Claude Code mod

claude-jev

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.

27 starsGit & GitHub modsFails validation Source

Install

From source
git clone https://github.com/0x7067/claude-jev.git
claude --plugin-dir ./claude-jev/.

The repo has no marketplace file, so load the plugin folder directly with --plugin-dir.

What it can access

Reach
L2Writes or runs: runs processes, changes config, reads settings, persists state, draws
Sees
compaction
Draws in
Pane
Hooks
session.startcommand.runconfig.describeui.closeui.rendersession.compact

From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.

How Claude Code mods work

  • A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
  • It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
  • Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
  • Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Claude Code docs

Details

Folder
.
Author
0x7067
License
MIT
Last updated
17 October 2026

FAQ

What is claude-jev?

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. It is a mod for Claude Code, from 0x7067/claude-jev on GitHub.

What can the claude-jev mod access?

Its widest reach is "writes or runs" (runs processes, changes config, reads settings, persists state, draws). It sees compaction. It draws in Pane. Like any mod, it runs with your permissions.

How do I install claude-jev?

Clone 0x7067/claude-jev and start Claude Code with --plugin-dir pointing at the mod's folder (.).

Is claude-jev popular?

0x7067/claude-jev has 27 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 17 October 2026.

More git & github mods

Browse the most popular Claude Code mods, all git & github mods, or the skills and MCP server directories.