anth-policy-guardrails - Anthropic Policy Guardrails
Implement content policy guardrails, input/output validation, and usage governance for Claude API integrations.
Tags
Updated: 2026-09-19Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Validate API inputs
- Filter sensitive output content
- Enforce cost limits
- Enforce model access policies
- Canary test policy changes
Inputs
- User inputs and prompts
- Guardrail configurations
- Requested models and user tiers
Outputs
- Guardrail receipts
- Validated responses or denial messages
Requirements
- Claude Code environment
- Secret manager for API keys
- Approved policy and allowlists