jev-belay

Name: jev-belay
Availability: InStock
Author: valentynkit

A Claude Code Stop hook that reads the turn transcript locally and calls Jev only when files changed and no check has passed, blocking an unverified “done”.

High Quality

New

Join 0+ developers using this skill

command

AI & Machine Learning

intermediate

0 installs

4/5 quality

View Source

Last updated: September 23, 2026

AI Skill Market Insights

Real data. Real impact.

Popularity

Rising

Emerging

Active Users

Developers

Quick Start

Install Command

git clone https://github.com/valentynkit/jev-belay.git

TEAR & SHARE

2-3hrs/WK

RISING

0.0K+ USING

jev-belay

A Claude Code Stop hook that reads the turn transcript locally and calls Jev only when files changed and no check has passed, blocking an unverified “done”.

Where Jev makes the decision

Four questions: whether the closing message claims done, claims checks passed, whether verification applies, and a complete / partial / blocked / other choice.

Why it matters

Skips the model when a check already passed; every error path lets the turn end.

Claims & evidence

Author and repository text is preserved where clear; missing languages are enriched automatically. Checks establish source-level Jev integration, not runtime, safety, or performance validation.

About Jev

Jev is TypeSafe AI's System One decision model: it returns typed scores and choices (not free text), so agents can route, filter and gate at low latency and cost.

Source: valentynkit/jev-belay — 18 stars, MIT. Listed by Awesome Jev.

jev-belay

AI Skill Market Insights

Quick Start

Install Command

TEAR & SHARE

Tags

Multi-Agent Patterns

Be Part of the 0+ Developer Community

jev-belay

Where Jev makes the decision

Why it matters

Claims & evidence

About Jev

License

Memory Systems Design

Context Degradation Detection

brainstorming

writing-skills

Channels

Learn

Compare

Company

Agents