Intuitively makes sense, but in my experience, a more realistic workflow is using the main agent to sub-agent delegation pattern instead of straight 7x-ing token costs.

By delegating to sub agents (eg for brainstorming or review), you can break out of local maxima while not using quite as many more tokens.

Additionally, when doing any sort of complex task, I do research -> plan -> implement -> review, clearing context after each stage. In that case, would I want to make 7x research docs, 7x plans, etc.? probably not. Instead, a more prudent use of tokens might be to have Claude do research+planning, and have Codex do a review of that plan prior to implementation.

Is this going to get my Claude subscription cancelled if I run it with a claude backend, given that it's orchestrating the CLI? I am still a little unclear about the boundaries of that.

AI is like XML: if it doesn't solve your problem, you are not using enough of it.

Any suggestions for «orchestrating» this type of experiment?

And how does one compare the results in a way that is easy to parse? 7 models producing 1 PR each is one way, but it doesn’t feel very easy to compare such.