<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Context on the art of simplicity</title><link>https://naoko.github.io/tags/context/</link><description>Recent content in Context on the art of simplicity</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 11 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://naoko.github.io/tags/context/index.xml" rel="self" type="application/rss+xml"/><item><title>Three Agent Tools, One Context Budget: TokenEconomizer, Trail-Code, humanlayer/skills</title><link>https://naoko.github.io/posts/2026-11-11-three-agent-tools-one-context-budget/</link><pubDate>Wed, 11 Nov 2026 00:00:00 +0000</pubDate><guid>https://naoko.github.io/posts/2026-11-11-three-agent-tools-one-context-budget/</guid><description>&lt;p&gt;Three tools showed up in my feed inside about a week, each with a tidy one-line pitch, and all three arrived framed as though the job was to pick one of them. TokenEconomizer stops your agent burning money on tool definitions it never uses. Trail-Code gives every agent on your team a shared memory. humanlayer/skills turns open-ended chatting into repeatable workflows.&lt;/p&gt;&#10;&lt;p&gt;I went and read all three properly, partly because I&amp;rsquo;ve &lt;a href="https://naoko.github.io/posts/2026-06-28-cheaper-ai-coding-rtk-codegraph/"&gt;written about this problem before&lt;/a&gt; and partly because the three descriptions didn&amp;rsquo;t sound like they were describing the same &lt;em&gt;kind&lt;/em&gt; of thing at all.&lt;/p&gt;</description></item></channel></rss>