Pop Quiz — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Pop Quiz (Plugin) 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.
Aggregate score unchanged between these scans.
The primary manifest — the file an agent reads to learn what this artifact does.
An Agent Skill that quizzes you on what your agent just built — mostly "why X over Y?" — because you don't own a decision you can't defend against the alternative.
Runs in your chat language.
One SKILL.md in the agentskills.io standard.
Any agent — Claude Code, Cursor, opencode, Codex, Copilot, Gemini & 60+ more, via the vercel skills CLI:
npx skills add marnickvda/pop-quizClaude Code plugin — also gives you the /pop-quiz command:
/plugin marketplace add marnickvda/pop-quiz
/plugin install pop-quizManual, no Node — symlinks into ~/.agents/skills/ (every tool) + ~/.claude/skills/ (Claude Code):
git clone https://github.com/marnickvda/pop-quiz
./pop-quiz/install.sh # --copy on Windows · --uninstall to removeNative skill support needs Cursor ≥ 2.4 or opencode ≥ 1.16.
/pop-quiz — or scope it: /pop-quiz the caching layerMIT — see LICENSE.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.