this repo is f**king insane compaction is still a

Replaced a summarization prompt with Jev scoring each tool call as a yes/no question, dropping calls that no longer matter.
The original post
this repo is f**king insane compaction is still a summarization prompt in 2026 - this dev deleted the prompt and let Jev score every tool call instead each call gets a question - does this still matter - and those that don't just go away. your messages are unchanged, in order,
Engagement when collected
Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.
Where this case fits
Filed under agents & workflows, coding & developer tools. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Other posts in the same family are on the agents & workflows page.
Related Jev cases
found the perfect use case for @typesafeai Jev: instant
Agents
Breaking: Browser Use + Jev = Ultrafast Findings flights
AgentsBrowser agents
The gains aren’t free: Jev can't generate text Comparing
Dev toolsClassification
Jev case: in 40 seconds it broke down 724 live ads from 37
WebsitesAgents
Keep browsing: all 1173 Jev cases · more from @0xCarnagee · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post