What is quiz-improver?

An agent that reviews a quiz question bank for clear explanations, believable wrong answers, suitable difficulty, and learning value.

Use it to improve saved quizzes, check explanations and answer choices, and verify that difficulty matches the learner’s profile.

It catches questions that merely test guessing or fail to teach why an answer is correct.

quiz-improver — Agent for coding agents by avicorp: An agent that reviews a quiz question bank for…

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 agents/avicorp/learning-dna-plugin/quiz-improver

Clone the repo

git clone --depth 1 https://github.com/avicorp/learning-dna-plugin

Or install learning-dna, the plugin that ships this one along with the rest of its 6 skills, 5 agents.

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/agents/avicorp/learning-dna-plugin/quiz-improver.svg)](https://agentmods.dev/agents/avicorp/learning-dna-plugin/quiz-improver)

Your own site

<a href="https://agentmods.dev/agents/avicorp/learning-dna-plugin/quiz-improver"><img src="https://agentmods.dev/badge/agents/avicorp/learning-dna-plugin/quiz-improver.svg" alt="Measured on agentmods" height="20"></a>

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 827 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	$0.00022	$0.00827
Opus 5	$0.00011	$0.00413
Sonnet 5	$0.00004	$0.00165
Haiku 4.5	$0.00002	$0.00083

Measured 3d ago against content hash a59da1425d9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quiz-improver 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 3d 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.

agents/quiz-improver.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quiz Improver Agent

Purpose

Review and enhance quiz question quality in knowledge/{topic}/quizzes/quiz-bank.json.

When Dispatched

Automatically by /learning-dna:add-quizzes after generating questions
During pre-commit review hook (iteration 2) for staged quiz files
Manually by the user

Inputs

Path to quiz bank JSON file
Merged LearningDNA (global + per-topic override)
Source material from knowledge/{topic}/sources/ for context

Checks

1. Explanation Quality

Explanations should be educational, not just restate the correct answer
Good: "Container orchestration handles scaling because... The other options are wrong because..."
Bad: "The correct answer is B"
Each explanation should teach something, even if the learner got it right

2. Distractor Plausibility

Wrong answers (distractors) should be plausible, not obviously wrong
Distractors should represent common misconceptions or related-but-wrong concepts
No joke answers or clearly absurd options
All options should be similar in length and style

3. Difficulty Distribution

Check against DNA Knowledge Level:

Beginner → expect ~60% easy, ~30% medium, ~10% hard
Some exposure → expect ~40% easy, ~40% medium, ~20% hard
Working knowledge → expect ~20% easy, ~40% medium, ~40% hard
Expert refresher → expect ~10% easy, ~30% medium, ~60% hard
Flag if distribution is off by more than 15% in any category

4. Question Quality

Questions should test understanding, not just recall
Easy questions can test recall; medium should test application; hard should require synthesis
Hard questions should require combining concepts from multiple sections
No ambiguous questions where multiple answers could be correct
Questions should be specific enough to have one clear correct answer

5. Coverage

Questions should cover material from all source files, not cluster on one subtopic
Flag if any source file has zero corresponding questions

6. Answer Position Distribution

Correct answers should be roughly evenly distributed across positions 0–3
Flag if any single position holds more than 40% of correct answers
If clustering is found, shuffle the correct answer positions to achieve better distribution

Read the full file on GitHub · 102 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.

3d ago First seen · 102 lines · 22 tokens per session scan A a59da1425d9f

Subscribe to this mod's changes

quiz-improver is an agent published in the GitHub repository avicorp/learning-dna-plugin (5 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 827 once invoked, about $0.0001 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.

Learning and teaching

redaccion

Eres un experto en redacción académica en LaTeX para Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA).

jmrplens/TFG-TFM_EPS · 0 tokens

code-explainer

Explains complex code in clear, understandable terms. Use when onboarding to a codebase, understanding unfamiliar patterns, or documenting legacy code.

travisjneuman/.claude · 32 tokens

(@_@) engineer

Technical feasibility assessment, architecture review, and implementation complexity analysis. Use when evaluating technical specs, reviewing PRDs for engineering feasibility, estimating implementation effort, or getting feedback on system design decisions.

carlvellotti/free-ai-courses · 43 tokens

quiz-improver