Agent Plugins Marketplace
← All plugins

jev-use

v0.7.1

Hands the agent steps that need no text output to Jev, TypeSafe's judgment model: typed yes/no, pick-one and score questions about one state answered in a single batched call, with typed escalation back to the LLM for anything it cannot or should not decide.

Codex1 MCP serverstdio

By shitianfangLicense: MIT1.1k GitHub starsUpdated 2 days ago

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-use for Codex

Installs for the current user
codex plugin marketplace add hashgraph-online/awesome-codex-plugins
codex plugin marketplace upgrade awesome-codex-plugins
codex plugin add jev-use@awesome-codex-plugins

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

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

  • Codex: jev-use@agent-plugin-marketplace → jev-use@awesome-codex-plugins

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/hashgraph-online/awesome-codex-plugins

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

Plugin files

plugins/shitianfang/jev-use/
├── .codex-plugin/plugin.json
└── .mcp.json

MCP servers1

jevstdio
command
npx
args
-y [email protected] serve

Plugin manifests1

plugins/shitianfang/jev-use/.codex-plugin/plugin.json
{
  "name": "jev-use",
  "version": "0.7.1",
  "description": "Hands the agent steps that need no text output to Jev, TypeSafe's judgment model: typed yes/no, pick-one and score questions about one state answered in a single batched call, with typed escalation back to the LLM for anything it cannot or should not decide.",
  "repository": "https://github.com/shitianfang/jev-use",
  "license": "MIT",
  "interface": {
    "displayName": "jev-use",
    "shortDescription": "Route the no-text-output steps to a judgment model",
    "composerIcon": "./assets/icon.svg"
  },
  "author": {
    "name": "shitianfang",
    "url": "https://github.com/shitianfang"
  },
  "homepage": "https://github.com/shitianfang/jev-use",
  "keywords": [
    "jev",
    "typesafe-ai",
    "judgment",
    "router",
    "codex",
    "mcp"
  ],
  "mcpServers": {
    "jev": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]",
        "serve"
      ]
    }
  }
}

For maintainers

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

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