CalibratedDecisions.

Repo · Safety & guardrails

jev-secret-guard

Claude Code hook: block known secret formats locally; send masked unknowns to TypeSafe Jev so checks never leak the secret.

Open github.com ↗

From the repository

Claude Code hook that blocks secrets, passwords and API keys before your AI agent writes, commits or sends them. Known keys caught locally; unknown ones judged by Jev (TypeSafe), masked.

agent-safetyai-agentai-agentsanthropicapi-keysclaudeclaude-aiclaude-codeclaude-code-hookshooksjevpythonsecret-scanningsecrets-detectionsecuritytypesafe

How builders describe it

A Claude Code PreToolUse hook that blocks known key formats locally and sends only masked unknown high-entropy strings to Jev for a Noul judgment, blocking at 0.80 and asking the human from 0.30 or whenever Jev is unavailable.

The decision Jev makes

Allow, flag or escalate a message, tool call or action.

Where it fits

Screening messages, tool calls and outputs before they cause trouble. Jev gives a fast, calibrated verdict that can sit in front of every request or agent action. All 229 safety & guardrails projects →

Related projects