Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

claude-jev-mod

Claude Code mod that adds $.jev to the engine interface so other plugins and hooks can ask Jev typed questions through six providers.

ServicebetaMIT
View on GitHub ↗

Overview

This Claude Code mod (a plugin whose behaviour is a hooks module) adds $.jev to Claude Code's engine interface. Any plugin seated above it can ask Jev a map of Choice, Score and Noul questions over one state and read calibrated probabilities back, for example asking whether a shell command deletes files that cannot be reproduced and denying it above 0.9.

Because Jev only returns values from the declared answer space, the decision is typed, cheap and fast enough to sit inside a hook. The mod speaks six providers (including OpenRouter, Vercel AI Gateway, Cloudflare Workers AI, LiteLLM and the TypeSafe API) and picks one from your environment. It requires Claude Code v2.1.287 or later.

What the decision model decides

TypeQuestionAnswers
Yes / noThe command deletes files that could not be reproduced.true · false

How it works

  1. Install the mod
  2. Another plugin calls $.jev.ask with state and questions
  3. Mod routes the request to an available provider
  4. Plugin acts on the probabilities (e.g. deny above 0.9)

Strengths

  • Shared Jev access for all plugins
  • Works with whichever provider key you have
  • Typed answers suitable for hooks

Caveats

  • Requires Claude Code v2.1.287+
  • A building block, not an end-user feature

Getting started

/plugin marketplace add chrishan17/claude-jev-mod then /plugin install jev@jev-mod

At a glance

Type
Service
Status
beta
Language
TypeScript
Runtime
Claude Code mod (hooks module)
Has code
yes
License
MIT

Use cases and integrations

How curated lists describe it

  • Typed decisions in Claude Code: adds $.jev over TypeSafe's Jev, through OpenRouter, Vercel AI Gateway, Cloudflare Workers AI, LiteLLM or the TypeSafe API.

    logicrw/awesome-jev-projects

Frequently asked questions

What is a mod?

A Claude Code plugin whose behaviour is a hooks module; this one exposes $.jev.

Which providers are supported?

Six, including OpenRouter, Vercel AI Gateway, Cloudflare Workers AI, LiteLLM and TypeSafe.

Which Claude Code version?

v2.1.287 or later.

Related projects

  • decision-circuits★ 1

    Zero-dependency Python SDK for deterministic gates over calibrated model answers, with LangChain, OpenAI and Claude agent hooks.

    LibrarybetaPython
  • TanStack AI

    Provider-agnostic TypeScript AI SDK; per list sources, an @tanstack/ai-typesafe adapter exposes Jev decisions through decide().

    ServiceproductionTypeScript
  • typesafe-jev-bridge

    Zero-dependency Node bridge that exposes Jev through an OpenAI-compatible API, plus a CLI, code-audit tool and auto-fix loop.

    CLIbetaJavaScript
  • Ax

    Ax, a DSPy-style multi-language LLM framework, listed with a native TypeSafe provider for Boolean, Choice, Score and raw Jev questions.

    PluginproductionTypeScript
  • Composio

    Composio agent SDK with an optional TypeSafe provider that uses Jev to shortlist and pick tools and closed-set arguments.

    ProjectproductionTypeScript
  • Effect

    Effect TypeScript library whose @effect/ai-typesafe package maps classify, probability and rating operations to Jev questions.

    ProjectproductionTypeScript