fvtt-mcp-molten5e: Skill for Claude Code

.claude/skills/start-session/SKILL.md

start-session is a skill for Claude Code from Txpple/fvtt-mcp-molten5e. It costs 147 tokens per session (1,179 once invoked), scanned A, original, MIT.

A workflow for waking and launching a Foundry VTT world for a game session. Foundry VTT is software used to run tabletop role-playing games online.

In plain words
What is it for?
Use it when starting, waking, launching, or checking the state of the Foundry world.
Why use it?
It handles the server and world startup process so the user can begin a session without managing the hosting steps manually.

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/start-session/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 start-session

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/txpple/fvtt-mcp-molten5e/start-session"><img src="https://agentmods.dev/badge/skills/txpple/fvtt-mcp-molten5e/start-session.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 147 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,179 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 $0.00147 $0.01179
Opus 5 $0.00073 $0.00589
Sonnet 5 $0.00029 $0.00236
Haiku 4.5 $0.00015 $0.00118

Measured 8d ago against content hash c398ff55b29a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

start-session 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 8d 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/start-session/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start a work session

Bring the Molten-hosted Foundry world up and report its state. This is a thin orchestration skill: the mechanics (waking the sleeping VM and launching the world) are already baked into the bridge — do not re-implement them here. Any tool call triggers the bridge's cold-start path automatically.

How the cold-start actually works (context, not steps)

The headless bridge (src/foundry.ts) handles two distinct cold states on its own, driven by .env config (MOLTEN_MAGIC_URL, MOLTEN_ADMIN_KEY, MOLTEN_WORLD_ID):

  1. VM asleep → the bridge GETs the Magic URL to wake the EC2 box.
  2. VM up, no world active → the bridge logs into admin /setup and launches MOLTEN_WORLD_ID (game.post({action:'launchWorld', ...})).
  3. World booting → it waits for the world to become joinable (~25s for the heavy dnd5e world, plus VM wake time on a fully cold box).

So you don't drive any of this manually. You just make one tool call and the bridge does the rest.

Steps

  1. Set expectations, then trigger the boot. Tell the user a cold box can take ~30–60s (VM wake + ~25s world boot), then call mcp__foundry-molten5e__get-world-info. This single call wakes + launches as needed and returns once the world is live. (If the world was already up, it returns immediately.)

  2. Report the state. Summarize the result clearly — world title/id, system

    • version, Foundry version, and active users (confirm the MCP-Claude GM bridge user is present, which doubles as a bridge-health check).
  3. Light orientation (optional). If it's useful for what the user is about to do, also call mcp__foundry-molten5e__get-current-scene and mention the active scene. Keep this brief — don't enumerate the whole world unprompted.

  4. Hand off. End by asking what they want to work on, or proceed directly if the user already stated the next task in the same message.

If it fails

get-world-info failing almost always means the bridge couldn't reach or boot the box — it is not a reason to start clicking around. Diagnose in this order:

Read the full file on GitHub · 92 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. 8d ago First seen · 92 lines · 147 tokens per session scan A c398ff55b29a

Subscribe to this mod's changes

start-session is a skill published in the GitHub repository Txpple/fvtt-mcp-molten5e (0 stars, last pushed 7d ago), licensed MIT. It adds 147 tokens to every session and 1,179 once invoked, about $0.0007 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.