Developer-Tools

Your AI Harness Is Hand-Crafted. That's the Problem.

Stanford’s Meta-Harness paper argues that optimizing the code around the model matters more than optimizing the model itself. I applied it to my Claude Code setup and got the first real numbers: 3,723 tokens always in context, with no evidence they’re the right ones.

The Missing Step: What a Colleague's Hint Taught Me About AI-Driven Planning

Structured requirements, deviation rules, and the art of selective theft: five concepts borrowed from GSD, twenty rejected.

When Your AI Skills Library Gets Too Smart for Its Own Context Window

From token optimization to an orchestrated development workflow with Claude Code: teaching an AI your patterns is only part of the problem.

From Asking Claude to Code to Teaching Claude Our Patterns: Building Modular AI Skills

The best way to work with AI isn’t to ask it to write code: it’s to teach it your patterns first.