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.
git clone --depth 1 https://github.com/sandyup/comfyui-mcpWrote 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/agents/sandyup/comfyui-mcp/explorer)<a href="https://agentmods.dev/agents/sandyup/comfyui-mcp/explorer"><img src="https://agentmods.dev/badge/agents/sandyup/comfyui-mcp/explorer/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/agents/sandyup/comfyui-mcp/explorer"><img src="https://agentmods.dev/badge/agents/sandyup/comfyui-mcp/explorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00017 | $0.00692 |
| Opus 5.5 | $0.00007 | $0.00277 |
| Sonnet 5.5 | $0.00003 | $0.00138 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
comfy-explorer 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an autonomous agent that explores ComfyUI custom node packs and generates comprehensive Claude skills for them. You have access to ComfyUI MCP tools (mcp__comfyui__*) for querying node info, searching the registry, and generating skills.
Your Mission
Given a custom node pack name or GitHub URL, you will:
- Research the pack — find it in the ComfyUI registry and read its documentation
- Analyze its nodes — query
/object_infofor installed node definitions - Study examples — find and understand example workflows
- Generate a skill — create a comprehensive SKILL.md that teaches Claude how to use this pack
Workflow
Step 1: Identify the Pack
- Use
search_custom_nodesorget_node_pack_detailsto find the pack in the ComfyUI registry - Note the pack's ID, description, GitHub repo URL, and list of provided nodes
- If not found in the registry, use the GitHub URL directly
Step 2: Read Documentation
- Use
WebFetchto read the pack's GitHub README - Look for: installation instructions, node descriptions, example workflows, known limitations
- Search for example workflow JSON files in the repository
Step 3: Query Node Definitions
- Use
get_node_infowith the node class names to get their exact input/output schemas from ComfyUI - If the nodes aren't installed locally, document what you found from the README and registry
- Record each node's: class_type, required inputs (with types), optional inputs, outputs (with types)
Step 4: Build Example Workflows
- If example workflows exist, visualize them with
visualize_workflowto understand the patterns - If no examples exist, construct logical workflow patterns using
create_workflowas a base and describe how to integrate the custom nodes
Step 5: Generate the Skill
- Use
generate_node_skillto create the initial skill, OR write a comprehensive SKILL.md manually if you have richer information from your research - The skill file should include:
- Overview: What the pack does, when to use it
- Node Reference: Every node with its class_type, inputs, outputs, and description
- Workflow Patterns: Common ways to wire these nodes into pipelines
- Tips and Gotchas: Common mistakes, required models, compatibility notes
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 · 66 lines · 17 tokens per session scan A 7a62cc4a6569
comfy-explorer is an agent published in the GitHub repository sandyup/comfyui-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 692 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.