nuke-compositing

nuke-compositing is a skill for Claude Code from sideshowroberto/vfx-agent-toolkit. It costs 64 tokens per session (2,484 once invoked), scanned A, original, MIT.

Node graph compositing workflows for Nuke including Read/Write setup, grading, merging, keying, and multi-layer comp patterns. Use when setting up comps, creating node graphs, or when user mentions nuke comp, node graph, grade, merge, keying, aov.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Install with agentmods
npx agentmods add skills/sideshowroberto/vfx-agent-toolkit/nuke-compositing
Install

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.

Any agent
npx skills add sideshowroberto/vfx-agent-toolkit --skill nuke-compositing
Clone the repo
git clone --depth 1 https://github.com/sideshowroberto/vfx-agent-toolkit

Made for: Claude Code.

Wrote 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.

agentmods badge for nuke-compositing

README.md
[![agentmods](https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/nuke-compositing/github.svg)](https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/nuke-compositing)
Your own site
<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/nuke-compositing"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/nuke-compositing/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.

agentmods 80×15 button for nuke-compositing

Your own site · 80×15
<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/nuke-compositing"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/nuke-compositing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,484 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.02484
Opus 5.5 $0.00026 $0.00994
Sonnet 5.5 $0.00013 $0.00497
Haiku 4.5 $0.00006 $0.00248

Measured today against content hash 3916e77ec35a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nuke-compositing 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.

plugins/nuke-vfx/skills/nuke-compositing/SKILL.md · 382 lines

How it starts

The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.

nuke-compositing

Version: 1.0.0 Last Updated: 2025-12-03 Dependencies: Nuke (Foundry), NukeMCPLogger


Overview

Node graph compositing workflows for Nuke including plate ingestion, grading, layer merging, keying, and multi-layer comp patterns. Uses NukeMCPLogger for structured output.

Key Patterns:

  • Basic comp structure (Read -> Grade -> Merge -> Write)
  • Multi-layer workflows with AOVs
  • Keying and integration
  • Batch processing setup

Quick Start

Basic Comp Workflow

from nuke_mcp_logger import NukeMCPLogger
import nuke

log = NukeMCPLogger(session_name="BasicComp")

try:
    # Read plate
    read_node = nuke.createNode("Read")
    read_node['file'].setValue("D:/Plates/Shot001_%04d.exr")
    read_node.setName("BG_Plate")
    log.increment_stat("nodes_created")

    # Grade
    grade_node = nuke.createNode("Grade")
    grade_node.setName("MainGrade")
    log.increment_stat("nodes_created")

    # Write output
    write_node = nuke.createNode("Write")
    write_node['file'].setValue("D:/Output/Shot001_comp_%04d.exr")
    write_node.setName("MainOut")
    log.increment_stat("nodes_created")

    log.success(f"Comp setup complete: {log.stats['nodes_created']} nodes")

except Exception as e:
    log.error("Comp setup failed", e)

result = log.get_results()

Expected Result:

  • 3 nodes created (Read -> Grade -> Write)
  • Automatic connection in linear graph
  • Ready for render

Standard Workflows

Workflow 1: Plate + Grade + Write (Simplest Comp)

Use When: Basic color correction comp

def setup_basic_comp(plate_path: str, output_path: str, frame_range: tuple):
    """
    Create basic Read -> Grade -> Write comp for ANY project.

    Args:
        plate_path: Input image sequence path
        output_path: Output render path
        frame_range: (first, last) frame tuple

    Returns:
        dict: Logger results
    """
    import nuke
    from nuke_mcp_logger import NukeMCPLogger

    log = NukeMCPLogger(session_name="BasicComp")

    try:
        # Clear script
        nuke.scriptClear()

        # Read plate
        read_node = nuke.createNode("Read")
        read_node['file'].setValue(plate_path)
        read_node['first'].setValue(frame_range[0])
        read_node['last'].setValue(frame_range[1])
        read_node.setName("BG_Plate")
        log.increment_stat("nodes_created")

        # Grade
        grade_node = nuke.createNode("Grade")
        grade_node.setName("MainGrade")
        log.increment_stat("nodes_created")

        # Write
        write_node = nuke.createNode("Write")
        write_node['file'].setValue(output_path)
        write_node['file_type'].setValue("exr")
        write_node.setName("MainOut")
        log.increment_stat("nodes_created")

        log.success(f"Basic comp: {log.stats['nodes_created']} nodes")
        return log.get_results()

    except Exception as e:
        log.error("Setup failed", e)
        return log.get_results()

Read the full file on GitHub · 382 lines

Changes

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.

  1. today First seen · 382 lines · 64 tokens per session scan A 3916e77ec35a

Subscribe to this mod's changes

nuke-compositing is a skill published in the GitHub repository sideshowroberto/vfx-agent-toolkit (16 stars, last pushed 22d ago), licensed MIT. It adds 64 tokens to every session and 2,484 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.

Related

Other skills, from other repositories

git-automation

Infrastructure skill — Git repository analysis and automation: inspect commits, branches, diffs, and file history. Use when analysing a codebase, reviewing changes, or automating version control workflows independent of any DCC. Not for DCC asset versioning or Perforce operations — use a domain skill bound to the…

dcc-mcp/dcc-mcp-core · 72 tokens

skills-pr-handle

Use when explicitly asked to handle a pull request in the Scenario skills repository, including review comments and skill validation.

scenario-labs/skills · 27 tokens

pr-handle-comments

Handle review comments received on GitHub for the current branch's PR or a given PR number or URL, by triaging each unresolved thread, fixing what is warranted, pushing, and replying in each thread, when asked to address, fix or answer PR comments. Works in any Scenario repository.

scenario-labs/skills · 63 tokens

pr-squash-message

Generate one short Conventional Commits squash message describing only the net diff between the PR's base and head, set its header as the PR title, validate it with the repository's commitlint and both copy its description to the clipboard and display it, when asked for a squash message. Works in any Scenario…

scenario-labs/skills · 73 tokens

pr-summary

Refresh the current pull request description from its net changes, following the repository's PR template, when asked to update or write the PR summary. Works in any Scenario repository, whatever its default branch.

scenario-labs/skills · 42 tokens

dcc-cua

A routing guide for controlling application interfaces through the project’s DCC-CUA system. DCC applications are digital-content tools such as Maya, Blender, and Houdini.

dcc-mcp/dcc-mcp-core · 131 tokens