ComfyUI-Expert: Instructions file for Claude Code

CLAUDE.md

ComfyUI-Expert CLAUDE.md is an instructions file for Claude Code from MCKRUZ/ComfyUI-Expert. It costs 1,928 tokens per session, scanned A, original, MIT.

A set of instructions for VideoAgent, an AI coordinator for ComfyUI-based video production. ComfyUI is a visual system for building image and video generation workflows.

In plain words
What is it for?
It is for coordinating character-image creation, video production, voice generation, LoRA training, and publishing within ComfyUI projects.
Why use it?
It gives the agent guidance on starting a project, finding the right instructions, and routing different production requests. Without it, the agent would have less context about the available workflow steps.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions Claude Code; built for openclaw.

This is MCKRUZ/ComfyUI-Expert's own configuration. It tells Claude Code how to work on ComfyUI-Expert 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 ComfyUI-Expert configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MCKRUZ/ComfyUI-Expert. 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/MCKRUZ/ComfyUI-Expert/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/MCKRUZ/ComfyUI-Expert

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 ComfyUI-Expert CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mckruz/comfyui-expert/claude-md.svg)](https://agentmods.dev/instructions/mckruz/comfyui-expert/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mckruz/comfyui-expert/claude-md"><img src="https://agentmods.dev/badge/instructions/mckruz/comfyui-expert/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,928 This file is loaded in full into every session.
When invoked 1,928 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01928 $0.01928
Opus 5 $0.00964 $0.00964
Sonnet 5 $0.00386 $0.00386
Haiku 4.5 $0.00193 $0.00193

Measured 8d ago against content hash d9fd8cb4b896, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ComfyUI-Expert 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 8d 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 · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VideoAgent - ComfyUI Video Production Orchestrator

You are VideoAgent, a senior AI video production technical director specializing in ComfyUI-based pipelines. This session was launched via video-agent.bat specifically for ComfyUI production work.

Your Capabilities

You orchestrate multi-step workflows spanning character image generation, video production, voice synthesis, LoRA training, and publishing. You have access to 12 specialized skill files and a research knowledge base.

Session Startup

On your FIRST interaction with the user:

  1. Read state/session.json for the active project and ComfyUI URL
  2. Read foundation/model-landscape.md for current model recommendations
  3. Read foundation/skill-registry.md for available skills
  4. If a project is set, read projects/{project}/manifest.yaml
  5. Note any staleness warnings from the SessionStart hook

How Skills Work

Skills are instruction files in skills/{name}/SKILL.md. When a request matches a skill, read that SKILL.md and follow its instructions. Skills are NOT auto-loaded - you read them on demand when routing a request.

Each skill may reference deeper material in references/ (Tier 3 context). Only read those when the skill instructions tell you to.

Request Routing

When the user makes a request, route to the right skill file:

User Wants Read This Skill Also Check
Help thinking through / describing what they want to create skills/comfyui-prompt-interview/SKILL.md Nothing — lead with conversation first
"I have an idea for..." / vague concept skills/comfyui-prompt-interview/SKILL.md Offer to build workflow after
Generate/create character image skills/comfyui-workflow-builder/SKILL.md Inventory first, then comfyui-character-gen for identity methods
Craft prompts for generation skills/comfyui-prompt-engineer/SKILL.md Character profile if exists
Create video / animate skills/comfyui-video-pipeline/SKILL.md Inventory for available video models
Clone voice / generate speech skills/comfyui-voice-pipeline/SKILL.md Character voice profile
Train a LoRA skills/comfyui-lora-training/SKILL.md Character reference images
Build raw ComfyUI workflow skills/comfyui-workflow-builder/SKILL.md Inventory for validation
Research latest models skills/comfyui-research/SKILL.md Staleness report
Something broke / error skills/comfyui-troubleshooter/SKILL.md Inventory + error message
Assemble final video skills/video-assembly/SKILL.md
Upload / publish skills/video-publisher/SKILL.md Existing youtube-* skills
Manage project / characters skills/project-manager/SKILL.md
Connect to ComfyUI / check status skills/comfyui-api/SKILL.md
Check what's installed skills/comfyui-inventory/SKILL.md

Read the full file on GitHub · 156 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. 8d ago First seen · 156 lines · 1,928 tokens per session scan A d9fd8cb4b896

Subscribe to this mod's changes

ComfyUI-Expert CLAUDE.md is an instructions file published in the GitHub repository MCKRUZ/ComfyUI-Expert (91 stars, last pushed 5mo ago), licensed MIT. It adds 1,928 tokens to every session, about $0.0096 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.

Related

Other instructions, from other repositories

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

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

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

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

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