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 | $0.00139 | $0.01037 |
| Opus 5.5 | $0.00056 | $0.00415 |
| Sonnet 5.5 | $0.00028 | $0.00207 |
| Haiku 4.5 | $0.00014 | $0.00104 |
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 1mo 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Token cutout (Foundry install half)
The cutout itself moved to fvtt-mcp-artificer on 2026-09-19. Call cutout-image there
(chroma key for flat plates, rembg AI matte fallback, 512 square, magenta preview). Tokens
generated or edited with generate-image / edit-image in kind: "token" arrive already cut.
There is no script in this folder any more; token_cutout.py lives at
fvtt-mcp-artificer/scripts/token_cutout.py and the tool is its only caller.
Read the *_preview.png the tool reports before trusting the edge: a colour halo means a fringe
survived (ask for erode: 1 or method: "rembg"); eaten hair or a thin blade means over-cut
(prefer rembg). Coverage near 0% or 100% means the key was misread; pass color.
Put it in Foundry
upload-assetthe PNG toworlds/<world>/assets/tokens/<name>.png(get<world>fromget-world-info).- Assign it.
set-actor-artsets the portrait AND the prototype token in one call —imagePathis the portrait and doubles as the token texture unlesstokenImagePathoverrides it. So by default both get set; say so plainly before you run it. Find the actor withlist-actors/get-actor.- Token-only, keeping the existing portrait, IS possible — read the current portrait back and
pass it straight through.
export-actorto a scratch path dumps the full document (img,prototypeToken,folder, ownership), so:imagePath= theimgyou just read,tokenImagePath= the new cutout. The portrait write becomes a no-op and only the token changes. (export-actoris also how you tell two same-named actors apart —foldergives it away.) - Portrait-only is the plain
applyToToken: false.
- Token-only, keeping the existing portrait, IS possible — read the current portrait back and
pass it straight through.
- Reset the inherited prototype config —
set-actor-artonly swaps the texture. A module or compendium actor keeps the rest of its prototype token exactly as imported, so fresh art lands on someone else's settings. The 2024dnd-monster-manualactors ship a dynamic ring on andtexture.scaleX/scaleYat 2 (their art is a small subject on a big plate; a 512-square cutout is already trimmed and centred, so 2 overflows the token's footprint and the ring draws a dark disc under it) — andlockRotation: true, so the token won't turn to face its movement like every other token at the table. After every art swap,update-actorwithtokenScale: 1,tokenRing: false,tokenAutoRotate: true(house rules —_shared/authoring-policy.mdrule 10). - Prototype vs placed. Setting the prototype only affects newly dropped tokens. A copy already
sitting on a scene won't change —
list-tokensthe scene and patch each withupdate-token(scale,ring,lockRotation: false), or have the user delete + re-drop it. - Check which way the art faces before you enable auto-rotate. Foundry treats the top of the image as the token's front at rotation 0, so art drawn head-down (or side-on) will move backwards once auto-rotate is live. Look at the cutout and say so — the fix is rotating the source PNG, which is the user's call, not a silent edit.
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.
- 1mo ago Changed · -100 lines · -61 tokens per session ecc6d5be9173
- 1mo ago Changed · +18 lines def7f77008c6
- 2mo ago Changed · +31 lines · +19 tokens per session 3edfb431c4e6
- 2mo 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 1mo ago), licensed MIT. It adds 139 tokens to every session and 1,037 once invoked, about $0.0006 per session on Opus 5.5. 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.
token-cutout compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| token-cutoutTxpple/fvtt-mcp-molten5e | Skill | 0 | 1mo ago | MIT | A | 139 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |