Guard

Before you ship an agent workflow to production, this skill helps you add the safety rails you'll actually need: input validation, PII filtering, cost budgets, and permission checks. It walks through threat assessment (prompt injection, data leakage, cost explosion), then gives you concrete guard patterns for inputs, outputs, costs, and permissions. The checklist is practical: validate everything, scan for sensitive data, set spending limits, require confirmation for destructive actions. If you're deploying anything that touches real data or makes real API calls, you want these guardrails in place before things go sideways.