← All questions
Which Claude models does The Loop use?
context-loop runs on Opus 5.5 and next-loop runs on Sonnet 5.5, because scoring ambiguous tasks is a reasoning job and building a well-defined task is a transformation job.
Your own Claude Desktop session can run on a different model; the scheduled fires use the models set for each skill. You can change them if you want a different split.
For writing the task itself, use the biggest model you have, since every question you settle there is one context-loop does not have to ask.