A fun recent experience I had with Claude was I asked it to write a model for PBTs against a complex SUT, and it duplicated the SUT algorithm in the model — not helpful! I had to explicitly prompt it to write the model algorithm in a completely different style.

Ugh, yeah. Duplicating the code under test is a bad habit that Claude has had when writing property-based tests from very early on and has never completely gone away.

Hmm now that you mention it we should add some instructions not to do that in the hegel-skill, though oddly I've not seen it doing it so far.