[chrysoprace]

We tried adoption of Claude Code at my last job as our PM was quite excited about its potential and I saw some horrors that were raised during code review (where I thankfully read the code):

- Using private undocumented APIs subject to breaking changes;

- Removing a call to produce a message to an external topic, with no internal references besides tests, declaring it as "redundant" (it was very much not redundant);

- Repeated duplication of formatting, calculation, and permission logic, causing inconsistencies and bugs.

They met whatever goal the agent created for itself, but they would've broken several features in ways that would've been difficult to test for, either today or in the future.