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 blender-controlnet-passesgit 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/blender-controlnet-passes)<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/blender-controlnet-passes"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/blender-controlnet-passes/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/blender-controlnet-passes"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/blender-controlnet-passes.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 | $0.02642 |
| Opus 5.5 | $0.00024 | $0.01057 |
| Sonnet 5.5 | $0.00012 | $0.00528 |
| Haiku 4.5 | $0.00006 | $0.00264 |
Grade A, and why
blender-controlnet-passes 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender ControlNet Passes
Version: 1.1.1 | Last Updated: 2026-08-21 | Blender: 5.x
One parameterized script replaces the per-project pass-render scripts:
scripts/setup_controlnet_passes.py (relative to this skill directory)
Outputs per shot: <root>/<shot>/grey/ (16-bit PNG clay), <root>/<shot>/depth/
(16-bit PNG, near=white/far=black, fixed normalization), <root>/<shot>/crypto/
(multilayer EXR: Combined + CryptoObject layers), optional grey MP4, and a
<shot>_manifest.json.
Script vs MCP-interactive setup
- Use the script for anything repeatable: full sequences, batch/CLI background renders, half-speed re-renders, or when a scene needs the standard grey/depth/crypto setup from scratch. Import it via MCP too -- do not re-derive the compositor graph by hand.
- Use MCP-interactive only for scene-specific prep the script cannot know about: hiding locator meshes, switching shot collections/cameras, inspecting why a render looks wrong. Then call the script's functions.
CLI (background render)
blender -b shot.blend -P setup_controlnet_passes.py -- --shot SHOT_0010 --output-root "X:/renders" --test-slice
blender -b shot.blend -P setup_controlnet_passes.py -- --shot SHOT_0010 --output-root "X:/renders" --render --speed 0.5 --mp4
MCP (execute_blender_code)
import sys
sys.path.append(r"<workspace>/Blender/scripts")
import setup_controlnet_passes as scp
setup = scp.setup_scene(shot_name="SHOT_0010", output_root=r"X:/renders")
scp.render_sequence(setup, test_slice=10) # verify first
scp.render_sequence(setup) # then full range
With no action flag the CLI does setup only (no rendering). --test-slice
renders N frames (default 10) into a sibling <shot>_TEST folder; --render
does the full range.
Parameters
| Param (CLI / setup_scene) | Default | Meaning |
|---|---|---|
--shot / shot_name |
SHOT_0010 | file prefix + shot folder name |
--output-root / output_root |
controlnet/ next to .blend |
base output dir |
--passes / passes |
grey,depth,crypto | subset of the three passes |
--frame-start --frame-end |
scene range | render range |
--speed |
1.0 | 0.5 = half speed via frame_set(f, subframe=) sub-frame interpolation (for video-model minimum durations) |
--min-duration |
0 | seconds; tail-hold pad the last frame to reach it |
--wireframe + --wire-pixel-size |
off / 1.0 px | wireframe overlay on clay |
--grey-value --roughness |
0.5 / 0.75 | clay material |
--depth-max / depth_max |
100.0 | distance mapped to black (compositor-side) |
--crypto-depth |
6 | cryptomatte depth; EXR layers = ceil(depth/2) |
--depth-writer |
auto | file_output (background-safe) or viewer (interactive) |
--taa-samples --motion-blur |
untouched | optional EEVEE stability overrides |
--mp4 / make_mp4 |
off | ffmpeg encode of grey PNGs at SCENE fps |
--test-slice [N] / test_slice |
off | render first N frames to <shot>_TEST |
What ships with it
3 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 · 168 lines · 60 tokens per session scan A 01e13abcdb8d
blender-controlnet-passes 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 2,642 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
commercial-3d-product-render
Product lookdev and render-review helpers for commercial 3D work.
sd-node-ops
A Substance Designer guide for creating, connecting, and configuring nodes in material graphs, which are step-by-step networks that produce textures.
blender-material-ops
A guide for creating and editing Blender materials, which control how 3D objects look when rendered. It covers shader nodes, physically based materials, and Blender setups whose node names may differ by language.
sp-operation-rules
A guide to operating Substance Painter, a tool for painting materials and textures onto 3D models. It explains the Python interface, project checks, layer and texture-set work, baking, exporting, and precautions for changes that cannot be undone through the interface.
dcc-node-graph-workflow
A general method for planning and building node graphs in Unreal Engine Blueprints, Substance Designer materials, and Unreal materials.
artclaw-material
ArtClaw official Material node graph write operations for UE5. Create, delete, connect, and edit MaterialExpression nodes in a Material's node graph, create new Material assets, set material properties, and recompile materials. Use when AI needs to: (1) build materials from scratch by assembling expression nodes, (2)…