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

Building with Jev

Agent skill for writing and improving programs that call Jev: question design, state structure, thresholds and diagnosing wrong answers.

Agent skillproduction
View on GitHub ↗

Overview

Building with Jev by Drew Breunig is an agent skill for writing and improving programs that call Jev. It covers question design for Choice, Score and Noul, state structure, composing answers in code, confidence thresholds, and diagnosing questions that answer wrongly or with low confidence. It targets jev-1.13 and draws on the TypeSafe docs, listing the specific pages in SKILL.md.

It installs as a Claude Code plugin, through the skills CLI for Claude Code, Codex, Cursor and other agents, or manually. Claude loads it automatically when a task involves Jev, or via /jev.

What the decision model decides

TypeQuestionAnswers
OtherHow should a decision be phrased and thresholded as Jev questions?(inferred)—

How it works

  1. Install the skill
  2. Agent loads it when working on Jev code
  3. Agent designs questions and state per the guidance
  4. Agent diagnoses low-confidence or wrong answers

Strengths

  • Focused, documented guidance
  • Works across several agents

Caveats

  • Targets jev-1.13; may need updates

Getting started

npx skills add dbreunig/building-with-jev-skill (or /plugin marketplace add dbreunig/building-with-jev-skill then /plugin install jev@building-with-jev)

At a glance

Type
Agent skill
Status
production
Runtime
agent skill
Has code
yes
Stars
155

Use cases and integrations

How curated lists describe it

  • A skill for writing and improving programs that call Jev, TypeSafe's System One model

    wh000wh000/awesome-jev-live

  • Community agent skill covering question design, state preparation, confidence thresholds, and debugging decisions.

    cobanov/awesome-jev

  • A skill for writing and improving programs that call Jev, TypeSafe's System One model.

    hellogumbo/awesome-jev

  • Agent skill for writing programs that call Jev: question design, state structure, confidence thresholds, and diagnosing wrong answers.

    MrJev/awesome-jev

Frequently asked questions

What does the skill cover?

Question design, state structure, thresholds and debugging.

Which model version?

jev-1.13.

How do I invoke it?

It loads automatically, or use /jev.

Related projects

  • jev-agent-toolkit

    Portable Agent Skill teaching coding agents to use Jev as a bounded judgment layer, plus an optional MCP bridge.

    MCP serverbetaTypeScript
  • Building with TypeSafe Jev

    Unofficial skill teaching coding agents to design for Jev, with code sketches per pattern, links to 150+ projects and an eval harness.

    Pluginproduction
  • jev-anything

    Independent agent skill that makes a coding agent design, build, test and tune a bounded Jev decision layer with a contract first.

    Agent skillbeta
  • jev-mode (tiffygk)

    Claude Code and Codex skills plus a study course for building with Jev, including Jevaluate, which rates how well projects use Jev.

    Projectbeta
  • jev-skill (marcodicesare-dev)

    Community Jev skill for Claude Code and Codex: a guide, a dependency-free Python CLI and 5 measured question sets.

    Agent skillbetaPython
  • jev-system-architect

    Agent skill that finds fuzzy semantic judgments in a codebase and redesigns them as small Jev Choice, Score or Noul primitives.

    Agent skillbeta