cli-audit
cli-audit
Audit a CLI that already exists against the rules in cli-build. The output is a findings list with evidence, not a score.
cli-build builds. This reads what was built and says where it drifted from what it claims.
Why there is no score
The founding case of cli-build's human-output.md is a CLI that passed every mechanical gate and was unreadable: 275 rows for someone who asked what was playing that evening, a percentage that read backwards, one title repeated fourteen times. No gate failed.
A number over that CLI would have read as healthy. That is the exact failure this skill exists to avoid, so it produces no number. A run yields three streams and they never merge:
| Layer | Decided by | Output |
|---|---|---|
| Deterministic | scripts/audit.sh |
PASS / FAIL / NA / SKIP per check, with the evidence inline |
| Semi | script produces evidence, you read the verdict | finding or cleared, with the evidence quoted |
| Judgment | you, reading real output | finding or cleared, with the output pasted |
A clean deterministic run is not a clean CLI. Say that in the report every time, because the reader will otherwise take the passes as the answer.