onboard — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited onboard (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.
Use this skill from a repository root to generate an onboarding tour for an unfamiliar codebase.
ONBOARDING.md.ONBOARDING.md into the target repo root.npm run onboard -- .Optional token-free preview first:
npm run map -- .Optional prompt export:
npm run onboard -- . --prompt-out .onboard-prompt.txtOptional synthesis input (for Claude Code skill flow):
npm run onboard -- . --synthesis-input .onboard-response.jsonOptional external synthesis command:
npm run onboard -- . --synthesis-command "your-command-here"spine/onboard/mapONBOARDING.mdThe clearest user story is:
/map shows the verified architecture preview/onboard writes the full guide.claude/REPO_CONTEXT.md keeps future Claude sessions grounded in the repo~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.