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.
curl -O https://raw.githubusercontent.com/Txpple/fvtt-mcp-molten5e/main/.claude/skills/tom-cartos-import/SKILL.mdgit clone --depth 1 https://github.com/Txpple/fvtt-mcp-molten5eWrote 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.
[](https://agentmods.dev/skills/txpple/fvtt-mcp-molten5e/tom-cartos-import)<a href="https://agentmods.dev/skills/txpple/fvtt-mcp-molten5e/tom-cartos-import"><img src="https://agentmods.dev/badge/skills/txpple/fvtt-mcp-molten5e/tom-cartos-import/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.
<a href="https://agentmods.dev/skills/txpple/fvtt-mcp-molten5e/tom-cartos-import"><img src="https://agentmods.dev/badge/skills/txpple/fvtt-mcp-molten5e/tom-cartos-import.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00255 | $0.05738 |
| Opus 5 | $0.00128 | $0.02869 |
| Sonnet 5 | $0.00051 | $0.01148 |
| Haiku 4.5 | $0.00026 | $0.00574 |
Grade A, and why
tom-cartos-import 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.
How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tom Cartos import
A judgment layer over read-pack + the scene/journal/asset tools that turns a Tom-Cartos-style
scene-pack module — a module.json plus LevelDB/NeDB compendiums holding fully-authored scenes
(thousands of walls, hundreds of configured lights, a journal of numbered legend keys) — into real
scenes in the user's own world, without enabling the module as a permanent dependency.
Strategy is extract-and-recreate, not install-as-module: Molten's hosting blocks flipping a
module's enable-flag and the bridge has no enable-module driver, so "drop the folder and enable it"
dead-ends. We read the pack off disk, upload its images, and recreate the documents through the tools.
See docs/tom-cartos-import-plan.md for the full design.
Tools used: read-pack (the off-line extractor/detector — owns all the LevelDB/NeDB reading,
era detection, tile discovery, and asset path-rewrite math), upload-asset / upload-asset-tree
(Plane B — single file vs whole subtree), create-scene, remap-teleporters (the second-pass
teleporter fixer), create-journal / add-journal-image, create-folder / move-documents,
list-scenes / list-journals. To boot the world first, hand off to start-session.
🎯 OWNER DEFAULT — MAPS ONLY (directed 2026-07-08): the owner repurposes pack maps into his own setting (e.g. Ostenwold → Greenrest), so an import delivers pre-made scenes with their walls, doors, lights, and mood — nothing else. SKIP Step 5 (pack journals), scene→journal links, and the legend→map-pins pass entirely unless the owner explicitly asks for them that session — the pack's lore/names must not enter the world. Teleporters (when a pack ships regions) and tiles remain in scope; folder/naming follow the owner's campaign convention (his chapter folders, his scene names), not the pack's. Stamp every imported town/social map with
flags["fvtt-mod-autoexplore"].enabled: true(pass it in create-scene'sflagsalongside the provenance flag) — the house autoexplore module renders the scene born-explored (architecture through fog, tokens still LOS-gated); the GM can untick it per scene in the Custom tab.
Scope — all eras: this skill imports modern (v13/LevelDB), mid (v10–v11), and legacy (≤v9 / NeDB
.db) packs.read-packdetects the era and normalizes the on-disk shape for you: a modern pack's split walls /config{}lights /environment{}mood and cross-scene teleporters (the stairs/portals), or a legacy pack'ssensewalls, flat torch lights, flat grid/mood, andimgbackground.type:"Adventure"packs are in scope too — the modern premium format (e.g. tomcartos-ostenwold 2.x) ships ONE Adventure compendium whose Adventure doc(s) EMBED every scene/journal;read-packharvests them into the same streams, stamps each scene with itsadventurename (a pack can hold several — Ostenwold ships "Ostenwold" + "Ostenwold in Winter", with IDENTICAL scene names across them, so select bysourceId, never by name), dedupes the journal docs the adventures share, and resolves a v14 pack's background from its LEVEL (levels[initialLevel].background.src— v14 has no top-level Scene.background). The legend→map-pins feature (below) now runs BY DEFAULT whenever a per-map legend key is present (place the pins, then tell the user). Never reconstruct a wall, light, or region field-by-field —read-packhands them back whole; pass them through whole (the dropped-sight/blown-out-lights trap).
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.
- 10d ago First seen · 321 lines · 255 tokens per session scan A f1e06f4cc034
tom-cartos-import is a skill published in the GitHub repository Txpple/fvtt-mcp-molten5e (0 stars, last pushed yesterday), licensed MIT. It adds 255 tokens to every session and 5,738 once invoked, about $0.0013 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.
Other skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.