Split your agent monitoring into a cheap deterministic layer and an expensive advisory one.

LivePlan watches a programming agent's trajectory with rule-based detectors that need zero model calls, waking an advisor LLM only on drift, repeated failed actions, or an imminent no-patch exit. On SWE-agent across five LLMs it raised resolution rates up to 15.2% (9.9% average) for ~$0.08 extra per instance. Cheap monitors decide when to intervene, an expensive model decides what to say: the inverse of the "LLM judge watches everything" pattern that eats budget and hallucinates corrections.