3 tagged breaking changes, measured the same way as everything else here.
Agent Claude Code
Follow this repository's documented setup and run paths literally, and report where they drift from reality. Use when you want to know whether the docs can be trusted by an agent starting fresh, or before relying on a documented command.
Agent Claude Code
Try to bootstrap and run this repository like a cold agent, then report where the path breaks down. Use when you want to know whether the repo is actually easy to start, not just whether it claims to be.
Agent Claude Code
Assess whether an agent can verify a small change here without guessing or running an unnecessarily heavy loop. Use before relying on a gate, or when a verification loop feels slower than it should be.