A command that creates practice problems on a chosen topic and saves the problems separately from their answers. It can also use a weakness report to focus practice on areas that need improvement.

Use it to generate topic-based or weakness-based problem sets for paper practice, with answer files prepared for grading.

It gives learners targeted exercises without revealing answers before they finish, and supports checking work later with a grading command.

quiz — Command for coding agents by OPTIMETA: A command that creates practice problems on a chosen…

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.

agentmods

npx agentmods add commands/optimeta/paideia/quiz

Clone the repo

git clone --depth 1 https://github.com/OPTIMETA/PAIDEIA

Or install paideia, the plugin that ships this one along with the rest of its 6 skills, 18 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/optimeta/paideia/quiz.svg)](https://agentmods.dev/commands/optimeta/paideia/quiz)

Your own site

<a href="https://agentmods.dev/commands/optimeta/paideia/quiz"><img src="https://agentmods.dev/badge/commands/optimeta/paideia/quiz.svg" alt="Measured on agentmods" height="20"></a>

Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,101 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00049	$0.01101
Opus 5	$0.00024	$0.00550
Sonnet 5	$0.00010	$0.00220
Haiku 4.5	$0.00005	$0.00110

Measured 4d ago against content hash 7e2a7c37aa45, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quiz 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.

plugins/paideia/commands/quiz.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Output language

Read INTERFACE_LANG from .course-meta (default en). All user-facing prose — chat output and narrative parts of the generated quiz MD — must be in that language. Keep in English regardless: file paths, slash command names, pattern IDs (P1, P2…), LaTeX, tier markers, and the per-problem footer template's keyword shape (a one-line italic citation of §<section> and P<k>).

Load skills/exam-drill/SKILL.md. Also load course-index/summary.md, course-index/patterns.md, course-index/coverage.md if they exist.

Arguments: $ARGUMENTS (First word: topic, § number, or the literal weakmap. Second word if present: number of problems, default 5.)

Prerequisite: if course-index/ is empty, run /analyze first — problems generated without the index will be unfocused.

Procedure:

Weakmap mode. If the first arg is weakmap:
- Find the latest weakmap/weakmap_*.md (by mtime). If missing, tell the user to run /weakmap first and abort.
- Parse its "Top 5 weaknesses" and "User-declared weaknesses" sections to collect a target set of (§, Pk) pairs.
- Design the N-problem mix so every top weakness is covered at least once; user-declared items take priority. Spread remaining slots over top-ranked error patterns.
- Filename override: save to quizzes/weakmap_<ts>.md (+ _answers.md). Cite which weakness entry each problem targets in the footer.
- Skip step 1 below. Continue from step 2 with this weakness-driven mix.
Resolve topic. Map the argument to a specific set of sections and patterns via coverage.md and patterns.md. If ambiguous, ask the user to pick.
- Special case all. When the user passes all (broad diagnostic), weight section selection by HW density: draw ~70% of problems from 🔥🔥 Exam-primary sections, ~25% from 🔥 Exam-likely, ≤5% from 🟡, 0% from ⚪. Never sample ⚪ low-risk sections unless the user explicitly names them — the professor's HW already signaled what's off the exam. Filename stem override: diagnostic, not all — save to quizzes/diagnostic_<ts>.md (+ _answers.md) and print the upload name answers/diagnostic_<ts>.pdf, so /grade's diagnostic* resolution rule matches whatever the user's scanner names the file.
- Specific § or topic. If the user names a ⚪ low-risk section, comply but warn once (in $INTERFACE_LANG): "No HW touched this §, so exam probability is low. Still want to drill it?"
Design the problem mix (N problems):
- 1 warmup (definition recall, fastest pattern application)
- N-3 standard (single-pattern derivation or computation) — prefer patterns that recur across multiple HW problems in the target sections
- 1 applied (pattern used in a specific system / numerical case)
- 1 conceptual trap (tests a common student error — sign, wrong variable held fixed, wrong pattern chosen)
Save.
- Problems → quizzes/<topic>_<ts>.md
- Answers → quizzes/<topic>_<ts>_answers.md (do not display)
- Each problem cites the § and pattern being tested (at the end of the problem, not in title — don't spoil).
Print to chat (in $INTERFACE_LANG):
- Filename of the quiz (so user knows where it is)
- All N problem statements, numbered
- Closing line: "Solve on paper, scan, upload as answers/<topic>_<ts>.pdf, then /grade."
Do NOT ask the user to type answers in chat. If they start typing an answer, remind them of the PDF-upload workflow.

Read the full file on GitHub · 64 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.

4d ago First seen · 64 lines · 49 tokens per session scan A 7e2a7c37aa45

Subscribe to this mod's changes

quiz is a command published in the GitHub repository OPTIMETA/PAIDEIA (91 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 1,101 once invoked, about $0.0002 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 2026-08-30.

Learning and teaching claude-code claude-code-plugin engineering exam-prep local-first markdown

quiz

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Output language

What this file has done since we first saw it

Other commands, from other repositories

design-tutorial

demo-command

case-practice

recap

code-explainer

help