Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add emanzurv/quiz-me-skill --skill quiz-megit clone --depth 1 https://github.com/emanzurv/quiz-me-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/emanzurv/quiz-me-skill/quiz-me)<a href="https://agentmods.dev/skills/emanzurv/quiz-me-skill/quiz-me"><img src="https://agentmods.dev/badge/skills/emanzurv/quiz-me-skill/quiz-me/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/emanzurv/quiz-me-skill/quiz-me"><img src="https://agentmods.dev/badge/skills/emanzurv/quiz-me-skill/quiz-me.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 354 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Rogue Agent · line 364 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Rogue Agent · line 252 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 276 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 349 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 364 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00082 | $0.07957 |
| Opus 5 | $0.00041 | $0.03979 |
| Sonnet 5 | $0.00016 | $0.01591 |
| Haiku 4.5 | $0.00008 | $0.00796 |
Grade A, and why
quiz-me scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quiz Me
A gate that keeps the user in the loop. Claude investigates, then tests the user's understanding with interactive multiple-choice questions. Code lands only after the user answers every question correctly. After the change, Claude checks that the user can explain each edit.
The quiz is for the user, not for Claude. Claude already knows the answers from its investigation — the point is for the user to demonstrate them.
Workflow
1. Investigate first — no edits
Read the real code. Find the actual root cause, the specific line or function that produces the behavior, and what the fix touches. The quiz must be grounded in findings from this codebase, never a generic pop quiz.
If a misses log exists for this project, read it. Concepts the user has missed before get priority in this round's questions. Pull the streak in the same call — one read covers both files that exist, and a missing one just produces no output for its half:
r=$(git rev-parse --show-toplevel 2>/dev/null || pwd); f=~/.claude/quiz-me/"${r//\//_}"
cat "$f".misses.md "$f".streak 2>/dev/null
The log lives under ~/.claude/quiz-me/, never in the user's repo. Nothing this skill
writes lands in the working tree.
Derive the key from the repo root, not from $PWD. The hook starts from the payload's
cwd, which is where the session started, and then walks up to the repo root that
contains it, so both sides land on the same filename even when the session began in a
subdirectory. gate.py also resolves symlinks and falls back to a case-insensitive
match, so the two agree when the paths disagree on case. The repo root is what keeps them
agreeing in the first place — key off anything else and the marker is written under a
name the hook never checks, leaving the gate closed with nothing to unlock it but TTL
expiry. Every snippet below opens with the same r=/f= pair.
Open concepts carry forward
Every line is YYYY-MM-DD — <concept> — <what was missed>, except a resolution line,
which is YYYY-MM-DD — <concept> — RESOLVED. override is reserved: the escape hatch
logs under it, and those lines are bookkeeping, not misses. Nothing counts them as an
open concept — two overrides in a row would otherwise promote a concept the user never
got wrong to 🐉 boss — so never file a real miss under that name. A concept is open if its most recent
line (by position in the file) is a miss, not a RESOLVED. Group lines by the exact
<concept> text to find the latest one.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago Changed · +18 lines 7b5d6cc764a7
- 7d ago Changed · +39 lines 6a22a8ba5247
- 12d ago First seen · 533 lines · 82 tokens per session scan A 7b1d899aaddc
quiz-me is a skill published in the GitHub repository emanzurv/quiz-me-skill (5 stars, last pushed 5d ago), licensed MIT. It adds 82 tokens to every session and 7,957 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
learning-and-development
Builds capability — skills gaps, career frameworks, training that transfers to the job, and internal mobility. Use this to design a career ladder, close a capability gap, decide whether to build or hire a skill, structure onboarding into a role, or work out why training keeps failing to change anything.
economist-style
Apply The Economist style guide to written content. Use when editing markdown, HTML, documentation, or any written text that needs professional editing for clarity, precision, and brevity. Detects weasel words, fillers, passive voice, and style issues.
cpp-mentor
A general, self-adapting C++ mentor for any project. On first run with an empty profile it onboards: settles the goal and domain, derives a namespace from the goal, agrees conventions including the project's own error policy, and audits the developer's level in both C++ and the project's topic — with questions…
analyze
Reads input artifact(s) — codebase, planning session, refactor plan, or generic doc — and writes a tour-spec.json describing sections, embedded sources, cross-refs, quizzes, and external link maps. Use when the user wants a fresh learning guide built from source material; auto-hands-off to learning-guide:render.…
website-deploy-builder
Plan what to build on Website Deploy (simple-host.app). Helps a user decide whether their idea fits the static + light-backend model, maps it to concrete patterns (shared JSON state with atomic ops, append-only collections, localStorage, public APIs), and produces a focused prompt for an implementation agent. Knows…
connect-domain
Connect a user's own custom domain (subdomain e.g. recipes.brand.com via CNAME, or apex e.g. brand.com via A record) to a site already deployed on simple-host. Use when a user wants their site served from their own domain over HTTPS, or wants sign-in on saves from a page (a domain is what adds sign-in to saves; on the…