CLI Development

CLI Development

Build CLIs that stay actionable in both success and failure paths.

Core Principles

1. Avoid dead ends.
   • Print next steps when a reasonable next action exists.
   • On terminal completion, state that no further action is required.
2. Make failures diagnosable.
   • Print known state, failed operation, and likely cause.
   • Include recovery commands and focused help text.
   • Include usage text for argument or syntax errors.
3. Keep output minimal and context-efficient.
   • Use short defaults.
   • Show detail only when requested by flags or when needed to recover from failure.
4. Scope help to subcommands.
   • Keep root help high-level.
   • Put detailed flags, examples, and edge cases in subcommand help.

Command Contract

1. Keep output deterministic.
   • Use stable wording and field names.
   • Avoid random ordering in lists.
2. Use conventional stream behavior.
   • Write primary result data to stdout.
   • Write diagnostics, warnings, and human-oriented guidance to stderr.
   • In machine mode (--json), print a complete structured success or error object to stdout.
   • Document that automation should capture both stdout and stderr for full logs.
3. Return meaningful exit codes.
   • 0 for success.
   • Non-zero codes map to clear failure classes.
4. Support automation.
   • Add machine-readable output mode such as --json.
   • Keep human-readable output as the default.
5. Support safe execution.
   • Add --dry-run for mutating commands.
   • Make retry behavior explicit.