In my last post I described graphlens — what it does, how it works — and along the way I casually claimed that an agent "burns tokens grepping around a repo." I gave exactly zero numbers to back that up. This post fixes that. Here are the measurements, the data, and a reproducible harness. Spoiler: the conclusion is not the one I expected going in, and that's the interesting part. TL;DR I took one agent (Claude Code), changed exactly one thing — which MCP server feed...