Skill
model-judgment
The operating layer that makes boil-the-ocean affordable — let the agent use its OWN judgment to route each task to the cheapest model tier that clears the quality bar, delegating bulk work DOWN to smaller models in subagents and escalating hard judgment UP to the top model. Read alongside boil-the-
Claim this listing
Connect your GitHub to prove you own or maintain this listing. We verify repo access automatically — most publishers are confirmed in seconds.
1Connect GitHub
2Submit your claim
3Auto-verified, or reviewed within 48h