agent-dx-cli-scale

Evaluate CLI designs against agent-first design principles using a structured, axis-based scoring rubric. It scores seven axes from 0–3 to produce a total between 0–21, highlighting gaps in agent-readiness for architecture validation.

Score CLI agent-readiness across seven axes: machine-readable output, raw input, schema introspection, context discipline, input hardening, safety rails, and agent knowledge packaging. Each axis is rated 0–3 for both mutating and read operations.

Yes, you can apply this CLI scoring framework to risk assessments, design sprints, product reviews, and architecture validation. It provides consistent axis-based scores that guide design improvements to support agent orchestration.

The best way to score CLI designs for AI agents consistently is to apply a deterministic scoring rubric. Score each of the seven axes from 0–3 and sum them for a total score between 0–21 to evaluate agent-readiness.

No, CLI agent-readiness scoring requires no external dependencies. It operates as a standalone framework that evaluates CLI designs against agent-first principles using a YAML frontmatter format and a descriptive context body.

You should avoid using an axis-based CLI scoring rubric when evaluating non-CLI interfaces or systems outside AI agent orchestration contexts, as the seven evaluated axes specifically target command-line design hardening for agent interaction.