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

jev-architect

Agent skill that guides you in finding, designing and testing Jev decision loops, including when to keep logic in code.

Agent skillbetaMIT
View on GitHub ↗Live demo ↗

Overview

Jev Architect is an agent skill that helps decide what to build with Jev, where it could improve existing software, and what to test before committing. You bring a problem, an idea or a codebase, and the skill guides the coding agent: it explains concepts at your level, clarifies users, problem and constraints before proposing ideas, and for a concrete design works out the context Jev needs, the question to ask, and what code should do when the answer is uncertain or the request fails.

It explicitly allows the answer to be keep it in code, such as a free-shipping rule based on cart total, which needs an exact comparison rather than a model call. Its recommended next step is a small experiment with a baseline and a stopping criterion, and it treats suggested designs as hypotheses rather than evidence of speed, savings or accuracy. It uses the portable Agent Skills layout, installs with npx skills add or as a Claude Code plugin, has an examples site, and is MIT licensed.

What the decision model decides

TypeQuestionAnswers
OtherHelps decide whether a step should use Jev, and what Choice, Score or Noul question to ask(inferred)—

How it works

  1. Bring an idea, problem or codebase to the agent
  2. Skill clarifies users, problem and constraints
  3. Design the context, question and uncertainty handling
  4. Plan a small experiment with a baseline and stop condition

Strengths

  • Encourages experiments and baselines before adoption
  • Will recommend plain code when appropriate
  • Portable across agents

Caveats

  • Produces designs and plans, not working code by itself

Getting started

`npx skills add karanb192/jev-architect --skill jev-architect`, or `claude plugin marketplace add karanb192/jev-architect` then `claude plugin install jev-architect@jev-architect-marketplace`.

At a glance

Type
Agent skill
Status
beta
Runtime
agent skill, Claude Code plugin
Has code
yes
License
MIT

Use cases and integrations

How curated lists describe it

  • Design skill: finds, designs, and evaluates Jev decision loops, packaged as a skill with references on decision design and delivery.

    yibie/awesome-jev

  • Find, design, and evaluate TypeSafe Jev decision loops.

    hellogumbo/awesome-jev

Frequently asked questions

What does Jev Architect do?

Guides a coding agent through finding, designing and testing uses of Jev.

Will it always recommend Jev?

No, it may recommend keeping logic in code.

Are its designs proven?

No, the README calls them hypotheses to test.

Related projects

  • Building with Jev★ 155

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

    Agent skillproduction
  • jev-agent-toolkit

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

    MCP serverbetaTypeScript
  • 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