Agent-Friendly CLI Spec v0.1
When building or modifying CLI tools, follow these rules to make them safe and reliable for AI agents to use.
Core Philosophy
- Agent-only -- output is always JSON, no human-friendly mode
- Agent is untrusted -- validate all input at the same level as a public API
- Fail-Closed -- when validation logic itself errors, deny by default
- Verifiable -- every rule is written so it can be automatically checked
Layer Model
This spec now uses
[Description truncada. Veja o README completo no GitHub.]