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.
npx agentmods add instructions/willibrandon/pixel-mcp/claude-mdgit clone --depth 1 https://github.com/willibrandon/pixel-mcpWrote 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/instructions/willibrandon/pixel-mcp/claude-md)<a href="https://agentmods.dev/instructions/willibrandon/pixel-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/willibrandon/pixel-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.02726 | $0.02726 |
| Opus 5 | $0.01363 | $0.01363 |
| Sonnet 5 | $0.00545 | $0.00545 |
| Haiku 4.5 | $0.00273 | $0.00273 |
Grade A, and why
pixel-mcp 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 4d 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 — 228 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
An MCP (Model Context Protocol) server implementation in Go that exposes Aseprite's pixel art and animation capabilities through programmatic access. The server integrates with Aseprite's command-line interface and Lua scripting API to enable AI assistants to create and manipulate sprites.
Build Commands
# Build the server binary
make build
# or: go build -o bin/pixel-mcp ./cmd/pixel-mcp
# Run tests
make test
# or: go test -v -race -cover ./...
# Run integration tests (requires real Aseprite)
go test -tags=integration ./...
# Generate test coverage report
make test-coverage
# Run linters
make lint
# Clean build artifacts
make clean
# Install binary
make install
Configuration Requirements
CRITICAL: This project requires explicit configuration - no automatic discovery or environment variables.
All operations require a configuration file at ~/.config/pixel-mcp/config.json:
{
"aseprite_path": "/absolute/path/to/aseprite",
"temp_dir": "/tmp/pixel-mcp",
"timeout": 30,
"log_level": "info",
"log_file": "",
"enable_timing": false
}
Configuration fields:
aseprite_path(required): Absolute path to Aseprite executabletemp_dir(optional): Temporary directory, defaults to/tmp/pixel-mcptimeout(optional): Command timeout in seconds, defaults to 30log_level(optional): Verbosity level (debug,info,warn,error), defaults toinfolog_file(optional): Path to persistent log file, empty means stderr onlyenable_timing(optional): Enable request tracking/timing, defaults tofalse
The aseprite_path MUST be an absolute path to a real Aseprite executable. The project does NOT:
- Auto-discover Aseprite installations
- Use environment variables for Aseprite path
- Search system PATH for Aseprite
Testing Philosophy
ALL tests use real Aseprite - no mocks, stubs, or fakes for Aseprite integration.
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.
- 4d ago First seen · 228 lines · 2,726 tokens per session scan A bfbac2c4ab98
pixel-mcp CLAUDE.md is an instructions file published in the GitHub repository willibrandon/pixel-mcp (135 stars, last pushed 10mo ago), licensed MIT. It adds 2,726 tokens to every session, about $0.0136 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.
Other instructions, from other repositories
ase-deliver AGENTS.md
AGENTS.md instructions for ylty1516/ase-deliver, covering asedeliver — contract for any ai, what this tool is, do this, in order, templates and hard visual rules.
pixel-plugin CLAUDE.md
Instructions for willibrandon/pixel-plugin, covering claude.md, project overview, architecture, directory structure and plugin component specifications.
ase-deliver CLAUDE.md
Claude Code instructions for ylty1516/ase-deliver: Follow AGENTS.md. Compile sprites with python -m asedeliver. The deliverable is always out/ .aseprite.
OpenGeometry AGENTS.md
Instructions for OpenGeometry-io/OpenGeometry, covering agents.md, 1. project identity, 2. architecture, runtime flow and build pipeline.
Claw3D AGENTS.md
Instructions for iamlukethedev/Claw3D, covering agent instructions, cursor cloud specific instructions, service overview, running the app and lint, typecheck, and tests.
pixtuoid copilot-instructions.md
Copilot instructions for IvanWng97/pixtuoid, covering github copilot instructions — pixtuoid, architecture invariants (never break these), conventions and build & test.