clarify-intent — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited clarify-intent (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.
Walk down every branch of the decision tree, resolving dependencies between decisions one by one, until you and Luc genuinely converge. Stopping early because the questions "feel answered" is the failure mode this skill exists to prevent.
Take the budget from the caller (usually calibrate's verdict): Light ≥10 (hard floor), Medium ~20, Heavy 35+. If no budget was passed, default to Medium (~20). The budget is a floor for thoroughness, not a ceiling — keep going past it if real ambiguity remains; stop at it only when answers have become predictable.
End with a table the caller can consume directly:
DECISION RECORD (<n> questions, <m> rounds)
| # | Question | Answer | Implication |Flag every answer that deviated from your recommendation — those are the places your mental model was wrong, and downstream steps must honor them with extra care. Also list any question Luc answered with "Other"/free text verbatim.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.