vibe-workflow — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited vibe-workflow (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 the request and existing project state to choose the next useful action. Load only the context needed to identify the outcome, constraints, and current implementation. An existing file does not prove that a stage is complete.
Quick mode needs a clear outcome, constraints, and acceptance journey; deeper planning is useful for unresolved integrations or consequential decisions.
Use a change skill if available; missing planning documents do not require restarting discovery.
debugging skill if available, without redoing the new-product interview.
their limits; do not begin an unrequested implementation or deployment.
Use vibe-agents when creating project instructions, vibe-build for a new implementation, and an available verification skill for a relevant user journey. Only invoke skills actually present in the target environment. The five stages are a useful route, not five approval gates or a mandatory document set for every edit.
Reuse answered questions and Handoff Context. Ask for missing consequential decisions; otherwise proceed with clearly stated assumptions. Keep stable constraints in AGENTS.md, decisions in product documents, and current progress in MEMORY.md where the project uses it. One builder is sufficient unless independent work and available tools justify delegation.
Complete the scope the user requested, including relevant checks and fixes. When reporting, distinguish actual results from unperformed checks and name any concrete blocker. Do not stop at the first implementation if a working product was requested; do not publish merely because local work is complete.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.