transparent-cutout-cleanup

transparent-cutout-cleanup is a skill for Claude Code, Codex from 0xheycat/isometric-game-skills. It costs 29 tokens per session (449 once invoked), scanned A, original, MIT.

A process for removing backgrounds from generated sprites and saving them as clean images with transparent edges. It addresses halos, fringes, jagged borders, and leftover background pixels.

In plain words
What is it for?
It helps remove backgrounds in batches, inspect edges, remove color contamination, adjust transparency when needed, and verify PNGs on light and dark backgrounds.
Why use it?
Simple background removal can leave a visible colored outline, especially when a sprite is placed on a dark or contrasting tile. Cleaning the edge makes the sprite fit its surroundings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps remove backgrounds in batches, inspect edges, remove color contamination, adjust transparency when needed, and verify PNGs on light and dark backgrounds.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/0xheycat/isometric-game-skills/transparent-cutout-cleanup
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add 0xheycat/isometric-game-skills --skill transparent-cutout-cleanup
Clone the repo
git clone --depth 1 https://github.com/0xheycat/isometric-game-skills

Made for: Claude Code, Codex.

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 transparent-cutout-cleanup

README.md
[![agentmods](https://agentmods.dev/badge/skills/0xheycat/isometric-game-skills/transparent-cutout-cleanup/github.svg)](https://agentmods.dev/skills/0xheycat/isometric-game-skills/transparent-cutout-cleanup)
Your own site
<a href="https://agentmods.dev/skills/0xheycat/isometric-game-skills/transparent-cutout-cleanup"><img src="https://agentmods.dev/badge/skills/0xheycat/isometric-game-skills/transparent-cutout-cleanup/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 transparent-cutout-cleanup

Your own site · 80×15
<a href="https://agentmods.dev/skills/0xheycat/isometric-game-skills/transparent-cutout-cleanup"><img src="https://agentmods.dev/badge/skills/0xheycat/isometric-game-skills/transparent-cutout-cleanup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 449 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 $0.00029 $0.00449
Opus 5 $0.00015 $0.00225
Sonnet 5 $0.00006 $0.00090
Haiku 4.5 $0.00003 $0.00045

Measured 13d ago against content hash c425945a1019, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

transparent-cutout-cleanup 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 13d 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.

skills/transparent-cutout-cleanup/SKILL.md · 51 lines

What it actually says

Transparent Cutout Cleanup

Overview

AI-generated sprites come on a background. Naive removal leaves a colored halo or jagged edge that screams amateur when tiles are placed together. This skill produces clean, premultiplied-safe alpha cutouts.

When to Use

  • Any generated sprite needs a transparent background.
  • Placed sprites show a white/gray halo or fringe.
  • Edges look jagged or have leftover background color.

Process

  1. Generate on a PLAIN flat background (easier to key out than a busy one).
  2. Use a background-removal model (e.g. InSPyReNet / rembg) rather than a hard color key.
  3. Inspect edges at 400% zoom for halo or fringe pixels.
  4. Defringe / decontaminate edge color so no background tint remains.
  5. Erode the alpha by 1px if a faint halo persists.
  6. Save as PNG with straight alpha; verify on both light and dark backgrounds.
  7. Batch the cleaned sprites for the atlas packer.

Pair this with the ComfyUI rembg node in seamless-isometric-terrain/scripts.

Rationalizations (Stop Lying to Yourself)

Excuse Reality
"A white halo is barely visible" On a dark tile it is glaring. Defringe every sprite.
"Hard color-key is faster" It eats anti-aliased edges and looks jagged. Use a proper matting model.

Red Flags - STOP if you catch yourself:

  • Visible halo/fringe when placed on a contrasting background.
  • Jagged, aliased cutout edges.
  • Background color contaminating semi-transparent pixels.

Verification

You are NOT done until every box is checked:

  • Edges are clean at 400% zoom on light AND dark backgrounds.
  • No background-color contamination on semi-transparent pixels.
  • All sprites exported as straight-alpha PNG.
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. 13d ago First seen · 51 lines · 29 tokens per session scan A c425945a1019

Subscribe to this mod's changes

transparent-cutout-cleanup is a skill published in the GitHub repository 0xheycat/isometric-game-skills (15 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 449 once invoked, about $0.0001 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

seedance-pipeline

Integrate Seedance 2.0 with ComfyUI nodes and post-processing chains covering upscale, frame interpolation, color grade, composite, and metadata cleanup. Use when building automated video pipelines, connecting Seedance to external tools, or finishing and delivering a generated video clip.

Kingdaddy007/my-os · 60 tokens

comfyui-gateway

REST API gateway for ComfyUI servers. Workflow management, job queuing, webhooks, caching, auth, rate limiting, and image delivery (URL + base64).

ratnesh-maurya/cursor-claude-personas · 41 tokens

model-compatibility

Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.

artokun/comfyui-mcp · 47 tokens

data-charts-tako

Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.

gooseworks-ai/goose-skills · 35 tokens

apollo-lead-finder

Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.

gooseworks-ai/goose-skills · 51 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens