What is ComfyUI_Detonate CLAUDE.md?

A planned ComfyUI custom-node package for compositing, the process of combining visual layers, with tools inspired by professional VFX software such as Nuke and DaVinci Fusion. It is intended to support traditional compositing alongside AI image generation.

Use it to plan and build Python nodes for ComfyUI, organize the proposed 43-node roadmap, and work with libraries such as PyTorch, NumPy, and Pillow.

It gives agents a clear project vision, technology choices, reference documents, and implementation priorities before development begins.

How aTanguay/ComfyUI_Detonate configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to aTanguay/ComfyUI_Detonate. 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/aTanguay/ComfyUI_Detonate/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/aTanguay/ComfyUI_Detonate

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/atanguay/comfyui_detonate/claude-md/github.svg)](https://agentmods.dev/instructions/atanguay/comfyui_detonate/claude-md)

Your own site

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

Per session 2,994 This file is loaded in full into every session.

When invoked 2,994 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	$0.02994	$0.02994
Opus 5	$0.01497	$0.01497
Sonnet 5	$0.00599	$0.00599
Haiku 4.5	$0.00299	$0.00299

Measured 9d ago against content hash 5d20190e8915, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ComfyUI_Detonate 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 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.

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 · 363 lines

How it starts

The opening of the file, as written. The whole thing — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guide for Claude - ComfyUI_Detonate Project

This document provides context for future Claude sessions working on this project.

Project Summary

ComfyUI_Detonate is a custom node package for ComfyUI that brings professional compositing tools from Nuke and DaVinci Fusion to the ComfyUI platform. The goal is to provide VFX compositors with familiar, industry-standard nodes for traditional compositing workflows alongside AI image generation.

Key Project Documents

Primary References

PLANNING.md - Complete project vision, architecture, and roadmap
TASKS.md - Detailed task checklist for implementation
DOCS/NODE_PRIORITIES.md - 43 nodes prioritized by importance

Quick Reference

Language: Python 3.8+
Framework: ComfyUI Custom Node API
Core Libraries: PyTorch, NumPy, Pillow
Target: Professional compositors and VFX artists

Project Status

Current Phase: Phase 1 - Planning Complete ✓

Completed:

Project vision and goals defined
Architecture designed
Technology stack selected
43 nodes researched and prioritized
Development roadmap created

Next Steps:

Create directory structure
Set up pyproject.toml and requirements.txt
Implement utility modules (tensor_utils.py, image_processing.py, color_math.py)
Create __init__.py with node registration system
Begin implementing Priority 1 nodes (Merge, Transform, Blur, Grade, Premult/Unpremult)

Technical Architecture

Directory Structure

ComfyUI_Detonate/
├── __init__.py                 # Node registration
├── nodes/                      # Node implementations
│   ├── compositing/            # Merge operations
│   ├── color/                  # Color correction
│   ├── keying/                 # Keying tools
│   ├── transform/              # Transforms
│   ├── filter/                 # Blur, sharpen, etc.
│   ├── matte/                  # Matte operations
│   ├── channel/                # Channel ops
│   ├── time/                   # Time operations
│   └── 3d/                     # 3D compositing
├── utils/                      # Shared utilities
│   ├── tensor_utils.py
│   ├── image_processing.py
│   └── color_math.py
├── tests/                      # Unit tests
├── examples/                   # Example workflows
├── web/js/                     # Frontend extensions
├── pyproject.toml              # Package metadata
├── requirements.txt            # Dependencies
└── README.md                   # Documentation

Read the full file on GitHub · 363 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.

9d ago First seen · 363 lines · 2,994 tokens per session scan A 5d20190e8915

Subscribe to this mod's changes

ComfyUI_Detonate CLAUDE.md is an instructions file published in the GitHub repository aTanguay/ComfyUI_Detonate (5 stars, last pushed 3mo ago), licensed MIT. It adds 2,994 tokens to every session, about $0.0150 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.

Creative and media

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

ComfyUI_Detonate: Instructions file for Claude Code