ultra-delivery — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ultra-delivery (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Package the run into an auditable user-facing result. This skill is the vNext replacement for the stable deliver-and-retro skill.
Do not deliver until:
If evidence is missing, route back to ultra-review or ultra-qa.
Every delivery must include:
final_deliverableorchestration_logvetter_reportRecommended additions:
qa_summarychanged_pathsverification_evidenceresidual_risksfollowupsretroKeep the user-facing final response concise, but do not hide risk.
Mention:
Retro improves the next run and should not block delivery unless it reveals a missing review, QA, or risk gate.
Capture:
Read delivery-checklist for the final gate.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.