<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Claude-Code on korchasa@*ops</title><link>https://korchasa.dev/tags/claude-code/</link><description>Recent content in Claude-Code on korchasa@*ops</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 21 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://korchasa.dev/tags/claude-code/index.xml" rel="self" type="application/rss+xml"/><item><title>rtk: savings 160x lower than claimed</title><link>https://korchasa.dev/posts/2026_07_21_rtk_ekonomiya_v_160_raz_menshe/</link><pubDate>Tue, 21 Jul 2026 00:00:00 +0000</pubDate><guid>https://korchasa.dev/posts/2026_07_21_rtk_ekonomiya_v_160_raz_menshe/</guid><description>&lt;p&gt;I spent a month running &lt;a href="https://github.com/rtk-ai/rtk" rel="nofollow noopener noreferrer external"&gt;rtk&lt;/a&gt; — a proxy that filters shell command output to save LLM tokens. Its analytics reported 689 million tokens saved (93.3%).&lt;/p&gt;
&lt;p&gt;rtk hooks into the ide and rewrites bash commands: &lt;code&gt;git status&lt;/code&gt; becomes &lt;code&gt;rtk git status&lt;/code&gt;, and the output gets filtered and compressed. Two numbers go into its database: how many tokens the raw output contained and how many remained after filtering. The difference is declared &amp;ldquo;saved&amp;rdquo;. Looks perfectly logical: the bigger the output, the bigger the savings.&lt;/p&gt;</description></item></channel></rss>