Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sideshowroberto/vfx-agent-toolkitnpx agentmods add skills/sideshowroberto/vfx-agent-toolkit/houdini-python-automationWrote 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/houdini-python-automation)<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/houdini-python-automation"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/houdini-python-automation/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/houdini-python-automation"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/houdini-python-automation.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 | $0.00060 | $0.05105 |
| Opus 5.5 | $0.00024 | $0.02042 |
| Sonnet 5.5 | $0.00012 | $0.01021 |
| Haiku 4.5 | $0.00006 | $0.00511 |
Grade A, and why
houdini-python-automation 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 — 757 lines — stays where its author put it; the contents beside it link to each section on GitHub.
houdini-python-automation
Version: 1.1.1 Last Updated: 2026-10-09 Dependencies: Houdini 20+, Python 3.9+
CRITICAL: MANDATORY FIRST STEP
ALWAYS verify Python environment before execution:
import hou
# Verify Houdini session is active
try:
hip_file = hou.hipFile.path()
print(f"Active Houdini session: {hip_file}")
except hou.Error:
print("ERROR: No active Houdini session")
exit(1)
# Check Python version
import sys
print(f"Python version: {sys.version}")
Why Critical:
- Session Required: HOM (hou module) only works inside Houdini Python shell or hython
- Scene State: Some operations require saved scene (hou.hipFile.save())
- Thread Safety: UI operations must run on main thread
QUICK START
Most Common Use Case: Batch Node Creation
Goal: Create multiple nodes programmatically and connect them
Step 1: Get Parent Context
import hou
# Get geometry object
obj = hou.node("/obj")
geo = obj.createNode("geo", "procedural_geo")
# Delete default file node
file_node = geo.node("file1")
if file_node:
file_node.destroy()
Step 2: Create Node Network
# Create grid source
grid = geo.createNode("grid", "source_grid")
grid.parm("rows").set(50)
grid.parm("cols").set(50)
# Create mountain (noise deformation)
mountain = geo.createNode("mountain::2.0", "deform")
mountain.setInput(0, grid)
# Create scatter
scatter = geo.createNode("scatter::2.0", "scatter_points")
scatter.setInput(0, mountain)
scatter.parm("npts").set(5000)
print(f"Created {geo.children()} nodes")
Step 3: Set Display and Render Flags
# Set display flag (what you see in viewport)
scatter.setDisplayFlag(True)
scatter.setRenderFlag(True)
# Layout nodes automatically
geo.layoutChildren()
Step 4: Verify Results
# Check node count
nodes = geo.children()
print(f"Total nodes: {len(nodes)}")
# Check connections
for node in nodes:
inputs = node.inputs()
if inputs:
print(f"{node.name()} <- {[n.name() for n in inputs if n]}")
What ships with it
2 files 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.
- today First seen · 757 lines · 60 tokens per session scan A 4a3e4cf4542e
houdini-python-automation is a skill published in the GitHub repository sideshowroberto/vfx-agent-toolkit (16 stars, last pushed 22d ago), licensed MIT. It adds 60 tokens to every session and 5,105 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 skills, from other repositories
artclaw-tool-executor
An instruction set for running tools from the ArtClaw Tool Manager, an interface for choosing and executing registered tools.
ue5-cpp-gameplay
UE5.6/UE5.7 gameplay C++ implementation for Actors, Components, DataAssets, and gameplay logic. Use when requests ask to write .h/.cpp pairs, expose UPROPERTY/UFUNCTION to Blueprint, use GameplayTags, or build reusable component-based systems.
content-hash-cache-pattern
Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.
python-release
Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.
scenario-zbrush-expert
Use when an agent drives Maxon ZBrush 2026 for any task (sculpt in ZBrush, DynaMesh, ZRemesher, UVs, export, polypaint, posing, 3D print, clean up an AI mesh in ZBrush), when writing ZBrush Python (zbrush.commands) or ZScript, when the ZBrush bridge is not answering, a palette path or set() does nothing, a scripted…
comfyui-node-registry
Authoring & publishing ComfyUI custom nodes to the Comfy Registry, covering node structure, pyproject.toml spec, comfy-cli publishing, and CI.