Agent Plugins Marketplace
All plugins

jev

v1.0.0+codex.b966ac2d4249

Consult Jev for bounded typed second opinions during agent work: compare plans, check claims against supplied evidence, prioritize investigations, and challenge conclusions. Uses Vercel AI Gateway by default with configurable providers; skips when the selected key is absent. Includes a standalone uv-run helper and offline contract tests.

Codex1 Skill

By Alberto LealLicense: MIT22 GitHub starsUpdated yesterday

Directory evidence

Runtimes
Codex
Parsed components
1 skill or MCP entry
Source updated
Sep 22, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology

Install jev for Codex

Installs for the current user
codex plugin marketplace add dashed/claude-marketplace
codex plugin marketplace upgrade alberto-marketplace
codex plugin add jev@alberto-marketplace

Paste and run these commands in a terminal with Codex. They add and refresh the alberto-marketplace catalog, then install this plugin.

Compatibility: the page URL and API slug “jev-2” remain stable.

  • Codex: jev-2@agent-plugin-marketplacejev@alberto-marketplace

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/dashed/claude-marketplace

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/jev/.

Plugin files

plugins/jev/
├── .codex-plugin/plugin.json
└── skills/jev/SKILL.md

Included Skills1

jevskills/jev/SKILL.md

Use Jev as a bounded second opinion during agent work. Use when asked to consult Jev, compare explicit plans or candidates, check claims against supplied evidence, prioritize follow-up work, or challenge a proposed conclusion with typed judgments. For building TypeSafe-powered applications, use the typesafe-ai skill instead.

Plugin manifests1

plugins/jev/.codex-plugin/plugin.json
{
  "name": "jev",
  "version": "1.0.0+codex.b966ac2d4249",
  "description": "Consult Jev for bounded typed second opinions during agent work: compare plans, check claims against supplied evidence, prioritize investigations, and challenge conclusions. Uses Vercel AI Gateway by default with configurable providers; skips when the selected key is absent. Includes a standalone uv-run helper and offline contract tests.",
  "author": {
    "name": "Alberto Leal"
  },
  "license": "MIT",
  "keywords": [
    "jev",
    "typesafe",
    "vercel-ai-gateway",
    "typed-judgments",
    "agent",
    "review",
    "evaluation"
  ],
  "interface": {
    "displayName": "Jev",
    "shortDescription": "Consult Jev for bounded typed second opinions during agent work: compare plans, check claims against supplied evidence, prioritize investigations, and challenge conclusions. Uses...",
    "longDescription": "Consult Jev for bounded typed second opinions during agent work: compare plans, check claims against supplied evidence, prioritize investigations, and challenge conclusions. Uses Vercel AI Gateway by default with configurable providers; skips when the selected key is absent. Includes a standalone uv-run helper and offline contract tests.",
    "developerName": "Alberto Leal",
    "category": "Productivity",
    "capabilities": [
      "Skills"
    ],
    "defaultPrompt": [
      "Use $jev for this task."
    ]
  },
  "repository": "https://github.com/dashed/claude-marketplace/tree/master/plugins/jev",
  "skills": "./skills/"
}

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[jev on Agent Plugins Marketplace](https://pluginsmp.com/plugins/jev-2)