agentmods.dev

claude-draws: Instructions file for Claude Code

CLAUDE.md

claude-draws CLAUDE.md is an instructions file for Claude Code from atbaker/claude-draws. It costs 4,633 tokens per session, scanned A, original, MIT.

A project guide for Claude Draws, an automated art workflow in which browser automation asks Claude for Chrome to create illustrations in a Kid Pix-style app and publishes them in a SvelteKit gallery.

In plain words
What is it for?
Use it when working on the submission form, browser automation, OBS recording, Temporal workflows, BAML extraction, Cloudflare storage or Workers, or the gallery.
Why use it?
It explains how submissions, workflow orchestration, recording, text extraction, image storage, metadata, and the gallery connect across the monorepo, a repository containing multiple related projects.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is atbaker/claude-draws's own configuration. It tells Claude Code how to work on claude-draws 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 claude-draws configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/.../downloads/recordings/2025-11-04.

not rated 11 7mo ago A scan 4,633 tokens original MIT
View the source file atbaker/claude-draws
Reuse

Borrowing it

Nothing to install: this file belongs to atbaker/claude-draws. 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/atbaker/claude-draws/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/atbaker/claude-draws

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 claude-draws CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/atbaker/claude-draws/claude-md.svg)](https://agentmods.dev/instructions/atbaker/claude-draws/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/atbaker/claude-draws/claude-md"><img src="https://agentmods.dev/badge/instructions/atbaker/claude-draws/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,633 This file is loaded in full into every session.
When invoked 4,633 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 5.1 $0.04633 $0.04633
Opus 5 $0.02316 $0.02316
Sonnet 5 $0.00927 $0.00927
Haiku 4.5 $0.00463 $0.00463

Measured 6d ago against content hash 61ed698dc8e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

claude-draws 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 6d 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 · 403 lines

How it starts

The opening of the file, as written. The whole thing — 403 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

Claude Draws is an automated art project where Claude for Chrome creates crowdsourced illustrations using Kid Pix, sourced from user submissions at claudedraws.xyz. The complete workflow:

  1. Web form (claudedraws.xyz/submit) accepts art requests and stores them in Cloudflare D1
  2. Browser automation (Playwright + CDP) submits prompts to Claude for Chrome extension
  3. OBS recording captures the entire artwork creation process via WebSocket control
  4. Claude draws in a modified Kid Pix JavaScript app (served from local directory, not included in this repo)
  5. Temporal workflows orchestrate the post-processing pipeline
  6. BAML extraction parses Claude's title and artist statement from the final response
  7. Cloudflare R2 stores artwork images and creation videos
  8. Cloudflare D1 stores artwork metadata (including video URLs) in SQLite database
  9. SvelteKit gallery (gallery/) displays all artworks with videos at claudedraws.xyz with SSR-on-demand
  10. Cloudflare Workers hosts the gallery site

Repository Structure (Monorepo)

This repository uses a monorepo structure to organize different components:

claude-draws/
├── backend/              # Python backend (CLI, Temporal workflows, BAML)
│   ├── claudedraw/      # CLI tool for browser automation
│   ├── workflows/       # Temporal workflow definitions
│   ├── worker/          # Temporal worker process
│   ├── baml_src/        # BAML definitions for metadata extraction
│   ├── pyproject.toml   # Python dependencies
│   └── Dockerfile.worker # Container for worker
├── gallery/             # SvelteKit frontend (SSR-on-demand with D1 API)
├── .chrome-data/        # Chrome profile for automation (gitignored)
├── downloads/           # Temporary artwork storage (gitignored)
├── docs/               # Documentation
└── docker-compose.yml  # Orchestrates all services

Read the full file on GitHub · 403 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. 6d ago First seen · 403 lines · 4,633 tokens per session scan A 61ed698dc8e7

Subscribe to this mod's changes

claude-draws CLAUDE.md is an instructions file published in the GitHub repository atbaker/claude-draws (11 stars, last pushed 7mo ago), licensed MIT. It adds 4,633 tokens to every session, about $0.0232 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.

Browser automationCreative and media
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 · 5,182 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

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

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