# The agent-native CLI standard

> CLI tools are how AI agents touch everything else. Compilers, databases, git, the cloud, the shell. An agent asked to ship code, rotate a credential, grep a log, or deploy a branch does not call a SaaS API — it shells out to a binary, reads the output, decides what went right or wrong, and picks the next move. There is no human between the request and the process. The CLI either makes that loop tractable or it does not.

## Principles

- [P1: Non-Interactive by Default](https://agentnative.dev/p1.md)
- [P2: Structured, Parseable Output](https://agentnative.dev/p2.md)
- [P3: Progressive Help Discovery](https://agentnative.dev/p3.md)
- [P4: Fail Fast with Actionable Errors](https://agentnative.dev/p4.md)
- [P5: Safe Retries and Explicit Mutation Boundaries](https://agentnative.dev/p5.md)
- [P6: Composable and Predictable Command Structure](https://agentnative.dev/p6.md)
- [P7: Bounded, High-Signal Responses](https://agentnative.dev/p7.md)

## Pages

- [Check your CLI](https://agentnative.dev/check.md)
- [About this standard](https://agentnative.dev/about.md)