<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Self-Improvement on zolty.systems</title><link>https://blog.zolty.systems/tags/self-improvement/</link><description>Recent content in Self-Improvement on zolty.systems</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 16 Jun 2026 20:00:00 -0400</lastBuildDate><atom:link href="https://blog.zolty.systems/tags/self-improvement/index.xml" rel="self" type="application/rss+xml"/><item><title>Token-budgeted self-improvement: pointing parallel agents at my own repos</title><link>https://blog.zolty.systems/posts/2026-06-16-token-budgeted-self-improvement/</link><pubDate>Tue, 16 Jun 2026 20:00:00 -0400</pubDate><guid>https://blog.zolty.systems/posts/2026-06-16-token-budgeted-self-improvement/</guid><description>A budgeted sweep that fans out parallel agents to scan releases, CVEs, and CI inefficiencies across my repos, test the safe wins in isolated worktrees, and open merge requests — under a hard token cap.</description></item></channel></rss>