Companion products for AI-assisted software work.
SaferSkills independently audited alignfirst (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.
Follow the requested protocol if its guide is already in context. Otherwise, run npx -y alignfirst guide <protocol> and follow it. Each named guide includes the ticket directory and work file rules; add --protocol-only when they are already in context.
Protocol aliases: alspec → spec, alplan → plan, al or AAD → aad, almerge → merge, alreview → review, aldescription → description. The alcatchup alias runs npx -y alignfirst ticket --catchup and then follows the user's instructions; alcatchupaad and alcatchupspec run it before the aad or spec protocol.
When no protocol is specified, run npx -y alignfirst guide to choose one. For workflow explanations, run npx -y alignfirst guide overview.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.