agent-ready-rails

The key words MUST, MUST NOT, SHOULD, SHOULD NOT and MAY in this skill are to be interpreted as described in BCP 14 (RFC 2119, RFC 8174) when, and only when, they appear in all capitals.

A read-only audit of whether a codebase is ready for coding agents — and a scaffolder for the rails it is missing.

The thesis, from the best-documented production case (Spotify's Honk agent over ~20M lines; see references/grounding.md): a powerful agent in a weak engineering system creates faster chaos; the same agent in a disciplined system creates leverage. The differential is not model capability — it is the rails around the agent. This skill scores those rails and tells you which to build first.

Default mode is read-only: observe, score, report. It only writes files when explicitly asked to install rails (step 5).

Locating this skill's helpers (do this first). The steps below run bundled scripts. You execute from the target repo, not from this skill's directory, so a path written relative to this skill will not resolve. Resolve the base directory once and use it everywhere — including in any subagent prompt, which MUST receive the literal absolute path: