Jev in production › Agent guardrails and approvals

jev-guard (muratcakmak)

Claude Code plugin that sends batched yes/no questions to Jev on each edit, shell command and finished answer, denying rule-breaking edits or unrequested deploys and nudging unsupported claims; it fails open when Jev is unreachable.

Open on GitHub ↗

The source publishes no measured number.
Use
Agent guardrails and approvals
Industry
Developer tools
Form
Open-source tool
Stage
Beta
Plugs into
Claude Code
Listed
2026-09-22
Found via
github
Repository
muratcakmak/jev-guard
Stars
7
Forks
0
Last push
2026-09-22
Language
TypeScript
License
MIT

The README opens with

A Claude Code plugin that scores what the model is about to do — and what it just claimed — with a probability model, and denies the call when the score is high enough.

Conventions written in CLAUDE.md are advice. The model follows them until the context gets long, then quietly stops. jev-guard moves the ones that matter out of the prompt and into hooks, where a broken rule is a denied tool call with the correction attached, not a review comment three days later.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for agent guardrails and approvals