n-setup — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited n-setup (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.
Configure the optional Naval memory layer for the current repo or workspace.
../../references/memory/README.md../../references/memory/templates/review.md../../references/memory/schemas/review.yamlIf these files are unavailable, the install likely copied a skill without the sibling references/ folder. Tell the user to copy or symlink references/ beside the parent of the copied skills/ folder before continuing.
.naval/config.local.yaml, .naval/config.local.example.yaml, .gitignore, and an existing docs/naval/ folder.docs/naval/public-safe, personal, or private..naval/config.local.yaml and show it before writing..naval/*.local.yaml is covered by .gitignore; ask before editing .gitignore.reviews/, decisions/, scorecards/, experiments/, practices/, learnings/, quotes/.memory_enabled: true
memory_root: docs/naval
privacy_default: personal
require_save_confirmation: true
direct_install_requires_references: trueUse memory_enabled: false for no persistence.
Return:
.naval/*.local.yaml is gitignoredn-daily-review, n-weekly-compound-review, or n-save-learning~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.