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/token-cutout/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/token-cutout)<a href="https://agentmods.dev/skills/txpple/fvtt-mcp-molten5e/token-cutout"><img src="https://agentmods.dev/badge/skills/txpple/fvtt-mcp-molten5e/token-cutout/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/token-cutout"><img src="https://agentmods.dev/badge/skills/txpple/fvtt-mcp-molten5e/token-cutout.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 | $0.00200 | $0.02584 |
| Opus 5 | $0.00100 | $0.01292 |
| Sonnet 5 | $0.00040 | $0.00517 |
| Haiku 4.5 | $0.00020 | $0.00258 |
Grade A, and why
token-cutout 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 2d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Token cutout
A prep helper that turns a background-baked token image (green/blue screen, a flat white or colored plate, or any busy background) into a transparent RGBA PNG ready to drop on the table — and, if asked, wires it into the live world as an actor's token art.
There is no MCP tool for this — the pixel work is a bundled script,
token_cutout.py (next to this file). This skill owns the judgment: which method, whether to keep the
cast shadow, verifying the edge, and the optional Foundry hand-off. The Foundry steps reuse the normal
tools: upload-asset (asset in) and set-actor-art (assign it).
Step 0 — Get the image and confirm the goal
Need a local file path (the script reads from disk, not from an uploaded asset). If the user only
gestured at "the token on my Desktop", find it with a glob first — and note the real extension: a
.jpg/.jpeg source has no alpha by definition, which is usually the whole reason we're here.
Step 1 — Pick the method
The script's --method auto (default) uses rembg if installed, else chroma. Override when you
know better:
- rembg (AI matte, U^2-Net) — the default and the right call for a character: soft edges, hair
wisps, thin details (bowstrings), and especially a cast shadow on the plate. It's also the
only option when the background is not a flat solid color (a scene, a gradient, clutter).
First use triggers a one-time ~176MB model download (
pip install "rembg[cpu]"). - chroma (offline, instant, deterministic) — best for a clean flat solid-color plate (classic
green/blue screen, or a uniform white/colored back). Auto-detects the key color from the four
corners. Prefer it when rembg isn't installed, when you want zero downloads, or for a batch where
every image shares the same clean plate. Pass
--color RRGGBBto force the key color if auto-detect is fooled by a subject that touches a corner.
When unsure for a single hero token, use rembg. For a bulk folder of identically-plated sprites, chroma is faster and more predictable.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed · +18 lines def7f77008c6
- 8d ago Changed · +31 lines · +19 tokens per session 3edfb431c4e6
- 11d ago First seen · 108 lines · 181 tokens per session scan A 29295c34c98f
token-cutout is a skill published in the GitHub repository Txpple/fvtt-mcp-molten5e (0 stars, last pushed 2d ago), licensed MIT. It adds 200 tokens to every session and 2,584 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…