workflow_templates: Instructions file for Claude Code

CLAUDE.md

workflow_templates CLAUDE.md is an instructions file for Claude Code from Comfy-Org/workflow_templates. It costs 4,880 tokens per session, scanned A, original, MIT.

Repository guidance for ComfyUI workflow templates, which are reusable instructions for ComfyUI image or media-generation processes. The repository is a monorepo, meaning one code repository contains several related packages and an Astro website.

In plain words
What is it for?
Use it when working on workflow definitions, template metadata, reusable blueprints, package mappings, or the templates.comfy.org website.
Why use it?
It explains how the template files, translations, blueprints, Python packages, and public website fit together so changes stay consistent across both systems.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

This is Comfy-Org/workflow_templates's own configuration. It tells Claude Code how to work on workflow_templates 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 workflow_templates configures →

About the project

workflow_templates is the repository of official ComfyUI workflow templates and reusable subgraph blueprints. It supplies standalone workflows and node components for ComfyUI, along with a browsable site for finding templates. The catalogue entries are skills and instructions for working with these workflows.

Comfy-Org/workflow_templates · 1,360 stars · on GitHub · pypi.org

Reuse

Borrowing it

Nothing to install: this file belongs to Comfy-Org/workflow_templates. 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/Comfy-Org/workflow_templates/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Comfy-Org/workflow_templates

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 workflow_templates CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/comfy-org/workflow_templates/claude-md/github.svg)](https://agentmods.dev/instructions/comfy-org/workflow_templates/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/comfy-org/workflow_templates/claude-md"><img src="https://agentmods.dev/badge/instructions/comfy-org/workflow_templates/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 workflow_templates CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/comfy-org/workflow_templates/claude-md"><img src="https://agentmods.dev/badge/instructions/comfy-org/workflow_templates/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,880 This file is loaded in full into every session.
When invoked 4,880 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 $0.04880 $0.04880
Opus 5.5 $0.01952 $0.01952
Sonnet 5.5 $0.00976 $0.00976
Haiku 4.5 $0.00488 $0.00488

Measured 14d ago against content hash 7d432174b3e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

workflow_templates 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 14d 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 · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — ComfyUI Workflow Templates Monorepo

What This Repo Is

A monorepo managing ComfyUI workflow templates distributed as Python packages AND a public Astro-based workflow hub website at comfy.org/workflows. Two distinct systems share the same template data.

Repository Map

workflow_templates/
├── templates/              # SOURCE OF TRUTH: workflow JSONs, thumbnails, index metadata
│   ├── index.json          # Master template metadata (English)
│   ├── index.{locale}.json # 11 locale variants (zh, ja, ko, es, fr, ru, tr, ar, pt-BR, zh-TW)
│   ├── *.json              # ComfyUI workflow definitions
│   └── *-1.webp, *-2.webp # Template thumbnails
├── blueprints/             # Reusable subgraph blueprint definitions
├── bundles.json            # Maps template names → Python package bundles
├── blueprints_bundles.json # Maps blueprint names → package
├── packages/               # Python distribution packages (Nx monorepo)
│   ├── core/               # Loader + manifest
│   ├── media_api/          # API-calling templates (Replicate, BFL, etc.)
│   ├── media_image/        # Image generation templates
│   ├── media_video/        # Video generation templates
│   ├── media_other/        # Audio, 3D, utilities
│   ├── media_assets_01/    # Frozen asset shard 01
│   ├── media_assets_02/    # Active asset shard (new templates)
│   ├── meta/               # Meta package aggregating all above
│   └── blueprints/         # Subgraph blueprints package
├── scripts/                # Python: validation, sync, i18n (see scripts/README.md)
│   ├── sync/               # sync_data, sync_bundles, sync_blueprints, etc.
│   ├── mcp/                # MCP index pipeline (index.mcp.json)
│   ├── validate/           # validate_templates, check_links, analyze_models, etc.
│   ├── ci/                 # ci_version_manager, PyPI quota, version helpers
│   ├── data/               # i18n.json, whitelist.json, models_capabilities.json
│   ├── lib/                # Shared modules (paths, locale_index_files, ai/)
│   ├── maintenance/        # archive_templates, local-only tools
│   ├── blueprints/         # import_blueprints
│   └── docs/               # Script-specific markdown (whitelist.md, etc.)
├── site/                   # INDEPENDENT Astro 5 project (see "Site" section below)
├── docs/                   # Specs, i18n guide, publishing guide
├── .claude/skills/         # Claude skill definitions (incl. managing-mcp-index)
├── .github/workflows/      # CI/CD (validation, deploy, lint, tests)
├── pyproject.toml          # Python project version & config
├── package.json            # Nx monorepo root (npm run sync, etc.)
└── nx.json                 # Nx workspace config

Read the full file on GitHub · 391 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. 14d ago Changed · +1 lines · +36 tokens per session 7d432174b3e6
  2. 1mo ago Changed · +3 lines · +72 tokens per session 31daa5397d0a
  3. 1mo ago Changed ff4b7907d0b9
  4. 1mo ago First seen · 387 lines · 4,772 tokens per session scan A ad9bfee0e66a

Subscribe to this mod's changes

workflow_templates CLAUDE.md is an instructions file published in the GitHub repository Comfy-Org/workflow_templates (1,360 stars, last pushed yesterday), licensed MIT. It adds 4,880 tokens to every session, about $0.0195 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 2026-08-30.

Related

Other instructions, from other repositories

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 · 9,715 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 · 7,581 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens