jev
by Savino Fiore · ★ 4 · updated 2 days ago
0
Three-level decision layer on TypeSafe's Jev: picks model and effort per session and per subagent, compacts context without rewriting it, and gates code review with calibrated closed questions. Pairs with lexi: the review runs after the last GREEN.
Install
/plugin marketplace add savinofiore/lexi/plugin install jev@lexiThen run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.
What it hooks into
From an automated scan with claude plugin validate, not a security review. Mods run with your permissions; read the code before installing.
- Events
session.startsession.endprompt.submitturn.stepagent.spawnsession.compact- API calls
$.clock.after$.clock.now$.clock.sleep$.env.get$.fs.read$.http.fetch$.ui.log$.ui.status$.ui.toast- Can see
every promptsubagent spawnscompaction- Reach
- level 3 of 3 networkreads filesreads env varsdraws
Origin
- How it got here
- Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
- Repository
- github.com/savinofiore/lexi
- Path in repo
jev- Author
- Savino Fiore @savinofiore
- License
- MIT
- First published
- Last pushed
- First listed here
Name and description come from the mod's own manifest. We link to the code; we don't host it, and it stays under its author's license.