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.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Comfy-Org/workflow_templates --skill editing-site-contentgit clone --depth 1 https://github.com/Comfy-Org/workflow_templatesWrote 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.
[](https://agentmods.dev/skills/comfy-org/workflow_templates/editing-site-content)<a href="https://agentmods.dev/skills/comfy-org/workflow_templates/editing-site-content"><img src="https://agentmods.dev/badge/skills/comfy-org/workflow_templates/editing-site-content/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.
<a href="https://agentmods.dev/skills/comfy-org/workflow_templates/editing-site-content"><img src="https://agentmods.dev/badge/skills/comfy-org/workflow_templates/editing-site-content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00158 | $0.01656 |
| Opus 5.5 | $0.00063 | $0.00662 |
| Sonnet 5.5 | $0.00032 | $0.00331 |
| Haiku 4.5 | $0.00016 | $0.00166 |
Grade A, and why
editing-site-content 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editing Site Content
You are helping a content manager or creative edit template pages on the ComfyUI workflow template site. They should never need to understand JSON, code, or the build pipeline — you handle all of that.
How It Works
Template pages on the site have AI-generated content. To override that content with human-written copy, you create a JSON file in site/overrides/templates/{template-name}.json. The build pipeline merges these overrides on top of AI output, preserving human edits across regenerations.
Step 1: Identify the Template
The user may refer to a template by its display name, a partial name, a description of what it does, or a URL slug.
To find the right template:
- Search
templates/index.jsonfor the template. It contains all templates grouped into bundles withname,title, anddescriptionfields. - The
namefield (e.g.,templates-sprite_sheet) is the filename key used for the override file. - If the user's request is ambiguous, show them matching candidates with their titles and descriptions and ask them to confirm.
Example: User says "the sprite sheet one"
→ Search index.json → find templates-sprite_sheet with title "Sprite Sheet Generator"
→ Confirm with user: "I found Sprite Sheet Generator — is that the one you mean?"
Step 2: Check for Existing Override
Read site/overrides/templates/{template-name}.json if it exists. If it does, you'll be editing the existing override. If not, you're creating a new one.
Also read the current generated output at site/src/content/templates/{template-name}.json (if it exists) to see what the current live content looks like. Show the user what's currently there before making changes.
Step 3: Make the Changes
Overridable Fields
These are the fields you can set in an override file:
| Field | Type | What It Is |
|---|---|---|
extendedDescription |
string |
The main long-form description shown on the template detail page. Supports plain text. |
metaDescription |
string |
SEO meta description shown in search results. Keep to 150-160 characters. |
howToUse |
string[] |
Step-by-step instructions. Each array item is one step. |
suggestedUseCases |
string[] |
List of use cases or scenarios where this template shines. |
faqItems |
Array<{question, answer}> |
FAQ section. Each item has a question string and an answer string. |
humanEdited |
boolean |
Set to true to fully replace AI content and prevent regeneration. |
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.
- 1mo ago First seen · 123 lines · 158 tokens per session scan A cec497b1ade3
editing-site-content is a skill published in the GitHub repository Comfy-Org/workflow_templates (1,360 stars, last pushed yesterday), licensed MIT. It adds 158 tokens to every session and 1,656 once invoked, about $0.0006 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.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.