Its a good point that there is benefit to using general intelligence models to figure out what code to write and to write specs. Implementation plans as well as long as the general intelligence is also great at coding. But you would actually prefer here the model that performs best in your business domain rather than best at general intelligence.

The Opus frontier model will spin up a cheaper Sonnet subagent to explore the code base. Similarly we can have a Pareto optimal subagent write most code and verify it.