jev-belay GitHub avatar by valentynkit

valentynkit /

Decision Tools

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”.

License: MITLanguage: TypeScriptLast push: 9/19/2026#typed-decisions#classification-ranking

What Jev Does in this Architecture

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

Key Architecture Benefit

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

Review & Benchmark Note: 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.
Clone Repository
git clone https://github.com/valentynkit/jev-belay.git

Inspect on GitHub

Check out the upstream repository README, issues, and commit log.

valentynkit/jev-belay

Architecture Category

Decision Tools

Standalone decision helpers, schema validators, probability decoders, and utilities.

View all in this category →

Related Projects in Decision Tools

jev-playground repository icon by Little-Planet-Labs

Little-Planet-Labs

jev-playground

1
Decision ToolsMITTypeScript

A web playground for entering state and decision questions, then inspecting Jev answers and probability distributions.

What Jev does here

Submits multiple Noul, Choice, and Score questions in one request.

Lets users try questions and answer options before writing application code.

#typed-decisions#evaluation-benchmarks
2 evidence links
Inspect details
jev-predict-skill repository icon by DanielKillenberger

DanielKillenberger

jev-predict-skill

1
Decision ToolsMITHTML

An Agent skill recipe that predicts another skill’s closed-set outcome from its rules and evidence.

What Jev does here

Jev first assesses whether a closed decision is possible, then selects among the target skill’s outcomes.

Includes API-call and response-check examples; it predicts the outcome without executing the target skill.

#mcp-integrations#typed-decisions
2 evidence links
Inspect details
jevify repository icon by altryne

altryne

jevify

3
Decision ToolsMITPython

An Agent Skill for finding suitable Jev decision points and designing questions and comparison experiments.

What Jev does here

Designs Noul, Choice, and Score question packs for an application, with a script for API-backed case runs.

Connects integration ideas, question design, and evaluation methods.

#mcp-integrations#evaluation-benchmarks#typed-decisions
2 evidence links
Inspect details