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-compositinggit 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-compositing)<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.
<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>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 | $0.00064 | $0.02484 |
| Opus 5.5 | $0.00026 | $0.00994 |
| Sonnet 5.5 | $0.00013 | $0.00497 |
| Haiku 4.5 | $0.00006 | $0.00248 |
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.
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()
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 · 382 lines · 64 tokens per session scan A 3916e77ec35a
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.
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…
skills-pr-handle
Use when explicitly asked to handle a pull request in the Scenario skills repository, including review comments and skill validation.
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.
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…
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.
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.