sandboxing

2026-06-25 • 8 min read

Working on a small project, trying to implement skills into an agent that does not support skills, made me realize (again) that using skills to set guardrails depends a lot on the model you're using and is non-deterministic almost by design because of the way they are implemented…

2026-03-23 • 4 min read

Back in October or November last year, when I started using Opencode, I spent quite a bit of time setting up permissions and realised they were both complex to set up and, frankly, unreliable. Recently, I have been working on sandboxing the coding agents I use, and I wanted to sh…