The latest articles on DEV Community by Pedro Dias (@digitaldias). https://dev.to/digitaldias https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4229040%2F408560c9-e680-4f59-9505-3e3fd4b21077.jpg https://dev.to/digitaldias en Pedro Dias Thu, 05 Nov 2026 17:22:36 +0000 https://dev.to/digitaldias/your-model-choice-is-a-bet-build-a-router-that-keeps-score-1i8a https://dev.to/digitaldias/your-model-choice-is-a-bet-build-a-router-that-keeps-score-1i8a <p>Most of the time I pick the same Claude model I used last session, out of habit. So I built a small Claude Code mod that scores that habit.</p> <p>It reads your first prompt, asks Haiku which model and effort the task needs, and shows a verdict beside the chat: on target, one step off, overshot or undershot. Each verdict comes with a short poster and a WHY box. The WHY box is the part I learn from.</p> <p>The full post covers the rubric I use, how the mod is put together, what a model switch costs in cache terms, and a recipe you can paste into the Claude Desktop app to build your own. The cost numbers are my own estimates, so yours will differ.</p> <p><strong>Read the full post, with the recipe and the rubric:</strong> <a href="https://digitaldias.com/blog/2026-11-05-model-choice-is-a-bet/" rel="noopener noreferrer">https://digitaldias.com/blog/2026-11-05-model-choice-is-a-bet/</a></p> claude ai webdev devtools