What is pixel-surgeon-mcp CLAUDE.md?

Project instructions for Pixel Surgeon MCP, an image-generation server that can use configured Gemini or OpenAI image providers. They describe its architecture, commands, models, and how to add providers.

Working on Pixel Surgeon MCP, including building or starting it, understanding its image-provider setup, and adding a new provider.

They give an agent the repository’s conventions for building, running, and extending the server.

How j-east/pixel-surgeon-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to j-east/pixel-surgeon-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/j-east/pixel-surgeon-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/j-east/pixel-surgeon-mcp

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/j-east/pixel-surgeon-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/j-east/pixel-surgeon-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/j-east/pixel-surgeon-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/j-east/pixel-surgeon-mcp/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/j-east/pixel-surgeon-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/j-east/pixel-surgeon-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,087 This file is loaded in full into every session.

When invoked 1,087 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01087	$0.01087
Opus 5	$0.00544	$0.00544
Sonnet 5	$0.00217	$0.00217
Haiku 4.5	$0.00109	$0.00109

Measured 11d ago against content hash 77cc8c8943e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pixel-surgeon-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 11d 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 · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pixel Surgeon MCP Server

Quick Reference

Build: npm run build (TypeScript -> dist/)
Dev: npm run dev (tsx watch mode)
Start: npm run start (run compiled server)
Images dir: ~/Pictures/pixel-surgeon

Architecture

MCP server on stdio transport. Single source file: src/index.ts.

Multi-provider image generation via ImageProvider interface. Each provider implements generate() and edit(). Providers are registered at startup based on available API keys.

Providers

Gemini (GeminiProvider) — Google's nanobanana2 pipeline. Gemini 3.1 Flash Image (paid) with auto-fallback to 2.5 Flash Image (free) on billing errors. Supports 9 aspect ratios and 4 image sizes.
OpenAI (OpenAIProvider) — GPT Image 1 and GPT Image 2. gpt-image-1 maps to 3 fixed sizes; gpt-image-2 supports flexible resolutions (true 2K/4K at all 9 aspect ratios). Image size param mapped to quality (medium/high). Prefer gpt-image-2 for text-heavy images — it has dramatically better text rendering.

Adding a new provider

Implement ImageProvider interface (generate + edit)
Add model entry to MODELS registry with provider field
Register in main() based on env var availability

Flash chokes on text-heavy images. The fix tools exploit this by sending smaller regions.

Video generation uses Veo 3 (async API with polling, Gemini only). Supports 16:9 and 9:16, 5s or 8s duration. Generates both video and ambient audio.

Tools (9)

generate_image / generate_images — text-to-image (single / parallel batch)
- generate_images applies a single style to ALL images in the batch. To generate images in different styles, use separate generate_image calls (they can run in parallel).
generate_video — text-to-video via Veo 3 (async polling, 1-3 min, generates audio)
edit_image — edit existing image with instructions
list_images / save_image — file management
fix_image — grid-based tile repair (2x2, 3x3, etc.)
fix_region — targeted region repair (percentage coords, auto aspect ratio snap)
interactive_fix — browser crop UI with multi-shot (1-5 parallel shots, user picks best)

Read the full file on GitHub · 64 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.

11d ago First seen · 64 lines · 1,087 tokens per session scan A 77cc8c8943e6

Subscribe to this mod's changes

pixel-surgeon-mcp CLAUDE.md is an instructions file published in the GitHub repository j-east/pixel-surgeon-mcp (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,087 tokens to every session, about $0.0054 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.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

pixel-surgeon-mcp: Instructions file for Claude Code