3 posts tagged #model-selection.
Stored session transcripts are an external memory most people throw away after 30 days. A skill that forks a cheap model to grep, expand, and re-rank them turns 'what did we decide about X' into ranked snippets — so the agent stops re-making old mistakes.
Subagents are sold as parallelism. The real win is context hygiene plus model arbitrage: delegate read-heavy investigation to cheap explorers so your expensive model only ever sees distilled findings.
Stop fighting the context limit with a bigger window. Write an exhaustive plan to a file, then run a relay of fresh sessions that each tick off items — so a migration too big for any single context still ships coherently.