generate-books

generate-books is a skill for Claude Code from protoLabsAI/mythx-mcp. It costs 27 tokens per session (1,219 once invoked), scanned A, original, MIT.

A command that turns an existing tabletop role-playing game world pack into printable books for the game master and players, plus a bestiary and setting guide.

In plain words
What is it for?
Use it to create a game-master book, player book, bestiary, campaign setting, shared rules, character sheet, and reference appendices from a selected world pack.
Why use it?
It removes the need to assemble the world's rules, story information, monsters, items, conditions, and encounter tables by hand.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool.

Part of the rpg plugin — 7 skills, 5 agents, 4 hooks shipped together

Good fit Use it to create a game-master book, player book, bestiary, campaign setting, shared rules, character sheet, and reference appendices from a selected world pack.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/protolabsai/mythx-mcp/generate-books
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.

Any agent
npx skills add protoLabsAI/mythx-mcp --skill generate-books
Clone the repo
git clone --depth 1 https://github.com/protoLabsAI/mythx-mcp

Made for: Claude Code.

Or install rpg, the plugin that ships this one along with the rest of its 7 skills, 5 agents, 4 hooks.

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 generate-books

README.md
[![agentmods](https://agentmods.dev/badge/skills/protolabsai/mythx-mcp/generate-books/github.svg)](https://agentmods.dev/skills/protolabsai/mythx-mcp/generate-books)
Your own site
<a href="https://agentmods.dev/skills/protolabsai/mythx-mcp/generate-books"><img src="https://agentmods.dev/badge/skills/protolabsai/mythx-mcp/generate-books/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for generate-books

Your own site · 80×15
<a href="https://agentmods.dev/skills/protolabsai/mythx-mcp/generate-books"><img src="https://agentmods.dev/badge/skills/protolabsai/mythx-mcp/generate-books.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,219 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00027 $0.01219
Opus 5 $0.00014 $0.00609
Sonnet 5 $0.00005 $0.00244
Haiku 4.5 $0.00003 $0.00122

Measured 12d ago against content hash c0ac90336a65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

generate-books 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 12d 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.

world-builder/skills/generate-books/SKILL.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate Books Command

Generate print-ready books from an existing world pack.

Usage

/generate-books <world-pack-id>

If no world pack ID is provided, lists available packs.

Output

Creates files in the data directory (configurable via RPG_MCP_DATA_DIR environment variable, defaults to ~/.mythxengine/data/):

data/
├── rules/                    # Shared across all worlds
│   ├── core-rules.txt        # Complete rulebook
│   ├── quick-reference.txt   # One-page reference
│   └── character-sheet.txt   # Printable character sheet
│
└── books/<pack-id>/          # World-specific books (uses pack ID)
    ├── gm-book.txt           # GM-only content (full spoilers)
    ├── player-book.txt       # Player-facing content
    ├── bestiary.txt          # All monsters
    ├── campaign-setting.txt  # World overview
    └── appendices/
        ├── items.txt         # Complete item catalog
        ├── conditions.txt    # Conditions reference
        └── encounters.txt    # Encounter tables

Workflow

Phase 1: World Pack Selection

If no pack ID provided:

  1. Call mcp__rpg__list_world_packs() to get available packs
  2. Use AskUserQuestion to let user select:
    header: "World Pack"
    question: "Which world do you want to generate books for?"
    options:
      - label: "<pack-name>"
        description: "<pack-tagline>"
      ...
    

Phase 2: Validate Pack

  1. Call mcp__rpg__load_world_pack({ packId }) to verify it exists
  2. Display world summary:
    • Name and tagline
    • Content counts (archetypes, monsters, locations, etc.)
  3. Confirm generation with user

Phase 3: Generate Rulebook (if needed)

  1. Call mcp__rpg__generate_rulebook({ force: false })
  2. If cached: false:
    • Launch rpg:book-generator subagent for rulebook
    • Wait for completion

Phase 4: Generate World Books (Parallel)

Launch 4 book-generator subagents in a SINGLE message:

Task(subagent_type: "rpg:book-generator",
     prompt: "Generate GM book for pack <id>. Type: gm")
Task(subagent_type: "rpg:book-generator",
     prompt: "Generate player book for pack <id>. Type: player")
Task(subagent_type: "rpg:book-generator",
     prompt: "Generate bestiary for pack <id>. Type: bestiary")
Task(subagent_type: "rpg:book-generator",
     prompt: "Generate campaign setting for pack <id>. Type: setting")

Read the full file on GitHub · 190 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. 12d ago First seen · 190 lines · 27 tokens per session scan A c0ac90336a65

Subscribe to this mod's changes

generate-books is a skill published in the GitHub repository protoLabsAI/mythx-mcp (2 stars, last pushed 23d ago), licensed MIT. It adds 27 tokens to every session and 1,219 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.