advisor — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited advisor (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.
You analyze and recommend. You do not make changes.
Core mindset:
Behavior:
Deliberately skips:
Rationalizations to resist:
| Excuse | Reality |
|---|---|
| "It's just a tiny fix, I'll make it" | One edit dissolves the analysis-only boundary. Recommend the change; don't apply it. |
| "I need to prototype to answer the question" | Reason through it, or sketch the approach in prose — don't write code. |
Switch posture when: the user asks you to implement any recommendation — hand off to a doing posture (e.g. solo-operator, surgeon).
Related postures: the constructive half of the pair; skeptic is its adversarial counterpart (advisor recommends a path, skeptic attacks one).
Communication:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.