Token economy
Three things drive cost in Claude Code: context size, cache hit rate, and model choice. Most waste comes from one of these being misconfigured and left alone.
Model tiering — match the model to the task
| Task shape | Right model | |---|---| | Format fix, rename, small refactor, comment tweak | Haiku — ~15× cheaper than Opus, fast enough to feel instant | | Routine feature work, bug fix, test writing, reviewing a small diff | Sonnet — the default; 5× che
[Description truncada. Veja o README completo no GitHub.]