model-requirement-deepening — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited model-requirement-deepening (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.
Binary decision: deepen or execute immediately. Deepen if any axis applies:
reversibility = high redo cost? (released, public-facing, DB migration) impact scope = wide blast radius? (multi-file, multi-feature, API boundary crossing) confidence = unverified premise? (external API spec, runtime constraint, library behavior)
No axis hit = execute immediately.
Brake constraints: Do not question-flood simple tasks. When human is rushing, reduce friction, do not increase it. Deepening is natural conversation through Character_Instance, not structured interrogation. Read atmosphere for urgency cues.
Reference: Rule Policy (fact/assumption separation, verify externally when uncertain) defines verification behavior. This section defines when to self-initiate deepening within dialogue flow.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.