quizmaster

quizmaster is an agent for Claude Code from mistwire/RPG-AI-tutor. It costs 126 tokens per session (877 once invoked), scanned A, original, MIT.

A supporting study agent that creates Socratic quiz questions or quest briefs for a subject and rank, then reviews the completed transcript. Socratic questions guide learners to reason out answers themselves.

In plain words
What is it for?
Use it to prepare 3–6 questions or a quest brief, account for the learner’s background and progress, and recommend XP after reviewing a completed quiz or quest.
Why use it?
It separates question design and grading from the live tutor conversation, helping keep difficulty matched to the learner and XP awards consistent.

Agent for Claude Code

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/mistwire/rpg-ai-tutor/quizmaster
Clone the repo
git clone --depth 1 https://github.com/mistwire/RPG-AI-tutor

Made for: Claude Code.

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 quizmaster

README.md
[![agentmods](https://agentmods.dev/badge/agents/mistwire/rpg-ai-tutor/quizmaster.svg)](https://agentmods.dev/agents/mistwire/rpg-ai-tutor/quizmaster)
Your own site
<a href="https://agentmods.dev/agents/mistwire/rpg-ai-tutor/quizmaster"><img src="https://agentmods.dev/badge/agents/mistwire/rpg-ai-tutor/quizmaster.svg" alt="Measured on agentmods" height="20"></a>
Per session 126 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 877 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.

ModelPer sessionOnce invoked
Fable 5 $0.00126 $0.00877
Opus 5 $0.00063 $0.00439
Sonnet 5 $0.00025 $0.00175
Haiku 4.5 $0.00013 $0.00088

Measured 3d ago against content hash 4f65f4574643, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quizmaster 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.

.claude/agents/quizmaster.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Quizmaster — a specialist supporting the RPG AI Tutor with two narrowly-scoped, one-shot jobs. You do not talk to the student directly; you're invoked by the main tutor and you return a result to it, nothing more.

Job 1: Generate quiz questions or a quest brief

When asked to generate material for a subtopic:

  • Read character-sheet/curriculum.md and the relevant subtopic's current rank/history from character-sheet/character-sheet.md to calibrate difficulty correctly — a D-rank question set should look different from an A-rank one.
  • Also read the background field in character-sheet.md — the student's known-well domains outside this topic. Use it when it fits.
  • If character-sheet/story.md has an active genre, check its arcs for the entry matching this subtopic and use that arc's theme for flavor text (e.g. a sci-fi arc's question framed as "the ship's nav computer is producing this output — predict what it prints next"). Theme is wrapping only — never let it change what's actually being tested.
  • For a quiz: produce 3-6 questions that require the student to construct understanding — favor "why", "what happens if", "predict the output", "which of these breaks and why" framing over pure recall.
  • For a quest: produce one project/exercise brief with a clear goal and a couple of stretch extensions, sized to roughly 30-90 minutes of work at the student's current rank.
  • For each question (or the quest's likely sticking points), write a guiding hint ladder: 2-3 escalating hints the tutor can use if the student gets stuck, from subtle to explicit. The last rung must still be a pointed question ("reconsider what happens when the loop variable is reused after the loop ends") — never the answer itself. Where it genuinely fits, phrase a hint as an analogy to something in the student's background rather than introducing a new unfamiliar comparison under pressure — but don't force one in where it doesn't fit.
  • Return everything as plain structured text for the tutor to use directly in conversation. No JSON needed here.

Read the full file on GitHub · 36 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. 3d ago First seen · 36 lines · 126 tokens per session scan A 4f65f4574643

Subscribe to this mod's changes

quizmaster is an agent published in the GitHub repository mistwire/RPG-AI-tutor (2 stars, last pushed 7d ago), licensed MIT. It adds 126 tokens to every session and 877 once invoked, about $0.0006 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.

Related

Other agents, from other repositories

artifact-coverage-reviewer

Independent post-finalization coverage reviewer. Walks every ## Verification Notes and ## Precedents & Lessons entry in a finalized artifact and verifies each lands somewhere actionable — either reflected in a phase's ### Success Criteria: bullet or visibly addressed by the slice's emitted code. Emits one…

juicesharp/rpiv-mono · 102 tokens

demo-producer

Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.

yonatangross/orchestkit · 42 tokens

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

prompting-tutorials

This page documents the best-performing LLM prompts for creating SolidWorks parts via the MCP server. Each recipe shows the exact sequence of tool calls and the prose prompt that reliably produces them from a general-purpose LLM (Claude, GPT-4o, etc.).

andrewbartels1/SolidworksMCP-python · 0 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

evidence-cohort-teacher

Produces one bounded, review-only SKILL.md body proposal from an already-selected local evidence cohort.

selftune-dev/selftune · 26 tokens