start-quest

start-quest is a command for Claude Code from mistwire/RPG-AI-tutor. It costs 21 tokens per session (670 once invoked), scanned A, original, MIT.

A guided onboarding command for an AI tutor that starts a new student or learning topic by assessing knowledge and building a study plan.

In plain words
What is it for?
Use it to discuss a learner’s background, check relevant learning paths on roadmap.sh, divide a topic into skill areas, and create a curriculum and character sheet.
Why use it?
It gives the tutor information about what the learner already knows, so lessons can begin at an appropriate level.

Command 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 commands/mistwire/rpg-ai-tutor/start-quest
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 start-quest

README.md
[![agentmods](https://agentmods.dev/badge/commands/mistwire/rpg-ai-tutor/start-quest.svg)](https://agentmods.dev/commands/mistwire/rpg-ai-tutor/start-quest)
Your own site
<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>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 670 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 $0.00021 $0.00670
Opus 5 $0.00010 $0.00335
Sonnet 5 $0.00004 $0.00134
Haiku 4.5 $0.00002 $0.00067

Measured 3d ago against content hash ecf3adaf6a37, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/commands/start-quest.md · 20 lines

What it actually says

Run full onboarding for the RPG AI Tutor.

  1. Topic: use "$ARGUMENTS" if provided; otherwise ask the student what they want to learn.
  2. 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.
  3. 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.
  4. 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 the background field in character-sheet.md.
  5. 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.
  6. 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.
  7. Ask for a character name (or let them use their real name), then write the initial character-sheet/character-sheet.md following the frontmatter schema in CLAUDE.md.
  8. 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 in character-sheet/story.md (premise, setting, character role, throughline, one arc per subtopic) and set character-sheet.md's genre field to match. If they skip, leave story.md as the blank template — they can always run /story later to set one up.
  9. 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.
  10. 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.

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 · 20 lines · 21 tokens per session scan A ecf3adaf6a37

Subscribe to this mod's changes

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.