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 MCKRUZ/ComfyUI-Expert --skill comfyui-researchgit clone --depth 1 https://github.com/MCKRUZ/ComfyUI-ExpertWrote 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/mckruz/comfyui-expert/comfyui-research)<a href="https://agentmods.dev/skills/mckruz/comfyui-expert/comfyui-research"><img src="https://agentmods.dev/badge/skills/mckruz/comfyui-expert/comfyui-research/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/mckruz/comfyui-expert/comfyui-research"><img src="https://agentmods.dev/badge/skills/mckruz/comfyui-expert/comfyui-research.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 | $0.00063 | $0.01651 |
| Opus 5 | $0.00032 | $0.00826 |
| Sonnet 5 | $0.00013 | $0.00330 |
| Haiku 4.5 | $0.00006 | $0.00165 |
Grade A, and why
comfyui-research 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 10d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI Research Skill
Keeps the VideoAgent knowledge base current by monitoring sources, extracting knowledge, and flagging stale information.
Triggers
- On demand: User invokes
/research comfyuior asks to check for updates - Session start: Quick staleness check (read
references/staleness-report.md) - Before workflow generation: Targeted check if the specific model/technique is >2 months old
Research Pipeline
1. Discovery
Search for new developments across three source types:
YouTube Channels (technique extraction):
| Channel | Focus | URL |
|---|---|---|
| Pixaroma | ComfyUI tutorials, GGUF, beginner-friendly | youtube.com/@pixaroma |
| Kijai | Advanced nodes, model implementations | youtube.com/@Kijai |
| Sebastian Kamph | ComfyUI workflows, automation | youtube.com/@sebastiankamph |
| Olivio Sarikas | AI art techniques, ComfyUI | youtube.com/@OlivioSarikas |
| Matt Wolfe | AI tool roundups | youtube.com/@maboroshi |
| Nerdy Rodent | Stable Diffusion deep dives | youtube.com/@NerdyRodent |
GitHub Repositories (node/model updates):
| Repository | What to Check |
|---|---|
| comfyanonymous/ComfyUI | Releases, breaking changes |
| Kosinkadink/ComfyUI-AnimateDiff-Evolved | New motion modules |
| cubiq/ComfyUI_IPAdapter_plus | Maintenance status, forks |
| ltdrdata/ComfyUI-Impact-Pack | FaceDetailer updates |
| Wan-AI/Wan2.1-Preview | New model versions |
| hzwer/Practical-RIFE | Interpolation updates |
| resemble-ai/chatterbox | Voice model updates |
| SWivid/F5-TTS | TTS updates |
HuggingFace (model releases):
- Trending models:
huggingface.co/models?sort=trending - Filter: diffusers, video, audio, text-to-image
- Watch for: New FLUX variants, Wan updates, identity models, voice models
2. Extraction
For each discovery, extract structured knowledge:
From YouTube videos:
Use youtube-video-analyst or youtube-chapter-clipper skills to:
- Get transcript
- Identify new models mentioned (name, source, requirements)
- Identify new techniques (workflow changes, parameter discoveries)
- Identify new nodes (package name, what it does)
- Note any benchmark results or comparisons
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 184 lines · 63 tokens per session scan A bd12787d7476
comfyui-research is a skill published in the GitHub repository MCKRUZ/ComfyUI-Expert (91 stars, last pushed 5mo ago), licensed MIT. It adds 63 tokens to every session and 1,651 once invoked, about $0.0003 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.
Other skills, from other repositories
ai-media-generator
A workflow for turning ideas into prompts for AI-generated images, videos, and music across several media platforms. When needed, it can also send those prompts to the chosen platform through browser automation.
minimax-h3
Write, debug and structure prompts for MiniMax H3 video generation (T2VA, I2VA, FL2VA, L2VA, Ref2VA) and configure its ComfyUI workflow. Use when the user mentions MiniMax H3, minimaxh3, fl2va, ref2va, MiniMaxH3ReferenceToVideo, reference-to-video, asks to animate a photo, write a video prompt, pick a model quant, or…
Prompt craft for ComfyUI generation
Use when writing prompts for ComfyUI image or video models: choosing tags vs literary format, fixing composition and anatomy artifacts, picking samplers per LoRA, and writing short movement prompts for video. Neutral examples only.
handoff
Work with Master Canvas AI video handoff packages. Use when a user provides a Master Canvas ZIP or projectmanifest.json and wants Hermes to inspect assets, preserve scene and shot order, prepare ComfyUI/LTX 2.3 jobs, or hand off prompts to Kling, Veo, or another video generation operator. Also use when a user wants…
local-ai-film
A directing workflow for producing AI short films with local or cloud-based models, including atmospheric films, trailers, vlogs, and dialogue-driven stories. It covers creative decisions, avoiding repetitive results, production steps, and final editing.
rhythm-density
A video-editing guide for arranging several short locally generated shots so their pacing alternates between quick, dense sections and slower breathing space.