nozomi-koborinai/jev-spec

jev-spec: catch spec drift on every commit — Image from github.com

nozomi-koborinai/jev-spec on GitHub

Stars: 6
Forks: 1
Language: TypeScript
License: MIT
Last push: 21 Sep 2026

Read from GitHub on 24 Sep 2026. Counts change daily.

How it uses Jev

const MET = { minProbability: 0.85 } as const;
const NOT_VIOLATED = { maxProbability: 0.3 } as const;

export default defineConfig({
  client: { model: 'jev-1.13.0' },
  targets: {
    exitCodes: {
      description: 'Exit codes of the check command',
      specPath: 'docs/specs/exit-codes.md',
      codePaths: ['bin/jev-spec.js', 'src/cli/main.ts', 'src/cli/commands/check.ts'],
      rubrics: {
        'REQ-EXIT-01': noul(
          'When every target that was checked passes, does the check command return exit code 0?'
        ),
        'REQ-EXIT-02': noul(

View in jev-spec.config.ts

Open on GitHub

Use casesCompliance verification

leepokai/jev-guard

Security hook for coding agents that risk-scores every tool call with session context (deny/ask/allow), flags prompt injection in tool results and checks skills and plugins. Supports Claude Code, Codex, Copilot, Gemini, Cursor, pi, OpenCode and ACP.

leepokai30 starsOpen

ToolLLM guardrails+3

ShuhanSun/jev-oas-sentinel

Checks an OpenAPI spec for breaking changes hidden in its prose, combining deterministic schema checks with Jev's semantic review.

ShuhanSun4 starsOpen

ToolCompliance verification

russfranky/jev-crawlers

Learns a repository's decision norms from its history, then uses Jev to adversarially judge past decisions against those norms, through five Unix-style primitives: seed, expand, judge, verify, report.

russfranky1 starsOpen

ToolCompliance verification

fatwang2/jev-review-action

A configurable GitHub Action that reviews directory submissions and classifies pull requests using only Jev: typed yes/no checks plus one category choice, with code applying the policy and posting one PR comment.

fatwang21 starsOpen

ToolCompliance verification

CryptoOda/typesafe-guard

LLM-agnostic guardrails library using Jev to detect prompt injection, jailbreak attempts, PII exposure and credential leaks in one batched request. Not published to PyPI at time of check.