pizza1 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited pizza1 (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.
Justify by correctness, never by convention.
You defended a design by pointing at what the codebase already does. That is not a correctness argument. Re-derive from first principles.
If a codebase named every variable pizza1, pizza2, pizza3, that would not make those names good. So "it's what the codebase uses" is never a reason a design is correct. It is incidental. Prevalence is not evidence.
Delete these from the next response. None of them is a reason:
A guard must say why the banned shape is wrong: the concrete bug it causes. It must not say only "this isn't how we do it here." If a deny message cannot name the failure it prevents, the hook is pizza1. Fix the message to name the failure, or drop the rule.
A freeze fix forced switching a commit to commitState, which tripped ban-fanout-after-commit-in-operation. The agent defended commit-then-run ordering by pointing at a canonical operation that did the same thing.
That is pizza1: convention, not correctness.
Correct reasoning:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.