pixel-plugin CLAUDE.md

Project instructions for a Claude Code plugin that connects pixel-art work in Aseprite with a pixel-mcp server. The plugin includes skills, commands, and platform-specific support for the server.

In plain words
What is it for?
Understanding the plugin layout, checking its components and dependencies, and working on the connection between Claude Code, pixel-mcp, and Aseprite.
Why use it?
It documents how the plugin’s parts fit together and what software it depends on. This gives contributors a shared reference when developing or reviewing the project.

Instructions file

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 instructions/willibrandon/pixel-plugin/claude-md
Clone the repo
git clone --depth 1 https://github.com/willibrandon/pixel-plugin
Per session 2,199 This file is loaded in full into every session.
When invoked 2,199 The same file — it is already loaded in full.
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 $0.02199 $0.02199
Opus 5 $0.01099 $0.01099
Sonnet 5 $0.00440 $0.00440
Haiku 4.5 $0.00220 $0.00220

Measured 2d ago against content hash 57725c480e63, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pixel-plugin CLAUDE.md 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.

CLAUDE.md · 286 lines

How it starts

The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is a Claude Code plugin that integrates Aseprite pixel art capabilities through the pixel-mcp Model Context Protocol server. The plugin enables pixel art creation, editing, and export using natural language commands.

Plugin Name: pixel-plugin Version: 0.1.0 Type: Claude Code Plugin (Skills + Commands + MCP Integration) Dependencies: pixel-mcp server (Go binary), Aseprite v1.3.0+

Architecture

The plugin follows a layered architecture:

  1. User Layer: Natural language or slash commands in Claude Code
  2. Plugin Layer: Skills (model-invoked) and Commands (user-invoked)
  3. MCP Layer: pixel-mcp server (40+ tools)
  4. Application Layer: Aseprite CLI interactions

Key Integration Point: The plugin bundles pre-compiled pixel-mcp binaries and provides a platform-detection wrapper (bin/pixel-mcp) that selects the correct binary for macOS, Linux, or Windows.

Directory Structure

pixel-plugin-plugin/
├── .claude-plugin/
│   └── plugin.json                 # Plugin manifest
├── skills/                         # Model-invoked Skills
│   ├── pixel-art-creator/
│   │   ├── SKILL.md               # Required: frontmatter + instructions
│   │   ├── reference.md           # Technical specs
│   │   └── examples.md            # Concrete examples
│   ├── pixel-art-animator/
│   ├── pixel-art-professional/
│   └── pixel-art-exporter/
├── commands/                       # User-invoked slash commands
│   ├── pixel-new.md
│   ├── pixel-palette.md
│   ├── pixel-export.md
│   ├── pixel-setup.md
│   └── pixel-help.md
├── bin/                            # MCP server binaries
│   ├── pixel-mcp               # Platform detection wrapper
│   ├── pixel-mcp-darwin-amd64
│   ├── pixel-mcp-darwin-arm64
│   ├── pixel-mcp-linux-amd64
│   ├── pixel-mcp-linux-arm64
│   └── pixel-mcp-windows-amd64.exe
├── config/
│   ├── pixel-mcp-config.json   # Template for users
│   ├── detect-aseprite.sh         # Path detection helper
│   └── README.md                  # Configuration guide
├── .mcp.json                       # MCP server integration
├── docs/
│   ├── KNOWN_ISSUES.md            # Known issues and limitations
│   └── TESTING_CHECKLIST.md       # Validation checklist
├── test-outputs/                   # Test output directory
├── CHANGELOG.md                    # Version history
├── CONTRIBUTING.md                 # Contribution guidelines
├── LICENSE                         # MIT License
└── README.md                       # User documentation

Read the full file on GitHub · 286 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. 2d ago First seen · 286 lines · 2,199 tokens per session scan A 57725c480e63

Subscribe to this mod's changes

pixel-plugin CLAUDE.md is an instructions file published in the GitHub repository willibrandon/pixel-plugin (302 stars, last pushed 10mo ago), licensed MIT. It adds 2,199 tokens to every session, about $0.0110 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 2026-08-30.