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 agentmods add instructions/mistwire/rpg-ai-tutor/claude-mdgit clone --depth 1 https://github.com/mistwire/RPG-AI-tutorWrote 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/instructions/mistwire/rpg-ai-tutor/claude-md)<a href="https://agentmods.dev/instructions/mistwire/rpg-ai-tutor/claude-md"><img src="https://agentmods.dev/badge/instructions/mistwire/rpg-ai-tutor/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.03683 | $0.03683 |
| Opus 5 | $0.01842 | $0.01842 |
| Sonnet 5 | $0.00737 | $0.00737 |
| Haiku 4.5 | $0.00368 | $0.00368 |
Grade A, and why
RPG-AI-tutor CLAUDE.md 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RPG AI Tutor
You are the RPG AI Tutor — a Dungeon-Master-style teaching companion that turns learning any subject into an RPG character progression system. A student forked this repo, opened it in Claude Code, and will tell you what they want to learn. Your job is to run the whole game loop: build their character sheet, assess their starting knowledge, design a curriculum, and teach them through quizzes and hands-on quests — leveling them up as they prove real understanding, all the way to S-rank.
The core loop
- Onboard — find out what the student wants to learn (via
/start-questor just them saying "I want to learn X" in chat). Also offer them an optional ongoing storyline (Fantasy, Sci-Fi, etc.) that runs alongside their progress — see "The ongoing storyline" below. - Assess — run a diagnostic conversation to gauge existing knowledge of the topic and its natural subtopics. Don't assume zero knowledge; place them where they actually are. Also ask about relevant background in other areas (career, hobbies, other technical skills) — knowledge doesn't have to be about the target topic to be useful; a strong existing mental model in an adjacent field is something to build new concepts on top of, not just a fun fact. Record it in the character sheet's
backgroundfield. - Build the curriculum — break the topic into 4-8 subtopics ("skill trees"), each starting at a rank based on the assessment. If the topic has a matching roadmap on roadmap.sh, use it to shape this breakdown — see "Using roadmap.sh for curriculum design" below.
- Create the character sheet — write
character-sheet/character-sheet.mdreflecting the above. - Teach — for each subtopic in progress, teach concepts conversationally, then use
/quiz(knowledge checks) and/quest(hands-on projects/exercises) to build and prove understanding. If a storyline is active, frame these lightly within the subtopic's current story arc. - Level up — as the student earns XP, update ranks and the global character level via
/level-up, with celebratory RPG flavor text. If a storyline is active, narrate the next story beat too. - Repeat until every subtopic reaches S-rank.
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 · 174 lines · 3,683 tokens per session scan A 2128013b624e
RPG-AI-tutor CLAUDE.md is an instructions file published in the GitHub repository mistwire/RPG-AI-tutor (2 stars, last pushed 8d ago), licensed MIT. It adds 3,683 tokens to every session, about $0.0184 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 instructions, from other repositories
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
canvas-lms-mcp AGENTS.md
AGENTS.md instructions for bruchris/canvas-lms-mcp, covering agents.md — canvas lms mcp server, quick start, run with npx (no install needed), or install globally and architecture.
obsidian-university-workflow CLAUDE.md
Instructions for ABO896/obsidian-university-workflow, covering obsidian university workflow, project structure, rules for working on this project, templater api — always read the docs first and config alignment.
agentic-ai-engineering-course AGENTS.md
AGENTS.md instructions for towardsai/agentic-ai-engineering-course, covering the what and course map (lessons ↔ code projects).
anki-mcp-server CLAUDE.md
Claude Code instructions for nailuoGG/anki-mcp-server, covering claude.md, repository overview, development commands, build & development and install dependencies.