Most Claude Code skills collapse into a tangle of if/else conditionals as you add output formats — bloating SKILL.md and burning context-window tokens. Borrowing two classic design patterns, Strategy and Template Method, you can keep one stable process and swap implementations from a resources/ folder. Here's how to build a polymorphic PR-summary skill that outputs a bullet list, prose, or a diagram on demand — without the bloat.

Most developers using Claude Code on Java projects default to one model and never look back — until the bill arrives, or the architectural suggestion turns out to be confidently wrong. Matching the right model to the right task is one of the highest-leverage habits you can build as an AI-assisted Java developer.

A 1M token context window sounds like a license to load everything into Claude Code and let it figure things out. The research — and a few painful debugging sessions — say otherwise. Past roughly 100k tokens, reasoning quietly degrades while the model keeps sounding confident. Here's how to work with the attention budget instead of against it.