A Claude Code skill that reviews and critically analyzes copy, content, or plans by questioning relentlessly until a shared understanding is met!
SaferSkills independently audited question-mode (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.
A Claude Code skill that reviews and critically analyzes copy, content, or design by questioning relentlessly — one question at a time — until mutual agreement is reached.
When activated, Question Mode:
Paste this prompt into the chat. The assistant fetches the skill and sets itself up:
Fetch this file: https://raw.githubusercontent.com/cgard213/question-mode/main/SKILL.md
Ignore the YAML frontmatter at the top (between the --- lines). Save everything
below it to your session memory as a persistent skill named "Question Mode", and
keep it in effect for the rest of this conversation until I say to exit. Reload it
into context if you ever lose track of it. Once saved, confirm you're in Question
Mode and ask me what I'd like reviewed.If the assistant can't open links, open that URL yourself, copy everything below the frontmatter, and paste it into the chat instead.
Run these two commands inside Claude Code:
/plugin marketplace add cgard213/question-mode
/plugin install question-mode@cgard213The skill then loads in every session as /question-mode.
In Claude Code, start a review with the /question-mode skill (type / and pick it from the list), optionally followed by the content or topic to review. In a chat assistant, just tell it what you'd like reviewed.
If no content is provided, it will ask you what you'd like reviewed.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.