What is PixelLabRat AGENTS.md?

Contribution instructions for PixelLabRat, a Bun and TypeScript workspace for generating and managing pixel art.

Use them when navigating the packages, running type checks, checking the project store or MCP server, or working on the desktop app.

They explain the project layout, available checks, and conventions so changes fit the repository and can be tested correctly.

How DasDarki/PixelLabRat configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to DasDarki/PixelLabRat. 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/DasDarki/PixelLabRat/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/DasDarki/PixelLabRat

Made for: Codex, OpenCode.

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/dasdarki/pixellabrat/agents-md/github.svg)](https://agentmods.dev/instructions/dasdarki/pixellabrat/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/dasdarki/pixellabrat/agents-md"><img src="https://agentmods.dev/badge/instructions/dasdarki/pixellabrat/agents-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/dasdarki/pixellabrat/agents-md"><img src="https://agentmods.dev/badge/instructions/dasdarki/pixellabrat/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 859 This file is loaded in full into every session.

When invoked 859 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	$0.00859	$0.00859
Opus 5.5	$0.00344	$0.00344
Sonnet 5.5	$0.00172	$0.00172
Haiku 4.5	$0.00086	$0.00086

Measured 2mo ago against content hash e840450e3082, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

PixelLabRat AGENTS.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 2mo 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.

AGENTS.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working on PixelLabRat

Guidance for AI agents (and humans) contributing to this repo. If you only want to use PixelLabRat to generate art from Claude Code, read docs/using-with-claude-code.md instead.

Layout

A Bun workspace. TypeScript everywhere.

packages/
  core/    PixelLab API client + typed wrapper, auth, async job polling
  store/   project store (folders + JSON), the style contract, generation logic
  mcp/     the MCP server (Claude Code / any MCP client)
  agent/   the embedded Claude agent — tool defs + system prompt
  app/     Electron + Vue 3 desktop frontend

A project is a folder, not a database row: a manifest, a few JSON files (library.json, characters.json, …), and the PNGs. The store reads and writes those directly.

Commands

bun run typecheck                    # core/store/mcp/agent
cd packages/app && bun run typecheck # the app (vue-tsc) — run separately
bun run store:check                  # store round-trip, offline
bun run mcp:check                    # MCP round-trip, offline
bun run agent:check                  # agent tools + prompt, offline
bun run app:dev / app:build          # the desktop app

The *:check scripts and the typechecks are offline and free — use them. Do not call the real PixelLab API in tests; generations cost money. bun run smoke (balance only) is the cheapest live sanity check.

Adding a PixelLab capability

Generation features flow through the layers in this order, and the agent and MCP surfaces are kept at parity:

core (packages/core/src/pixellab.ts) — add the method (submit + poll for async jobs, or a direct call for sync ones).
store (packages/store/src/generate.ts) — add the project-aware function that applies the style contract and persists results via project.ts.
agent (packages/agent/src/tools.ts) and mcp (packages/mcp/src/server.ts) — expose it as a tool in both. They should stay in sync; if you add a tool to one, add it to the other.
app — thread it through shared/api.ts → main/ipc.ts → preload/index.ts → renderer/store.ts → the relevant component.

Read the full file on GitHub · 76 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.

2mo ago First seen · 76 lines · 859 tokens per session scan A e840450e3082

Subscribe to this mod's changes

PixelLabRat AGENTS.md is an instructions file published in the GitHub repository DasDarki/PixelLabRat (0 stars, last pushed 5mo ago), licensed MIT. It adds 859 tokens to every session, about $0.0034 per session on Opus 5.5. 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.

Creative and media

PixelLabRat AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
PixelLabRat AGENTS.mdDasDarki/PixelLabRat	Instructions file	0	5mo ago	MIT	A	859	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

PixelLabRat: Instructions file for Codex