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 sideshowroberto/vfx-agent-toolkit --skill nuke-cattery-inferencegit clone --depth 1 https://github.com/sideshowroberto/vfx-agent-toolkitWrote 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/sideshowroberto/vfx-agent-toolkit/nuke-cattery-inference)<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/nuke-cattery-inference"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/nuke-cattery-inference/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/sideshowroberto/vfx-agent-toolkit/nuke-cattery-inference"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/nuke-cattery-inference.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 | $0.04400 |
| Opus 5.5 | $0.00025 | $0.01760 |
| Sonnet 5.5 | $0.00013 | $0.00880 |
| Haiku 4.5 | $0.00006 | $0.00440 |
Grade A, and why
nuke-cattery-inference 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 today.
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 — 483 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nuke-cattery-inference
Version: 1.1.1
Last Updated: 2026-03-10
Dependencies: NukeX or Nuke Studio (not Nuke Indie/Non-Commercial), Python 3.10+, PyTorch 2.1.1+cpu
Deep Reference: ClaudeCode/data/research/Nuke_ML_Inference_Research.md
Overview
NukeX's Cattery system lets you run PyTorch ML models inside Nuke via the Inference node. The workflow is:
- Export PyTorch model to TorchScript (.pt) - via
script()ortrace() - Compile .pt -> .cat via CatFileCreator node (NukeX/Studio only)
- Infer using the Inference node in any comp (base Nuke too)
Requires NukeX or Nuke Studio for authoring. Inference node works in any Nuke license. Nuke version -> PyTorch version mapping:
| Nuke | PyTorch | Notes |
|---|---|---|
| 13.x | 1.6.0 | .cat NOT compatible with Nuke 14+ |
| 14.x | 1.12.1 | Forward-compatible to 15+ |
| 15.0 | 1.x | Cannot load 2.x TorchScript models |
| 15.1+ / 16.x / 17.x | 2.x | Use torch==2.1.1+cpu for tracing |
Check Nuke's bundled version: In Script Editor: import torch; print(torch.__version__)
CRITICAL: Valid Channel Names
Only 19 predefined channels are valid. Custom names (like da.r, other.r, other.1) will cause invalid map<K, T> key errors.
| Category | Valid Channel Names |
|---|---|
| Color | rgba.red rgba.green rgba.blue rgba.alpha |
| Depth | depth.Z <- capital Z |
| Motion / Optical Flow | forward.u forward.v backward.u backward.v |
| Deep Compositing | deep.front deep.back |
| Disparity (Stereo) | disparityL.x disparityL.y disparityR.x disparityR.y |
| Masks | mask.a rotopaint_mask.a mask_planartrack.a mask_splinewarp.a |
Common depth estimation setup:
- Channels In:
rgba.red,rgba.green,rgba.blue - Channels Out:
depth.Z
Format: Comma-separated, full dot-notation names (not set names like "rgb").
Workflow 1: Export PyTorch Model to TorchScript
The tracing environment must match Nuke's PyTorch version (see table above).
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.
- today First seen · 483 lines · 63 tokens per session scan A 266b649bbbd7
nuke-cattery-inference is a skill published in the GitHub repository sideshowroberto/vfx-agent-toolkit (16 stars, last pushed 22d ago), licensed MIT. It adds 63 tokens to every session and 4,400 once invoked, about $0.0003 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 2026-11-02.
Other skills, from other repositories
comfyui-civitai
A ComfyUI integration for searching, inspecting, and downloading models from CivitAI, a website that hosts community-created AI models and model versions.
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.
prompt-engineering
ComfyUI prompt engineering knowledge covering CLIP text encoding syntax, weight modifiers, model-specific prompting strategies, and best practices.
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
scenario-model-training
Use when generated assets must keep a consistent style, character, or product look and references stop scaling, or when a user asks to train a custom model through the Scenario MCP, fine-tune a LoRA, clone a voice, curate a training dataset, choose a base model, set epochs and sample prompts, estimate training cost…
scenario-model-comparison
Use when comparing Scenario models on the same brief through MCP: a bake-off with shared prompts and inputs, cost, generation time and quality measured side by side, choosing a default model, testing a new release against the incumbent, or finding which model handles a style, edit, or reference image best. Keywords…