fvtt-mcp-molten5e: Skill for Claude Code

.claude/skills/table-builder/SKILL.md

table-builder is a skill for Claude Code from Txpple/fvtt-mcp-molten5e. It costs 214 tokens per session (2,584 once invoked), scanned A, original, MIT.

A builder for D&D 5e roll tables in Foundry VTT. A roll table randomly selects an entry, such as a monster, treasure, rumor, name, weather result, or magical effect.

In plain words
What is it for?
Use it to create random encounter, loot, rumor, name-generator, wild-magic, and weather tables.
Why use it?
It removes the need to manually format entries, assign roll ranges, and create document links. You still decide what the table contains.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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/table-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 table-builder

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/txpple/fvtt-mcp-molten5e/table-builder"><img src="https://agentmods.dev/badge/skills/txpple/fvtt-mcp-molten5e/table-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 214 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,584 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 $0.00214 $0.02584
Opus 5 $0.00107 $0.01292
Sonnet 5 $0.00043 $0.00517
Haiku 4.5 $0.00021 $0.00258

Measured 7d ago against content hash 1ba92e2d447c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

table-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 7d 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/table-builder/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Table builder

The judgment + content layer for roll tables (design.md §5) — the random-generation backbone of an adventure: what wanders out of the woods, what's in the hoard, what the tavern is whispering about. As with every authoring skill: you decide; the tool does.

The line that matters — yours vs the tool's

  • You (this skill) decide the CONTENTS — which entries are on the table, their relative weights, the theme, the flavor text (rumor wording, names, weather). That judgment IS the job.
  • The tool only STRUCTURES — it renders each entry into the correct v14 TableResult (the description field), auto-assigns roll ranges from weights, defaults the formula to 1d<total weight>, and validates + renders real document links (@UUID). It never decides what's on the table and never invents an item.

Authoring policy — what compendium-first means HERE

Read _shared/authoring-policy.md (2024 · compendium-first · never SRD · ask-don't-invent). Two table-specific clarifications:

  • Compendium-first governs the game CONTENT a result REFERENCES — the monster that ambushes, the magic item in the hoard, the spell a wild-magic surge mimics. Reference the real compendium entry by uuid (mix-and-match) so the table links the actual document with correct stats + art; never transcribe or invent its stats into the result text. This is exactly how the published DMG loot tables are built (each entry is an @UUID link to a real item).
  • It does NOT constrain the flavor text you author — rumor wording, tavern names, weather, a hook's phrasing are yours to write. But don't fabricate game facts (a made-up item, a non-existent monster). If the user wants a loot table of items that aren't in the books → STOP and ASK (or offer the closest real items).

Tools

  • create-rolltable — the structuring creator (your main tool). { name, results[], formula?, replacement?, displayRoll?, folderName?, description? }. Ranges auto-assign from weights and the formula defaults to 1d<total weight> unless you pass explicit ones.
  • import-rolltable — copy a whole published table from a compendium into the world ({ packId, itemId, folderName? }). Roll tables are world-only at roll time, so a DMG treasure / magic-item table must be imported before you can roll it; its results (and their @UUID item links) come along intact. Premium-book packs only. This is the table version of import-item — prefer it over hand-rebuilding a book table.
  • update-rolltable — change table fields and/or edit entries, two ways. To fix ONE entry (a typo, a re-link, a weight), use editResults — target it by roll (the die face, e.g. 7 on a d12) or resultId (from get-rolltable) and patch just its text/uuid/weight/range; the other entries — their ranges and @UUID item links — are left untouched. text REPLACES that entry's content: copy the raw text from get-rolltable, change only what you need, and keep any @UUID[...] enrichers you want preserved. Supplying results instead replaces the entire set (deletes + recreates all entries with fresh ranges) — right for a full re-theme, wrong for a typo.
  • roll-on-table — preview a draw on a world table (evaluates without marking drawn / posting to chat). A drawn loot entry's @UUID items come back as importable (uuid + label) so you can pull them into the world with import-item (see physical-item-builder).
  • list-rolltables — find tables + their ids (needed to target updates/deletes/rolls).
  • delete-rolltable — remove tables by exact id/name (strict, no fuzzy match).

Read the full file on GitHub · 140 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. 7d ago First seen · 140 lines · 214 tokens per session scan A 1ba92e2d447c

Subscribe to this mod's changes

table-builder is a skill published in the GitHub repository Txpple/fvtt-mcp-molten5e (0 stars, last pushed 7d ago), licensed MIT. It adds 214 tokens to every session and 2,584 once invoked, about $0.0011 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.