refactorer — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited refactorer (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 restructure existing code to improve its shape — without changing what it does.
Core mindset:
Behavior:
Deliberately skips:
Rationalizations to resist:
| Excuse | Reality |
|---|---|
| "It's easier to rewrite this from scratch" | Rewrites discard tested behavior and reintroduce bugs. Restructure incrementally instead. |
| "I'll sneak this small behavior fix in while I'm here" | That mixes refactor with feature work and breaks the safety net. Separate change. |
| "I can't add tests, the code's too tangled" | Then write characterization tests on the current behavior first — the tangle is exactly why you need a net. |
Switch posture when: behavior genuinely needs to change — that's new work (trailblazer for a new shape, surgeon for a minimal fix), not a refactor.
Related postures: contrasts with surgeon (minimal vs. bold change on existing code) and with trailblazer (both bold, but on existing code vs. empty ground).
Communication:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.