<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Developer Tools on Joe Bollen Security</title><link>https://joe-b-security.github.io/tags/developer-tools/</link><description>Recent content in Developer Tools on Joe Bollen Security</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>Yes, it's a real three-body problem simulation</copyright><lastBuildDate>Thu, 09 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://joe-b-security.github.io/tags/developer-tools/index.xml" rel="self" type="application/rss+xml"/><item><title>Improving a Coding Agent Harness: Part 2, Writing Code</title><link>https://joe-b-security.github.io/posts/2026-04-09-improving-coding-agent-harness-part2/</link><pubDate>Thu, 09 Apr 2026 00:00:00 +0000</pubDate><guid>https://joe-b-security.github.io/posts/2026-04-09-improving-coding-agent-harness-part2/</guid><description>&lt;p&gt;In &lt;a
href="https://joe-b-security.github.io/posts/2026-04-07-improving-coding-agent-harness-part1/"&gt;Part 1&lt;/a&gt;, I added tree-sitter tools that let our mini coding agent find definitions and trace references structurally. In &lt;a
href="https://joe-b-security.github.io/posts/2026-04-07-improving-coding-agent-harness-part1-5/"&gt;Part 1.5&lt;/a&gt;, I locked those tools behind a secure factory that makes files outside the workspace invisible for security. Both parts were about reading code, and this part will look into some approaches to improve the writing of code.&lt;/p&gt;</description></item></channel></rss>