The conclusion aligns with my own belief, which is that it's better to create a minimal context by hand than get agents to create it:
We find that all context files consistently increase the number of steps required to complete tasks. LLM-generated context files have a marginal negative effect on task success rates, while developer-written ones provide a marginal performance gain.
When I have got Claude to create a context, it's been overly verbose, and that also costs tokens.