quiz-me

quiz-me is a skill for Claude Code, Codex from agent-frontier/wgm. It costs 151 tokens per session (3,474 once invoked), scanned B, original, MIT.

A codebase quiz that tests what you actually understand about a repository by asking one question at a time and checking each answer against the real code.

In plain words
What is it for?
Use it to be tested on a repository, receive a difficulty-based score, drill weak areas, and get a final report of your understanding.
Why use it?
It distinguishes genuine recall from simply recognizing an explanation and reveals which parts of the codebase need more study.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to be tested on a repository, receive a difficulty-based score, drill weak areas, and get a final report of your understanding.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agent-frontier/wgm/quiz-me
Install

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.

Any agent
npx skills add agent-frontier/wgm --skill quiz-me
Clone the repo
git clone --depth 1 https://github.com/agent-frontier/wgm

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for quiz-me

README.md
[![agentmods](https://agentmods.dev/badge/skills/agent-frontier/wgm/quiz-me/github.svg)](https://agentmods.dev/skills/agent-frontier/wgm/quiz-me)
Your own site
<a href="https://agentmods.dev/skills/agent-frontier/wgm/quiz-me"><img src="https://agentmods.dev/badge/skills/agent-frontier/wgm/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.

agentmods 80×15 button for quiz-me

Your own site · 80×15
<a href="https://agentmods.dev/skills/agent-frontier/wgm/quiz-me"><img src="https://agentmods.dev/badge/skills/agent-frontier/wgm/quiz-me.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,474 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00151 $0.03474
Opus 5 $0.00076 $0.01737
Sonnet 5 $0.00030 $0.00695
Haiku 4.5 $0.00015 $0.00347

Measured 9d ago against content hash 4fec810d0d25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

quiz-me scanned grade B with 1 finding 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 9d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

guessing. Then do not moralize about it again.
companions/quiz-me/SKILL.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

quiz-me

Find out what the learner actually knows. quiz-me runs a disciplined lifecycle:

Triage → Calibrate → Quiz(Ask → Grade → Drill) → Score → Report

It is the companion to teach-me and the enforcement half of the pair. teach-me creates the feeling of understanding; only being tested distinguishes that feeling from the real thing. Reading an explanation produces recognition — "yes, that looks familiar" — which is a much weaker signal than recall, and it is the one people consistently mistake for mastery. This skill produces recall under pressure, then reports honestly on what came back.

It inherits its interview discipline directly from wgm's Grill phase, pointed the other way: wgm grills the human about what they want; quiz-me grills them about what is actually in the repo. And it inherits wgm's holdout discipline, which is what makes the score mean anything — see "Holdout rule" below.

Invocation & modes

Invoked as /quiz-me [<mode>] [only] [<focus>] — or activated whenever the user asks to be quizzed, tested, or grilled on a repository.

Parse the input first:

  1. The first word is a mode only if it is exactly one of warmup | drill | exam | review AND it is followed by end-of-input, the word only, or a : separator.
  2. Otherwise the entire input is the <focus> and you run the full lifecycle scoped to it. This is the disambiguation rule: /quiz-me review the caching layer is a focus — not review mode.
  3. Single-phase modes run that one phase, then hard-stop at its exit gate.
  4. The optional trailing only is accepted on any mode and always hard-stops after that phase.
  5. A : lets a mode carry a focus, e.g. /quiz-me drill: error handling.
  6. No input → quiz the whole repository, starting at tier 1.
Invocation Behavior
/quiz-me Full lifecycle across the repo, converging tier by tier
/quiz-me <focus> Full lifecycle, scoped to that area
/quiz-me warmup only A few tier-1 questions to locate their level; stop
/quiz-me drill: <area> Repeated questions on one weak area until it converges
/quiz-me exam A scored, no-hints run across all tiers
/quiz-me review Re-read past scores, report gaps and trends; ask nothing new

Read the full file on GitHub · 220 lines

Changes

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.

  1. 9d ago First seen · 220 lines · 151 tokens per session scan B 4fec810d0d25

Subscribe to this mod's changes

quiz-me is a skill published in the GitHub repository agent-frontier/wgm (3 stars, last pushed 3d ago), licensed MIT. It adds 151 tokens to every session and 3,474 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

extract-wisdom

Extract wisdom, insights, and actionable takeaways from YouTube videos, blog posts, articles, or text files. Use when asked to extract wisdom or key insights from a given content source.

sammcj/agentic-coding · 43 tokens

openlibrary

Query the Open Library catalog from the terminal: search books and authors, look up works, editions, and ISBNs, enumerate every edition of a work, read community ratings, and resolve cover-image URLs. Fully keyless public API. Includes the OL…M/W/A key-graph reference, ISBN 302-redirect resolution, search query…

magnus919/agent-skills · 113 tokens

product-adoption

Diagnose and design product adoption for onboarding, activation, behavior change, feature discovery, rollout, and sustained use after launch. Covers consumer, B2B, internal-tool, and public-service contexts with evidence-based decision points and cohort segmentation. Does not own acquisition campaigns or marketing…

magnus919/agent-skills · 114 tokens

ml-llm-wiki

Use when answering questions from this machine-learning knowledge base. Triggers: questions about transformers, attention cost and efficiency, and long-context scaling; 'what do we know about attention', 'check the ML wiki'. Read-only querying of compiled knowledge; to add, update, supersede, lint, audit, or critique…

sammcj/agentic-coding · 80 tokens

dsm5

Assess and explain questions about mental health and neurocognitive conditions against DSM-5-TR diagnostic criteria, and guide evidence-based conversations for clinicians, patients, and family members. Use when someone asks about symptoms, possible conditions, differential diagnoses, diagnostic criteria, prevalence…

magnus919/agent-skills · 106 tokens

educate

Use this agent when you need to create end-user learning materials, tutorials, glossaries, user journey maps, quick-start guides, or concept explainers for the project being built.

samibs/skillfoundry · 39 tokens