Token Efficiency

This is the skill you add when you're tired of burning tokens on log files and unnecessary file reads. It teaches Claude to use grep instead of reading entire files, bash commands instead of the read-edit-write cycle, and quiet flags by default. The model selection guidance alone (Opus for learning codebases, Sonnet for everything else) can cut costs in half. The real value is in the decision trees: when to use sed versus Read+Edit, when bash makes sense versus when you actually want to see a diff. It's opinionated about progressive disclosure and includes a helpful myth-buster about skill loading costs. If you've ever watched Claude read a 10,000 line log file to find one error, you need this.