Jev in production › Agent context and memory

jev-skill-gate

Scores every installed Claude Code skill against the current project in one parallel Jev pass and writes skillOverrides so only relevant skill descriptions load; the skill manifest came out 79% smaller on average (author).

Open on GitHub ↗

79% smallermeasured against a baseline, as published by the source
Use
Agent context and memory
Industry
Developer tools
Form
Open-source tool
Stage
In production
Plugs into
Claude Code
Listed
2026-09-24
Found via
github
Repository
ShivamPansuriya/jev-skill-gate
Stars
8
Forks
1
Last push
2026-09-23
Language
JavaScript
License
MIT

The README opens with

Claude Code loads every skill description into context at session start, whether or not the skill has anything to do with what you are working on. On a machine with a full skills library that is roughly 10,000 tokens spent before you type anything.

jev-skill-gate scores each skill against the project you are actually in, then writes skillOverrides so only relevant skills reach the model. Scoring runs on TypeSafe's Jev, a decision model that returns calibrated probabilities instead of text, in one parallel pass over all your skills.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for agent context and memory