<?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>Tooling on taude.xyz</title><link>http://taude.xyz/tags/tooling/</link><description>Recent content in Tooling on taude.xyz</description><generator>Hugo</generator><language>en-us</language><copyright>Todd</copyright><lastBuildDate>Thu, 03 Sep 2026 17:53:00 -0400</lastBuildDate><atom:link href="http://taude.xyz/tags/tooling/index.xml" rel="self" type="application/rss+xml"/><item><title>Auditing my own scripts drawer</title><link>http://taude.xyz/posts/auditing-my-own-scripts-drawer/</link><pubDate>Thu, 03 Sep 2026 17:53:00 -0400</pubDate><guid>http://taude.xyz/posts/auditing-my-own-scripts-drawer/</guid><description>&lt;p&gt;Every developer has a &lt;code&gt;~/dev/tools/scripts&lt;/code&gt; folder. Mine has run for years
without an index. I asked Claude Code to read every file in it and write
one.&lt;/p&gt;
&lt;p&gt;The brief was simple: read the whole directory, then produce an &lt;code&gt;INDEX.md&lt;/code&gt;
with three columns — tool, how to run it, what it does.&lt;/p&gt;
&lt;p&gt;It scanned roughly 40 files: Python CLIs built on &lt;code&gt;uv&lt;/code&gt;, shell wrappers, one-off
Snowflake key-rotation scripts, a tmux session launcher, a Hacker News
summarizer. Some had docstrings. Several had none, and their purpose was
recoverable only by reading the &lt;code&gt;argparse&lt;/code&gt; block or the hardcoded constants
at the top.&lt;/p&gt;</description></item></channel></rss>