How does it change model mid conversation?
Does it spawn sub agents with different models or is it the same single conversation dynamically switching models?
Yes, sub-agents I believe. You need to pay to reload context if you switch the main conversation model effort.
Subagents indeed. This [0] was the post I was referencing, and here's the original suggested prompt:
> For all coding tasks use your judgement to decide an appropriate lower power model and run that in a subagent
As said, I tweaked it a little bit to my preference (mostly because it started delegating a bit too much) and had it placed in my global claude.md but that's the gist.
[0] https://simonwillison.net/2026/Jul/3/judgement/