pixellab-forge-mcp: Instructions file for Claude Code

CLAUDE.md

pixellab-forge-mcp CLAUDE.md is an instructions file for Claude Code from rabbitcannon/pixellab-forge-mcp. It costs 1,150 tokens per session, scanned C, original, MIT.

Repository-specific instructions for developing PixelLab Forge MCP, a server that connects agents to PixelLab's pixel-art API.

In plain words
What is it for?
They guide work on its 89 tools for image generation, characters, animation, tilesets, editing, rotation, API requests, retries, and saved output.
Why use it?
They explain the server's structure, API details, message format, image handling, and release rules so changes fit the project.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is rabbitcannon/pixellab-forge-mcp's own configuration. It tells Claude Code how to work on pixellab-forge-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pixellab-forge-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rabbitcannon/pixellab-forge-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/rabbitcannon/pixellab-forge-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/rabbitcannon/pixellab-forge-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.

agentmods badge for pixellab-forge-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rabbitcannon/pixellab-forge-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/rabbitcannon/pixellab-forge-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rabbitcannon/pixellab-forge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rabbitcannon/pixellab-forge-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.

agentmods 80×15 button for pixellab-forge-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rabbitcannon/pixellab-forge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rabbitcannon/pixellab-forge-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,150 This file is loaded in full into every session.
When invoked 1,150 The same file — it is already loaded in full.
Security scan C 2 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 $0.01150 $0.01150
Opus 5 $0.00575 $0.00575
Sonnet 5 $0.00230 $0.00230
Haiku 4.5 $0.00115 $0.00115

Measured 9d ago against content hash bc8f8b009d77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

pixellab-forge-mcp CLAUDE.md scanned grade C with 2 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 9d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

7. **Verify**: query the registry directly (the local `npm view` cache lags) — `curl -s https://registry.npmjs.org/pixellab-forge-mcp | python3 -c "import sys,json;print(json.load(sys.stdin)['dist-tags']['latest'])"`.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

7. **Verify**: query the registry directly (the local `npm view` cache lags) — `curl -s https://registry.npmjs.org/pixellab-forge-mcp | python3 -c "import sys,json;print(json.load(sys.stdin)['dist-tags']['latest'])"`.
CLAUDE.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PixelLab Forge MCP

MCP server for the PixelLab pixel art generation API. 89 tools covering image generation, characters, animation, tilesets, editing, rotation, and more.

Project Structure

src/
  index.ts       - MCP server setup, tool registration via low-level Server API
  tools.ts       - All 89 tool definitions with JSON schemas and handlers
  api-client.ts  - PixelLab REST client with auto-polling, retry, and job logging
  job-log.ts     - Persistent job log for crash recovery (stored in OS temp dir)
  save-images.ts - Auto-saves base64 images from responses to ./pixellab-forge-output/

Key Architecture Decisions

  • Uses the low-level Server class from @modelcontextprotocol/sdk (not McpServer) because the high-level API requires Zod schemas. We use raw JSON Schema objects instead.
  • SDK v1.29 uses newline-delimited JSON for stdio transport, not Content-Length framing.
  • All tool schemas are verified against the OpenAPI spec at https://api.pixellab.ai/v2/openapi.json. Key naming:
    • v2 endpoints use no_background and seed (NOT guidance_scale, remove_background, or ai_freedom)
    • Character/object/tileset endpoints use text_guidance_scale, outline/shading/detail, color_image
    • Legacy endpoints (pixflux, bitforge, skeleton, rotate, inpaint) use Python SDK field names
  • Background jobs auto-poll every 2s for up to 10 minutes with 3 retries on network failure.
  • Job IDs are logged to stderr and persisted to $TMPDIR/pixellab-forge/jobs.json for recovery.
  • Generated images are auto-saved to ./pixellab-forge-output/ in the working directory.

Git Identity

Use rabbitcannon for all commits. The local git config is already set:

Do NOT add co-author attributions to commits.

Releasing

The canonical, detailed checklist is RELEASING.md — follow it. Summary of the actual flow:

  1. Bump version: npm version <major|minor|patch> --no-git-tag-version (npm rejects a duplicate version).
  2. Verify: npm run buildnpm test (expect all passing) → npm publish --dry-run.
  3. Update CHANGELOG.md — add a ## [X.Y.Z] - YYYY-MM-DD entry (newest first, grouped Added/Changed/Fixed/Security) plus its link reference at the bottom.
  4. Commit via PRmain is protected by the "Main protection" ruleset, so do not push to main directly. Branch → commit (vX.Y.Z - <summary>, no co-author trailers) → push → gh pr creategh pr merge --squash --admin --delete-branch (the Repository-admin role is a standing bypass actor).
  5. GitHub release: gh release create vX.Y.Z --target main --title "vX.Y.Z" --notes "<notes>". This auto-publishes the GitHub Packages mirror (@rabbitcannon/pixellab-forge-mcp) via .github/workflows/publish-gpr.yml. Optionally attach the tarball: npm pack --pack-destination /tmp/ && gh release upload vX.Y.Z /tmp/pixellab-forge-mcp-X.Y.Z.tgz.
  6. Publish to npmjs.org (manual, 2FA-gated): npm publish --otp=<code>. This is the canonical package users install; it is intentionally not automated.
  7. Verify: query the registry directly (the local npm view cache lags) — curl -s https://registry.npmjs.org/pixellab-forge-mcp | python3 -c "import sys,json;print(json.load(sys.stdin)['dist-tags']['latest'])".

Read the full file on GitHub · 70 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. 9d ago First seen · 70 lines · 1,150 tokens per session scan C bc8f8b009d77

Subscribe to this mod's changes

pixellab-forge-mcp CLAUDE.md is an instructions file published in the GitHub repository rabbitcannon/pixellab-forge-mcp (1 stars, last pushed 26d ago), licensed MIT. It adds 1,150 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens