I corrected my own benchmark claim from 91.5% to 88%. Here's what changed.

A week ago I shipped v4.4.3 of context-router with a number on the README: "91.5% fewer tokens than code-review-graph." It was true in the narrow sense that both numbers came from real benchmark runs. It was also wrong in every way that matters. The two tools were running on different repos, on different tasks, with different inputs. I was comparing my best-case workload to their best-case workload and putting a percent sign between them. This post is about the redo. v4.4.4 ships a workload-matc