agent-governance-patternslisted

# Agent Governance Patterns Patterns for adding safety, trust, and deterministic policy enforcement to tool-using and multi-agent AI systems. ## Overview Governance patterns ensure AI agents operate within defined boundaries — controlling which tools they can call, what content they can process, how much they can do, and maintaining accountability through audit trails. Use this skill to design or implement controls; use a compliance-focused skill when the task is to score an existing system against a formal standard. ``` User Request → Intent Classification → Policy Check → Tool Execution → Audit Log ↓ ↓ ↓ Threat Detection Allow/Deny Trust Update ``` ## Use This Skill When - **Agents with tool access**: Any agent that calls external tools (APIs, databases, shell commands) - **Multi-agent systems**: Agents delegating to other agents need trust boundaries - **Production deployments**: Compliance, audit, and safety requirements - **Sensitive operations**: Financial transactions, data access, infrastructure management - **Policy enforcement**: Tool allowlists, blocklists, approval gates, rate limits, or content filters are needed - **Operational accountability**: Tool calls need structured audit trails, denial reasons, or replayable records ## Do Not Use This Skill For - General security reviews where agent governance is not the focus - OWASP ASI compliance scoring or gap reporting - Supply