue/r3">https://github.com/hyperlogue/r3</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48973898">https://news.ycombinator.com/item?id=48973898</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Mon, 20 Jul 2026 02:57:52 +0000</pubDate><link>https://github.com/hyperlogue/r3</link><dc:creator>rickye26</dc:creator><comments>https://news.ycombinator.com/item?id=48973898</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48973898</guid></item><item><title><![CDATA[New comment by rickye26 in "Show HN: R3 – A Local Code Review Tool for You and Your AI Agent"]]></title><description><![CDATA[
<p>Your product looks great! Having AI to highlight important part of a code review is a great feature. I will add it to r3 too</p>
]]></description><pubDate>Sat, 11 Jul 2026 17:22:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=48873844</link><dc:creator>rickye26</dc:creator><comments>https://news.ycombinator.com/item?id=48873844</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48873844</guid></item><item><title><![CDATA[Show HN: R3 – A Local Code Review Tool for You and Your AI Agent]]></title><description><![CDATA[
<p>I built r3 to scratch my own itch when reviewing long design doc and planning doc from AI. The chat interface is inherently bad at tracking multiple pieces of feedback across different parts of a document, so I created a lightweight local web UI to organize the review process.<p>I have been using it on my own projects for one week, and it has made giving structured feedback to AI much easier. I thought others working with AI coding agents might find it useful too.<p>I'd love to hear what you think and any feedback you have!</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48855670">https://news.ycombinator.com/item?id=48855670</a></p>
<p>Points: 5</p>
<p># Comments: 2</p>
]]></description><pubDate>Fri, 10 Jul 2026 04:13:39 +0000</pubDate><link>https://github.com/hyperlogue/r3</link><dc:creator>rickye26</dc:creator><comments>https://news.ycombinator.com/item?id=48855670</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48855670</guid></item></channel></rss>