fvtt-mcp-molten5e: Skill for Claude Code

.claude/skills/stat-block-builder/SKILL.md

stat-block-builder is a skill for Claude Code from Txpple/fvtt-mcp-molten5e. It costs 241 tokens per session (4,916 once invoked), scanned A, original, MIT.

A workflow for building a complete non-player character in Foundry VTT from a D&D 5e stat block. An NPC is a game character controlled by the game master.

In plain words
What is it for?
Use it to create or update ready-to-play D&D 5e NPCs with their stats, features, inventory, artwork, ownership, and conditions.
Why use it?
It ensures the Foundry character includes more than basic numbers, including abilities, attacks, spells, effects, equipment, biography, and finishing details.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions Claude Code.

This is Txpple/fvtt-mcp-molten5e's own configuration. It tells Claude Code how to work on fvtt-mcp-molten5e itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fvtt-mcp-molten5e configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Txpple/fvtt-mcp-molten5e. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Txpple/fvtt-mcp-molten5e/main/.claude/skills/stat-block-builder/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Txpple/fvtt-mcp-molten5e

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 stat-block-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/txpple/fvtt-mcp-molten5e/stat-block-builder/github.svg)](https://agentmods.dev/skills/txpple/fvtt-mcp-molten5e/stat-block-builder)
Your own site
<a href="https://agentmods.dev/skills/txpple/fvtt-mcp-molten5e/stat-block-builder"><img src="https://agentmods.dev/badge/skills/txpple/fvtt-mcp-molten5e/stat-block-builder/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 stat-block-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/txpple/fvtt-mcp-molten5e/stat-block-builder"><img src="https://agentmods.dev/badge/skills/txpple/fvtt-mcp-molten5e/stat-block-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 241 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,916 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 $0.00241 $0.04916
Opus 5 $0.00120 $0.02458
Sonnet 5 $0.00048 $0.00983
Haiku 4.5 $0.00024 $0.00492

Measured 9d ago against content hash 886067dec2fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

stat-block-builder 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 9d 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/skills/stat-block-builder/SKILL.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Complete-NPC builder

A judgment layer over the actor-authoring tools. It turns a stat block (pasted text, a Monster Manual entry, or a freeform description) into a fully-built, ready-to-play Foundry NPC — base stats, defenses, senses, special traits, actions, spellcasting, effects, its full inventory and loot, biography, and a finishing pass — by sequencing the right tool calls. It adds NO new mechanics; every tool it calls holds its own correctness.

Tools used: create-actor-from-compendium (prefab copy · prefab-as-base via modifications), author-npc (authored from scratch), update-actor, add-feature (features / compendium-features / spells), import-item (COPY gear from a compendium — the default for inventory), add-item (author homebrew gear — last resort), manage-activity, manage-effect, apply-condition, set-actor-art, set-actor-ownership, move-documents, update-actor-item (per-item corrections), the faceted discovery tools search-compendium-creatures / search-compendium-spells / search-compendium-items (find things to copy by type + facet — each searches the premium books only and never the SRD, so you don't reason about pack ids), search-compendium (broad name lookup) / get-compendium-entry (full entry), plus get-actor / get-actor-entity to read back. Defer item judgment to the [[physical-item-builder]] skill.

Faceted discovery returns minimal hits. search-compendium-creatures / -spells / -items each return results: [{ id, name, type, uuid, pack, packLabel, img, facets }], premium-first ranked. Pick a hit by name, then feed its pack + id straight into create-actor-from-compendium, import-item, or get-compendium-entry — no pack-id guesswork.

add-feature invocation shape. It takes a top-level mode — only feature, compendium-features, or items — plus nested params. Authoring any single feature/attack/save/aura/spellcasting/spells/homebrew-spell is mode: "feature" with feature.featureType set to that value (e.g. mode:"feature", feature.featureType:"save"); importing named features is mode: "compendium-features" with compendiumFeatures.featureNames. Below, shorthand like "add-feature save" always means that mode:"feature" + feature.featureType form — featureType is NOT a top-level mode.

Read the full file on GitHub · 258 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. 9d ago First seen · 258 lines · 241 tokens per session scan A 886067dec2fb

Subscribe to this mod's changes

stat-block-builder is a skill published in the GitHub repository Txpple/fvtt-mcp-molten5e (0 stars, last pushed 8d ago), licensed MIT. It adds 241 tokens to every session and 4,916 once invoked, about $0.0012 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.