safety-compliance
Circuit breakers, kill switches, approval guards, and safety mechanisms for production agent systems.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for safety-compliance, derived from its capabilities.
AIVSS 6.2 · Medium
View MAESTRO 7-layer threat model →Overview
A Claude Code plugin providing safety primitives for production agentic systems: circuit breakers, kill switches, approval guards, and compliance checks. These are implemented as hooks that gate agent actions before they execute, so the plugin sits directly on the trust boundary. Ships agents and commands for enforcing approval gates.
Key features
- Kill switches and circuit breakers
- Approval guards on agent actions
- Production safety mechanisms
Use cases
- Gate risky agent actions behind approval
- Add fail-safes to autonomous agent runs