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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Comfy-Org/workflow_templatesnpx agentmods add skills/comfy-org/workflow_templates/managing-mcp-indexWrote 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/managing-mcp-index)<a href="https://agentmods.dev/skills/comfy-org/workflow_templates/managing-mcp-index"><img src="https://agentmods.dev/badge/skills/comfy-org/workflow_templates/managing-mcp-index/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/managing-mcp-index"><img src="https://agentmods.dev/badge/skills/comfy-org/workflow_templates/managing-mcp-index.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 | $0.00172 | $0.01971 |
| Opus 5.5 | $0.00069 | $0.00788 |
| Sonnet 5.5 | $0.00034 | $0.00394 |
| Haiku 4.5 | $0.00017 | $0.00197 |
Grade A, and why
managing-mcp-index 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing MCP Index
What This Is
templates/index.mcp.json is a machine-oriented template index for Comfy Cloud MCP tools. It is separate from:
| System | File(s) | Purpose |
|---|---|---|
| MCP index (this skill) | index.mcp.json |
English metadata for AI tool routing: description, io, capabilities, recommend |
| Hub manifest | index.json + index.{locale}.json |
Human UI + 11-language titles/descriptions → skill: managing-translations |
| Site SEO | site/ AI pipeline |
Long-form page copy → skill: regenerating-ai-content |
MCP descriptions are English only. There is no MCP translation step. Multi-language hub copy uses npm run i18n (sync_data.py), not the MCP pipeline.
Quick Commands (npm)
npm run mcp # Step 1: sync index.json → index.mcp.json
npm run mcp:check # Dry-run sync (no write)
npm run mcp:ai # Step 2b: AI English descriptions (stale templates only)
npm run mcp:models # Step 2a: AI model profiles in models_registry.json
npm run mcp:enhance # Step 2a + Step 2b in the required order
npm run i18n # Hub translations (NOT MCP — separate system)
Prerequisites for AI steps: copy .env.example → .env, set AI_API_KEY, AI_BASE_URL, AI_MODEL. Optional: COMFYUI_REPO_PATH for API node dropdown scanning during npm run mcp.
Advanced flags (run Python directly): see scripts/mcp/docs/MCP_AI_ENHANCEMENT.md.
Pipeline Overview
templates/index.json
│
▼ npm run mcp (sync_index.py)
templates/index.mcp.json ◄── merge description/io from template_cache (hash match)
│
├── npm run mcp:models → scripts/data/mcp/models_registry.json
└── npm run mcp:ai → scripts/data/mcp/template_cache.json → merge back to index.mcp.json
| Step | Script | Writes |
|---|---|---|
| 1 Sync | scripts/mcp/sync_index.py |
index.mcp.json, refreshes api_node_model_options.json |
| 2a Models | scripts/mcp/enhance_models_registry.py |
models_registry.json |
| 2b Templates | scripts/mcp/enhance_descriptions.py |
template_cache.json + merge → index.mcp.json |
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 Changed 113013cabbc9
- 1mo ago First seen · 171 lines · 172 tokens per session scan A 185bd2e85bc0
managing-mcp-index is a skill published in the GitHub repository Comfy-Org/workflow_templates (1,360 stars, last pushed yesterday), licensed MIT. It adds 172 tokens to every session and 1,971 once invoked, about $0.0007 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.