agent-sentinel

Purpose

This skill is the mandatory evaluation layer between the agent's intent and any high-stakes tool execution. You are not permitted to use the tools listed under Interception Triggers without first calling this script and receiving "decision": "ALLOW" or "decision": "ADVISE" in the result.

Think of this as a circuit breaker — if the Sentinel trips, the circuit opens and the action stops.

Interception Triggers

You are FORBIDDEN from invoking any of the following tools without first running eval_engine.py and parsing its response.