jev-auto-compact

Not yet reviewed

Jev-powered verbatim compaction: once context reaches 60%, prunes stale tool calls with zero generation. Skips (never falls back to the LLM summarizer) when…

Source

github.com/notque/vexjoy-agent/tree/main/plugins/jev-auto-compact

Made by

vexjoy-agent

Pinned commit

No commit pinned yet

Review notes

Listed from the community catalogue awesome-claude-code-mods (https://github.com/karanb192/awesome-claude-code-mods) on 2026-10-06. Not reviewed by modsforClaude.com yet: the hooked events and what it uses come from that catalogue's automated scan of the source.

What a scan found

Calls the model (uses tokens)
Sends data over the network
Stores data
Shows something on screen

Reported by an automated scan of the source, not checked by a person yet.

Hooked events

None listed

How to install

This mod is not in the official Claude directory, so you load it straight from its source on GitHub. modsforClaude.com is an unofficial community site: we do not host, repackage or install anything. Read the source and the review on this page first.

In the terminal

Clone the repository and start Claude Code with the mod. It stays loaded for that session.

git clone https://github.com/notque/vexjoy-agent
claude --plugin-dir ./vexjoy-agent/plugins/jev-auto-compact

In the desktop app

Clone the repository into a folder you keep:

git clone https://github.com/notque/vexjoy-agent ~/claude-mods/vexjoy-agent

Add that folder to CLAUDE_CODE_PLUGIN_DIRS in the env block of ~/.claude/settings.json, then start a new session in the Code tab. On Windows, with your own user name:

"env": {
  "CLAUDE_CODE_PLUGIN_DIRS": "C:\\Users\\you\\claude-mods\\vexjoy-agent\\plugins\\jev-auto-compact"
}

On macOS and Linux:

"env": {
  "CLAUDE_CODE_PLUGIN_DIRS": "~/claude-mods/vexjoy-agent/plugins/jev-auto-compact"
}

Already loading other mods this way? Add the folder to the same value, separated by ; on Windows or : on macOS and Linux.

Not working, or want to change its settings? How to load a Claude Code mod walks through every step.

Jev-powered verbatim compaction: once context reaches 60%, prunes stale tool calls with zero generation. Skips (never falls back to the LLM summarizer) when nothing is prunable; records evidence for learning.db.