CalibratedDecisions.

Repo · Safety & guardrails

jev-hook-guard

Standard-library Python module and example hook implementing the checks a Claude Code hook should run before sending session text to TypeSafe Jev or…

Open github.com ↗

From the repository

What a Claude Code hook must do before it sends text to an external judgment API: mask secrets and personal data, refuse secret dumps, honour exclusion words and session pins, post safely, never block the session. Python, stdlib only.

How builders describe it

Standard-library Python module and example hook implementing the checks a Claude Code hook should run before sending session text to TypeSafe Jev or another HTTP judge: kill switch, exclusion words with session pins, refusal of secret dumps, masking of keys and personal data, length cut, leftover…

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