Agent Plugins Marketplace
← All plugins

jev-auto-mode

v0.1.0

A permission layer driven by a JSON policy: allow, ask or deny every tool call (Bash, edits, web, MCP, subagents, skills), every slash command or skill you type, and every skill preloaded into a subagent. Rules decide first (deny > ask > allow, compound Bash commands split); what no rule covers can go to TypeSafe's Jev, which judges the action against your latest request with thresholds you set. Claude can never edit the policy. Needs function hooks (early access).

Claude Code

By claude-code-templatesLicense: MIT31.8k GitHub starsUpdated 3 hours ago

Directory evidence

Runtimes
Claude Code
Parsed components
0 skill or MCP entries
Source updated
Sep 26, 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-auto-mode for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install jev-auto-mode@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

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/davila7/claude-code-templates

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is cli-tool/components/mods/security/jev-auto-mode/.

Plugin files

cli-tool/components/mods/security/jev-auto-mode/
└── .claude-plugin/plugin.json

Plugin manifests1

cli-tool/components/mods/security/jev-auto-mode/.claude-plugin/plugin.json
{
  "name": "jev-auto-mode",
  "version": "0.1.0",
  "description": "A permission layer driven by a JSON policy: allow, ask or deny every tool call (Bash, edits, web, MCP, subagents, skills), every slash command or skill you type, and every skill preloaded into a subagent. Rules decide first (deny > ask > allow, compound Bash commands split); what no rule covers can go to TypeSafe's Jev, which judges the action against your latest request with thresholds you set. Claude can never edit the policy. Needs function hooks (early access).",
  "author": {
    "name": "claude-code-templates",
    "url": "https://www.aitmpl.com"
  },
  "repository": "https://github.com/davila7/claude-code-templates",
  "license": "MIT",
  "keywords": [
    "mod",
    "function-hooks",
    "security",
    "permissions",
    "auto-mode",
    "jev",
    "typesafe",
    "policy"
  ],
  "userConfig": {
    "configFile": {
      "type": "file",
      "title": "Policy file",
      "description": "Your policy JSON; empty uses ~/.claude/jev-auto-mode.json. The project's .claude/jev-auto-mode.json is merged on top and can only tighten it."
    },
    "typesafeApiKey": {
      "type": "string",
      "title": "TypeSafe API key",
      "description": "Key for api.typesafe.ai, the judge for actions no rule covers (calibrated probabilities). Empty: the Gateway key, else the built-in classifier.",
      "sensitive": true,
      "default": ""
    },
    "gatewayApiKey": {
      "type": "string",
      "title": "Vercel AI Gateway key",
      "description": "Reaches Jev through ai-gateway.vercel.sh when no TypeSafe key is set.",
      "sensitive": true,
      "default": ""
    },
    "provider": {
      "type": "string",
      "title": "Judge backend",
      "description": "auto (TypeSafe, then Gateway, then built-in), typesafe, gateway or builtin",
      "default": "auto"
    },
    "typesafeBaseUrl": {
      "type": "string",
      "title": "TypeSafe base URL",
      "description": "Empty uses https://api.typesafe.ai",
      "default": ""
    },
    "typesafeModel": {
      "type": "string",
      "title": "TypeSafe model",
      "description": "Empty uses jev-latest",
      "default": ""
    },
    "gatewayBaseUrl": {
      "type": "string",
      "title": "Gateway base URL",
      "description": "Empty uses https://ai-gateway.vercel.sh/v4/ai",
      "default": ""
    },
    "gatewayModel": {
      "type": "string",
      "title": "Gateway model",
      "description": "Empty uses typesafe-ai/jev",
      "default": ""
    },
    "logLevel": {
      "type": "string",
      "title": "Log level",
      "description": "blocked (asks and denies, the default), all (every decision) or off",
      "default": "blocked"
    }
  }
}

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