Building CLI Tools for AI Agents

When to Use

Use this skill when:

• Designing a new CLI tool that AI agents will invoke
• Adapting an existing CLI to be agent-friendly
• Reviewing a CLI for agent compatibility issues
• Adding commands or subcommands to an agent-facing CLI

Core Principle

Agents are not humans. They cannot see colors, navigate interactive menus, interpret spinner animations, or respond to TTY prompts. A CLI built for agents must communicate entirely through structured text on stdout, clear error messages on stderr, and meaningful exit codes. If an agent can't parse your output or recover from your errors in one retry, your CLI has failed.

Design Rules

1. No TTY Assumed — Ever