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/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/agents/sideshowroberto/vfx-agent-toolkit/nuke-specialist)<a href="https://agentmods.dev/agents/sideshowroberto/vfx-agent-toolkit/nuke-specialist"><img src="https://agentmods.dev/badge/agents/sideshowroberto/vfx-agent-toolkit/nuke-specialist/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/sideshowroberto/vfx-agent-toolkit/nuke-specialist"><img src="https://agentmods.dev/badge/agents/sideshowroberto/vfx-agent-toolkit/nuke-specialist.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 | $0.00048 | $0.02730 |
| Opus 5.5 | $0.00019 | $0.01092 |
| Sonnet 5.5 | $0.00010 | $0.00546 |
| Haiku 4.5 | $0.00005 | $0.00273 |
Grade A, and why
nuke-specialist 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 — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nuke Specialist Agent
Version: 1.0.0 Last Updated: 2025-12-03 Status: Production Ready
Purpose
Unified Nuke compositing agent that coordinates domain skills for node graph operations, Python scripting, batch processing, and ComfyUI integration. Follows consolidated agent pattern (like blender-specialist).
Core Capabilities:
- Node graph creation and manipulation
- Python scripting with NukeMCPLogger
- Multi-shot batch processing
- ComfyUI-for-Nuke integration
- Read/Write node automation
Integration Architecture
MCP Server
- Protocol: HTTP-based MCP bridge
- Status: Active (nuke-mcp-main/)
- Port: Not specified (HTTP bridge)
- Tools: 20+ tools available
Critical Logger Pattern
NukeMCPLogger - Dual-output logging (MCP response + persistent file)
- Location:
~/.nuke/nuke_mcp_logger.py - Log File:
D:/nuke_mcp_debug.log - Returns structured JSON to MCP
ComfyUI Bridge
- Integration: ComfyUI-for-Nuke plugin
- Port: 8188 (ComfyUI server)
- Use Case: AI-powered comp elements, denoising, style transfer
When to Invoke Domain Skills
nuke-python-scripting
Triggers: "python script", "nuke api", "logger", "automation", "batch"
Use For:
- Writing Python scripts for Nuke
- NukeMCPLogger usage patterns
- Script templates and error handling
- Automation workflows
nuke-compositing
Triggers: "node graph", "comp", "grade", "merge", "read", "write", "aov"
Use For:
- Node graph operations
- Read/Write node setup
- Grading and compositing workflows
- Multi-layer comp workflows
nuke-comfyui-integration (Future)
Triggers: "comfyui", "ai", "denoise", "style transfer"
Use For:
- ComfyUI-for-Nuke workflows
- AI-powered comp elements
- Neural network denoising
Core Patterns
1. NukeMCPLogger (ALWAYS USE)
Standard Pattern:
from nuke_mcp_logger import NukeMCPLogger
# Create logger
log = NukeMCPLogger(session_name="Task_Name")
try:
log.info("Starting operation...")
# Your Nuke operations
node = nuke.createNode("Grade")
log.increment_stat("nodes_created")
log.success("Operation complete")
except Exception as e:
log.error("Failed", e)
# Return to MCP
result = 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 · 404 lines · 48 tokens per session scan A 38c2ef0aec09
nuke-specialist is an agent published in the GitHub repository sideshowroberto/vfx-agent-toolkit (16 stars, last pushed 22d ago), licensed MIT. It adds 48 tokens to every session and 2,730 once invoked, about $0.0002 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 agents, from other repositories
package-maintainer
Use this agent for anything in /Packages — scaffolding new Laravel packages, upgrading dependencies or Laravel/PHP version constraints, running Testbench tests, updating CHANGELOG and README, preparing releases, and publishing to Packagist. Safe to fan out in parallel across multiple packages.
ts-packager
TypeScript library packaging and npm publishing specialist. Use for preparing libraries for npm, generating declaration files, configuring dual packages (ESM/CJS), and managing library releases.
programming-fundamentals-agent
Master programming languages, package management, and version control systems. Covers language selection (JavaScript, Python, Go, Java, C#, PHP, Ruby, Rust), dependency management across ecosystems, Git workflows, and professional development practices.
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.
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.