pixel-art

pixel-art is a skill for Claude Code, Codex from Retro-Diffusion/retro-diffusion-mcp. It costs 93 tokens per session (1,373 once invoked), scanned A, original, MIT.

A tool for creating and repairing pixel art, such as game characters, sprites, animations, tilesets, and other grid-based game images. It uses Retro Diffusion to keep pixels aligned to a controlled grid and palette.

In plain words
What is it for?
Use it to make game sprites, sprite-sheet animations, tilesets, retro or 8-bit assets, Minecraft-style items, and repaired pixel art.
Why use it?
It helps when ordinary image generation produces images that only look pixelated but do not have clean, usable pixels. It can also restore the original pixel grid in art that was enlarged or blurred.

Skill for Claude CodeCodex

Part of the pixel-art plugin — 1 skill, 1 MCP server shipped together

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.

agentmods
npx agentmods add skills/retro-diffusion/retro-diffusion-mcp/pixel-art
Any agent
npx skills add Retro-Diffusion/retro-diffusion-mcp --skill pixel-art
Clone the repo
git clone --depth 1 https://github.com/Retro-Diffusion/retro-diffusion-mcp

Made for: Claude Code, Codex.

Or install pixel-art, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 pixel-art

README.md
[![agentmods](https://agentmods.dev/badge/skills/retro-diffusion/retro-diffusion-mcp/pixel-art.svg)](https://agentmods.dev/skills/retro-diffusion/retro-diffusion-mcp/pixel-art)
Your own site
<a href="https://agentmods.dev/skills/retro-diffusion/retro-diffusion-mcp/pixel-art"><img src="https://agentmods.dev/badge/skills/retro-diffusion/retro-diffusion-mcp/pixel-art.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,373 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00093 $0.01373
Opus 5 $0.00046 $0.00687
Sonnet 5 $0.00019 $0.00275
Haiku 4.5 $0.00009 $0.00137

Measured today against content hash bae20f62470e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pixel-art 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 today.

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.

plugins/pixel-art/skills/pixel-art/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generating and repairing pixel art with Retro Diffusion

Retro Diffusion produces real, grid-aligned, palette-controlled pixel art — not "pixel-art style" images. The MCP server exposes tools to browse styles, estimate costs (free), generate, and recover the native grid of enlarged or softened art.

Setup (only if tools are unavailable or auth fails)

  1. The user needs an API key: free account at https://retrodiffusion.ai, then create a key at https://retrodiffusion.ai/app/devtools (keys start with rdpk-).
  2. This plugin reads the key from the RD_API_KEY environment variable. Have the user set it (e.g. in their shell profile) and restart Claude Code, or use the authenticate tool with the key directly.
  3. New accounts include free starter credits. Balance is prepaid; check it with get_balance.

Core workflow — always in this order

  1. Pick a style: call list_available_styles (filterable by model or tab). Each style declares its own size limits, batch limits, and whether it needs an input image or supports reference images. Never guess limits. Prefer RD Pro styles (rd_pro__*) for the highest quality.
  2. Estimate first: call estimate_inference_cost — it is free and returns the exact price. Tell the user the cost before generating anything expensive (RD Pro is $0.18/image; animations up to $0.25).
  3. Generate with create_inference for stills. It returns hosted output_urls plus a recovery request_id. If URLs are missing or expired after a successful call, call get_inference_result(request_id) — never repeat the paid generation automatically. For animations or batches use start_inference_job and poll get_inference_job every 2–5 seconds — they are long-running. If the response of start_inference_job is lost (timeout/disconnect) before you get a task_id, call list_inference_jobs to find the accepted job and resume polling it — never blindly re-submit, since the lost job was already accepted and charged.
  4. Repair the pixel grid when needed with fix_pixel_art before other edits. Use it for enlarged, softened, AI-rendered, or compressed pixel art. Choose the standard engine for native Rust grid detection or the neural engine for neural reconstruction with optional target width and height.
  5. Post-process with run_edit_tool: background_remover and color_style_transfer cost $0.01; color_reducer, palette_converter, pixel_correction, k_centroid_downscale, and rotate are free; image_edit, inpainting, outpainting, and seam_tiling are premium ($0.18). estimate_edit_tool_cost is always free.

Read the full file on GitHub · 52 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. today Changed bae20f62470e
  2. 4d ago First seen · 52 lines · 93 tokens per session scan A a252c6bc7a2f

Subscribe to this mod's changes

pixel-art is a skill published in the GitHub repository Retro-Diffusion/retro-diffusion-mcp (2 stars, last pushed 2d ago), licensed MIT. It adds 93 tokens to every session and 1,373 once invoked, about $0.0005 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

html-ppt-zhangzara-8-bit-orbit

A gamer's journey building a retro-arcade collection — the obsession, the hunt, and what the machines came to mean. Built as a decision-grade story deck for friends, hobby community.

nexu-io/open-design · 53 tokens

game-art

Game art principles. Visual style selection, asset pipeline, animation workflow.

vudovn/ag-kit · 17 tokens

asset-pipeline

Generate game-ready 3D assets for World of ClaudeCraft with the AI asset pipeline (Tripo API + optional gpt-image-2). Use when asked to create or generate game assets, a new weapon model, a prop, a creature or mob model, a player-class skin, or any 3D model or texture for the game. Drives…

levy-street/world-of-claudecraft · 0 tokens

sprite-gen

Generate clean 2D game sprites and animation atlases with a component-row pipeline: base identity, numeric sprite-request SSoT, per-state layout guides, image-gen row strips, chroma-key alpha cleanup, connected-component frame extraction, cell-based atlas composition, QA reports, and runtime manifest framelayout. Its…

aldegad/sprite-gen · 291 tokens

woc-image-to-glb

Turn a reference image into a shipping World of ClaudeCraft GLB through the img2threejs intake gates and the repo's deterministic export, optimize, fingerprint, and test pipeline. Use when asked to create, replace, rebuild, re-export, or re-pin a world asset (prop, furniture, building, landmark, stall, service object)…

levy-street/world-of-claudecraft · 83 tokens

audio-design

Implement game audio practice — bus/mixer architecture and gain in decibels, ducking (sidechain), adaptive/dynamic music via layering and re-sequencing, SFX variation, and beat synchronization. Engine-neutral. Use when the user mentions audio mixing, audio buses, adaptive/dynamic music, ducking, SFX variation, music…

gamedev-skills/awesome-gamedev-agent-skills · 81 tokens