Test output eating your usage, and Claude saying "done" when it isn't. 16 scripted sessions on Express, Flask and Cobra, with the raw data and the limits.
I measured two common Claude Code complaints on three repos. Neither showed up.
Related
The other half of the software factory
Event storming, vertical slicing and event sourcing, shown on one small book club in Erlang, with the five Ds and what runs today.
Building Ribbonlab, a 3D Animated Background Generator
Originally published on ayurchenko.xyz. The image above opens the live editor. Ribbonlab is a free...
Design Systems for Coding Agents: 11 Builds, Measured
Originally published on ayurchenko.xyz. I gave one AI agent the same brief again and again: with no...