Anything is possible with enough code *

Anthropic says Claude Code users approve 93% of permission prompts. That number cuts two ways. It's the whole motivation for auto mode (if you're going to rubber-stamp, let an AI rubber-stamp on your behalf). It's also a quiet admission that a lot

Two weeks of daily sandbox use, the config I landed on, and the friction I'm still sorting out

Awhile back, I shipped a big refactor last week. Weeks of effort, untangling legacy code, the kind of deep backend work that nobody sees unless you tell them about it. I posted in Slack: "Merged the BigRefactor™️!" Maybe a little too detailed about the how and the why,

Testing Claude Code plugins without trashing your config

In which we debug a shell script that has been around forever, and dive into building gem

You know when you are running your code, and you see a bunch of messages, and you have no idea what they are? And then one day, you just get used to them... I'm reminded of this article [https://www.forbes.com/sites/kenkrogue/2012/08/13/1-

Obligatory first post! It only took 7 years and a pandemic to get an update up on my blog. I purchased pickles.dev back when it was released [https://www.blog.google/technology/developers/highlights-first-year-dev/], but never got around to doing anything. So here it is, a

I’m filing this one under “blog posts I wish existed when I was googling.” If you are dealing with data on the web, you are probably most familiar with JSON and XML. Less common nowadays is CSV, but if it’s all you have, and the alternative is screen