<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>PyO3 on Joe Bollen Security</title><link>https://joe-b-security.github.io/tags/pyo3/</link><description>Recent content in PyO3 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>Wed, 15 Apr 2026 10:00:00 +0000</lastBuildDate><atom:link href="https://joe-b-security.github.io/tags/pyo3/index.xml" rel="self" type="application/rss+xml"/><item><title>Improving a Coding Agent Harness: Part 4.5, Security Hooks</title><link>https://joe-b-security.github.io/posts/2026-04-15-improving-coding-agent-harness-part4-5/</link><pubDate>Wed, 15 Apr 2026 10:00:00 +0000</pubDate><guid>https://joe-b-security.github.io/posts/2026-04-15-improving-coding-agent-harness-part4-5/</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 for structural code reading. 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. In &lt;a
href="https://joe-b-security.github.io/posts/2026-04-09-improving-coding-agent-harness-part2/"&gt;Part 2&lt;/a&gt;, I added an OODA loop with a rule engine and verify phase. In &lt;a
href="https://joe-b-security.github.io/posts/2026-04-10-improving-coding-agent-harness-part2-5/"&gt;Part 2.5&lt;/a&gt;, I added a RAG layer over OWASP guidance for secure code generation. In &lt;a
href="https://joe-b-security.github.io/posts/2026-04-13-improving-coding-agent-harness-part3/"&gt;Part 3&lt;/a&gt;, I used the harness to find a scoring-path bug in a coding benchmark. In &lt;a
href="https://joe-b-security.github.io/posts/2026-04-15-improving-coding-agent-harness-part4/"&gt;Part 4&lt;/a&gt;, I added a hook framework with fast Python and Rust dispatch paths.&lt;/p&gt;</description></item><item><title>Improving a Coding Agent Harness: Part 4, Hooks</title><link>https://joe-b-security.github.io/posts/2026-04-15-improving-coding-agent-harness-part4/</link><pubDate>Wed, 15 Apr 2026 00:00:00 +0000</pubDate><guid>https://joe-b-security.github.io/posts/2026-04-15-improving-coding-agent-harness-part4/</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 for structural code reading. 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. In &lt;a
href="https://joe-b-security.github.io/posts/2026-04-09-improving-coding-agent-harness-part2/"&gt;Part 2&lt;/a&gt;, I added an OODA loop with a rule engine and verify phase. In &lt;a
href="https://joe-b-security.github.io/posts/2026-04-10-improving-coding-agent-harness-part2-5/"&gt;Part 2.5&lt;/a&gt;, I added a RAG layer over OWASP guidance for secure code generation. In &lt;a
href="https://joe-b-security.github.io/posts/2026-04-13-improving-coding-agent-harness-part3/"&gt;Part 3&lt;/a&gt;, I used the harness to find a scoring-path bug in a coding benchmark.&lt;/p&gt;</description></item></channel></rss>