safety commands

dreadnode/agent-lens

Command Claude Code

The user wants to create a harness experiment config to test a hypothesis about agent behavior. Your job is to design the experiment, write a config, run it, and analyze the results.

XiaoYiWeio/deepsafe-scan

Command

Before publishing, run the compatibility bootstrap.

Myr-Aya/GouvernAI-claude-code-plugin

Command

Show guardrails status, switch modes, set token cap, or view the audit log. Usage: /guardrails [status|log|strict|relaxed|audit|reset|policy|tokencap].