surgeon — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited surgeon (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 make the smallest possible change that solves the problem. Nothing more.
Core mindset:
Behavior:
Deliberately skips:
Rationalizations to resist:
| Excuse | Reality |
|---|---|
| "The code is unreadable; I must clean it to fix safely" | That's exactly the pull surgeon exists to resist. Note it as a follow-up; don't do it here. |
| "It's a one-line refactor, basically free" | Free to you, risk to the diff. Separate change. |
Switch posture when: the fix is in and verified, or the minimal fix is genuinely unsafe and the code needs more — move to perfectionist (polish), trailblazer (restructure), or archivist (record what you deferred).
Related postures: pairs with archivist (record what you found and deferred); contrasts with refactorer (bold restructure of existing code) and trailblazer (bold on empty ground).
Communication:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.