ai-firstify — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ai-firstify (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
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.
Analyze and re-engineer projects to align with AI-first design principles.
Use this skill when asked to:
Perform a comprehensive read-only analysis across 7 dimensions. Output a scored report with recommendations. Do NOT modify any files.
Read references/mode-audit.md for the full audit procedure and dimension checklist.
First, perform the full audit (Mode 1). Then actively fix issues in 7 phases: foundation, de-agentification, skill extraction, complexity reduction, context hygiene, safety hardening, workflow optimization.
Read references/mode-reengineer.md for the full re-engineering procedure.
Guide the user through setting up a new AI-first project from scratch. Interactive: ask discovery questions, recommend architecture, scaffold, and test.
Read references/mode-bootstrap.md for the full bootstrap procedure.
Domain knowledge (load on demand per dimension):
Load the relevant reference file for the dimension you are currently analyzing. Do not load all references at once. Use progressive disclosure.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.