Agent Plugins Marketplace
← All plugins

claude-jev

v0.16.1

Hands the small judgments in a session to TypeSafe's Jev, a System One model that returns typed answers instead of generating text: what kind of request each prompt is, which model tier a subagent needs, whether an edit breaks a rule already written in your CLAUDE.md or AGENTS.md, and which transcript blocks survive compaction. Kept blocks carry over verbatim — no LLM writes a summary.

Claude Code2 Skills

By 0x7067License: MIT7 GitHub starsUpdated yesterday

Directory evidence

Runtimes
Claude Code
Parsed components
2 skill or MCP entries
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 claude-jev 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 claude-jev@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/0x7067/claude-jev

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

Plugin files

claude-jev/
├── .claude-plugin/plugin.json
├── skills/jev/SKILL.md
└── skills/stats/SKILL.md

Included Skills2

jevskills/jev/SKILL.md

Offload a snap decision to TypeSafe's Jev, a System One model that returns a typed answer with a probability in ~100–500 ms. Use when picking among a known set of options (which tool, which file, which approach), answering a yes/no check (is this done, is this ambiguous, is this safe to run), or rating something on a rubric (complexity, risk, quality). Do not use it to generate text, code, or plans — Jev returns values, not prose.

statsskills/stats/SKILL.md

Score the prompt router's live decisions against what the sessions actually did, from the hook's decision log. Use when the user asks how the router is performing, whether the hints are right, or runs /claude-jev:stats. This reports on past decisions; it does not classify anything new.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "claude-jev",
  "version": "0.16.1",
  "description": "Hands the small judgments in a session to TypeSafe's Jev, a System One model that returns typed answers instead of generating text: what kind of request each prompt is, which model tier a subagent needs, whether an edit breaks a rule already written in your CLAUDE.md or AGENTS.md, and which transcript blocks survive compaction. Kept blocks carry over verbatim — no LLM writes a summary.",
  "author": {
    "name": "0x7067"
  },
  "keywords": [
    "typesafe",
    "jev",
    "system-one",
    "routing",
    "intent",
    "rules",
    "compaction",
    "token-savings"
  ],
  "license": "MIT"
}

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.

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