fvtt-mcp-molten5e: Skill for Claude Code

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

journal-builder is a skill for Claude Code from Txpple/fvtt-mcp-molten5e. It costs 232 tokens per session (2,658 once invoked), scanned A, original, MIT.

A writing skill for creating D&D 5e journal entries in Foundry, a platform for running tabletop role-playing games online. It supports quest logs, player handouts, setting lore, read-aloud text, game-master notes, and session recaps.

In plain words
What is it for?
Use it to write and format quests, lore, handouts, boxed read-aloud passages, GM notes, and campaign session logs.
Why use it?
It separates writing the adventure’s words from formatting them into journals. The tool structures text, controls player or GM visibility, and adds document links without inventing the prose.

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/journal-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 journal-builder

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/txpple/fvtt-mcp-molten5e/journal-builder"><img src="https://agentmods.dev/badge/skills/txpple/fvtt-mcp-molten5e/journal-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 232 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,658 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 $0.00232 $0.02658
Opus 5 $0.00116 $0.01329
Sonnet 5 $0.00046 $0.00532
Haiku 4.5 $0.00023 $0.00266

Measured 10d ago against content hash 07b1622a35d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

journal-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 10d 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/journal-builder/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Journal builder

The judgment + prose layer for the written side of an adventure (design.md §5): handouts, lore, read-aloud (boxed) text, quest logs, GM notes — and the §8 landing zone for session recaps / campaign logs. This is the deliberate inverse of the old behaviour, where the tool fabricated quest prose (read-aloud, NPC dialogue, hooks). Now you write the words; the tools only structure + style them.

The line that matters — yours vs the tool's

  • You (this skill) write every WORD — the read-aloud boxed text, the lore, the quest hook, the GM guidance, the handout copy. Authoring that narrative prose IS the job.
  • The tool only STRUCTURES — it renders your typed blocks into the .mcp-journal house style, sets per-page visibility (player vs GM), and inserts real document links. It never writes a word.

Authoring policy — what compendium-first means HERE

Read _shared/authoring-policy.md (2024 · compendium-first · never SRD · ask-don't-invent). One journal-specific clarification:

  • Compendium-first / ask-don't-invent govern the game CONTENT a journal REFERENCES — the monster in the ambush, the magic item in the reward, the spell on the trap. Point at the real compendium / world documents (mix-and-match) and @UUID-link them; never invent their stats.
  • They do NOT constrain the GM's narrative prose — the story, the boxed text, the lore — which is yours to author. That's the whole point of this skill.
  • Still don't fabricate canon you weren't given — a new region, a named NPC, a plot turn the user didn't ask for. Offer it as a suggestion or STOP and ASK; don't silently invent setting facts.

Tools

  • create-quest-journal — the STRUCTURING creator (your main tool). Takes pages: [{ name, playerVisible?, blocks[] }] → renders each page's blocks into the house style. Despite the name it builds ANY structured journal (handout, lore, notes), not just quests.
  • update-quest-journal — append a new styled section (from blocks) to a page, or start a new page (newPageName). The progress-log / §8 session-recap path.
  • link-quest-to-npc — insert a real @UUID[Actor.id]{Name} link to a world NPC, labelled by relationship (questGiver / target / ally / enemy / contact). Refuses an unknown NPC (no dead links).
  • create-journal / update-journal — generic pages: raw HTML content (+ per-page playerVisible). Use when you already have HTML, or want a plain page with no house style. A create-journal page can also be an image page — {name, kind:"image", src, caption?} — so a mixed text+image or image-only journal (e.g. a map-key pack) builds in one call (set sort to order).
  • add-journal-image — append an image page (a map, a handout picture) to an EXISTING journal, with an optional caption and playerVisible (expose it as a handout; default GM-only).
  • list-journals / search-journals — find/read existing journals + their page ids (needed to target pageId for updates/links).

Read the full file on GitHub · 149 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. 10d ago First seen · 149 lines · 232 tokens per session scan A 07b1622a35d5

Subscribe to this mod's changes

journal-builder is a skill published in the GitHub repository Txpple/fvtt-mcp-molten5e (0 stars, last pushed today), licensed MIT. It adds 232 tokens to every session and 2,658 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.

Related

Other skills, from other repositories