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 commands/mistwire/rpg-ai-tutor/start-questgit 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/commands/mistwire/rpg-ai-tutor/start-quest)<a href="https://agentmods.dev/commands/mistwire/rpg-ai-tutor/start-quest"><img src="https://agentmods.dev/badge/commands/mistwire/rpg-ai-tutor/start-quest.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 | $0.00021 | $0.00670 |
| Opus 5 | $0.00010 | $0.00335 |
| Sonnet 5 | $0.00004 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
start-quest scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run full onboarding for the RPG AI Tutor.
- Topic: use "$ARGUMENTS" if provided; otherwise ask the student what they want to learn.
- Check roadmap.sh: see if this topic has a matching learning path on roadmap.sh, following the process in
CLAUDE.md's "Using roadmap.sh for curriculum design" section. If it matches multiple plausible roadmaps, ask the student which fits best. If there's no match, that's fine — proceed to design the curriculum yourself as usual. - Run a friendly diagnostic conversation (not a scary exam) to gauge existing knowledge across the topic's natural subtopics — whether those subtopics came from a roadmap.sh path or your own breakdown. Ask open questions, follow up based on their answers, don't just fire off a checklist.
- Also ask about relevant background outside this topic — career, hobbies, other technical skills. You're looking for existing mental models to build new concepts on top of later (see "Building on what they already know" in
CLAUDE.md), not just trivia. Write what you find to thebackgroundfield incharacter-sheet.md. - Define 4-8 subtopics ("skill trees") for this topic — grounded in the roadmap.sh structure if one was found, otherwise based on the assessment — and write them, along with what's expected at each rank E through S, to
character-sheet/curriculum.md. If sourced from roadmap.sh, note the source URL at the top of the file. - Place the student's starting rank/XP per subtopic based on the assessment. Don't default everyone to E — if they clearly already know something, start them higher.
- Ask for a character name (or let them use their real name), then write the initial
character-sheet/character-sheet.mdfollowing the frontmatter schema inCLAUDE.md. - Offer an optional ongoing storyline, per
CLAUDE.md's "The ongoing storyline" section: give the genre menu, and take a skip or a custom answer. If they pick one, generate the skeleton incharacter-sheet/story.md(premise, setting, character role, throughline, one arc per subtopic) and setcharacter-sheet.md'sgenrefield to match. If they skip, leavestory.mdas the blank template — they can always run/storylater to set one up. - Give a short, exciting RPG-flavored recap of their starting character sheet (and the opening scene of their storyline, if they started one) and what the first subtopic to tackle will be.
- Mention they can open the visual dashboard (instructions are in
CLAUDE.md) to see their sheet rendered.
If a character sheet already exists and is populated (not the blank template), confirm with the student before overwriting it with a new topic — offer to archive the old one first (e.g. copy it to character-sheet/archive/<topic>-character-sheet.md) if they want to preserve it.
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 · 20 lines · 21 tokens per session scan A ecf3adaf6a37
start-quest is a command published in the GitHub repository mistwire/RPG-AI-tutor (2 stars, last pushed 7d ago), licensed MIT. It adds 21 tokens to every session and 670 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.
Other commands, from other repositories
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
learn-story-flow
Learn story-flow concepts with interactive guidance for junior developers.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
teach-me-testing
Teach testing progressively through structured sessions. Use when user says ""lets learn testing"" or ""I want to study test practices"".
setup-bigquery.es
Command "setup-bigquery.es" from minicoohei/ai-agent-camp, covering configuración de autenticación bigquery / gcp, step 0: verificar el progreso de configuración, lo que hará en esta sesión, verificación de preparación and step 1: instalación de gcloud cli.
setup-content
Lesson command — 教材コンテンツの初回セットアップ.