CalibratedDecisions.

Repo · Coding & code review

jev-auto-approve

Claude Code hook: TypeSafe Jev auto-approves read-only shell commands in milliseconds; everything else still prompts you (fail-open)

Open github.com ↗

From the repository

Claude Code hook that auto-approves safe, read-only shell commands in milliseconds using Jev (TypeSafe). Fewer permission prompts; everything else still asks you.

agent-safetyai-agentai-agentsanthropicclaudeclaude-aiclaude-codeclaude-code-hooksdeveloper-toolshooksjevpermissionspretooluse-hookpythontypesafe

How builders describe it

Claude Code PreToolUse hook that asks Jev one Noul on whether a Bash command is strictly read-only and auto-approves at p of 0.95 or higher. It can only allow or stay silent, never deny, so unknown or risky commands fall back to Claude Code's normal permission prompt.

The decision Jev makes

Label a change, score its risk, pick the relevant file, or decide whether a coding agent should continue.

Where it fits

Code review and coding agents are full of small questions: is this change risky, what kind of fix is this, which file matters. These projects answer them with Jev and route the rest to people or bigger models. All 450 coding & code review projects →

Related projects