Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

Re:Claude Code sends 33k tokens before reading the prompt; O... by drob518 on Sunday July 12, 2026 @06:10PM (#48885352)

I think the commenter (who is not me) is saying to use Fable as the main agent but then use lesser models for your subagents so that you get the advantages of Fable to plan but then the subagents don’t cost as much, and may be more focused because they lack Fable’s thinking modes.

[ Parent | on HN ]

Re:Claude Code sends 33k tokens before reading the prompt; O... by ls612 on Sunday July 12, 2026 @09:52PM (#48886919)

I’ve heard the proper pattern is to have Fable write a software design doc and then tell Opus to follow that doc strictly in implementation and testing.

[ Parent | on HN ]

Re:Claude Code sends 33k tokens before reading the prompt; O... by mcv on Monday July 13, 2026 @08:43AM (#48891840)

I hear that too, but I'm much more ad-hoc about what model I use for what. Opus can be good at planning too, and Fable is remarkably good at figuring out obscure complexities in the code.

[ Parent | on HN ]