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-renderinggit 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-rendering)<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/blender-rendering"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/blender-rendering/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-rendering"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/blender-rendering.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 | $0.00054 | $0.02701 |
| Opus 5.5 | $0.00022 | $0.01080 |
| Sonnet 5.5 | $0.00011 | $0.00540 |
| Haiku 4.5 | $0.00005 | $0.00270 |
Grade A, and why
blender-rendering scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Removed HTTP Bridge requirements and curl health-check How it starts
The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender Rendering Skill
Version: 2.1.0 Last Updated: 2026-09-10 Dependencies: Blender 5.1+
Breaking Changes (4.5+ / 5.1+)
import bpy
# 1. EEVEE engine renamed (complete removal)
bpy.context.scene.render.engine = 'BLENDER_EEVEE_NEXT' # Not 'BLENDER_EEVEE'
# 2. Bloom removed from EEVEE - use Compositor Glare node
# scene.eevee.use_bloom = True <- AttributeError in 4.5.3+
# 3. SSR removed - use ray tracing
# scene.eevee.use_ssr = True <- AttributeError
scene.eevee.use_raytracing = True # replacement
# 4. Principled BSDF input names changed
bsdf.inputs["Transmission Weight"].default_value = 1.0 # was "Transmission"
bsdf.inputs["Subsurface Weight"].default_value = 0.2 # was "Subsurface"
bsdf.inputs["Emission Color"].default_value = (1,1,1,1) # was "Emission"
# 5. Cycles settings
cycles = bpy.context.scene.cycles # Direct access - no import needed
cycles.samples = 128
EEVEE Next / Cycles facts (loop-gauntlet round-2/3 lessons, 2026-09-10)
- Emissive meshes do not illuminate anything in EEVEE Next. A mesh with an emission shader (LED strips, glowing coves) renders bright itself but casts no light on neighbouring surfaces. If a reference shows spill from a glowing surface, place a real light (area light along the strip) - do not expect the emissive mesh to do it.
- Light-probe volume bake from a script/MCP execute context returns
FINISHEDwithout actually baking.bpy.ops.object.lightprobe_cache_bake(subset='ALL')completes in well under a second (even after waiting 60 s) with no visible change, andbpy.app.is_job_runninghas noLIGHT_BAKEenum to poll the bake state. Verify with an A/B render (probe object hidden vs visible) before relying on a bake - a script-triggered bake is unverifiable otherwise. - Blender 5.1
LightProbeVolumeproperties:resolution_x,resolution_y,resolution_z,surfel_density(int),bake_samples,capture_world. The oldergrid_*names (grid_resolution_x, etc.) do not exist on this version - do not assume they do from older docs. - Cycles light linking (Blender 4.0+):
obj.light_linking.receiver_collectionrestricts which objects a light illuminates. Use it to give each zone (and each matched camera view) its own lights without those lights leaking into other zones - a chamber-only near-vertical sun, a lantern-only point light, a hallway-only steeper sun, and view-only fills can all coexist in one scene this way. The linking collection does not need to be in the view layer and may hold child collections. - A strip emission value that reads as a clean bright line in EEVEE floods a room in Cycles. Moving an EEVEE-tuned rig to Cycles: strip emission strengths tuned for EEVEE (e.g. 40) need to drop roughly by a factor of 8 (to about 5) once Cycles adds real bounce light on top of them - re-measure with a mean-luminance readback rather than assuming a ratio.
What ships with it
4 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 · 336 lines · 54 tokens per session scan A b6dbf7ad6442
blender-rendering is a skill published in the GitHub repository sideshowroberto/vfx-agent-toolkit (16 stars, last pushed 22d ago), licensed MIT. It adds 54 tokens to every session and 2,701 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-02.
Other skills, from other repositories
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.
mesh-ops
Cross-adapter polygon modeling recipe pack for the shared cross-DCC modeling vocabulary. Structured RECIPES.yaml entries for primitive creation, hard-surface edits, topology cleanup, UV generation, radial arraying, and material assignment. Reusable by every DCC adapter's mesh-ops skill (maya, blender, houdini, 3dsmax…
marketplace-publish-extension
Infrastructure skill — publish (register/update) an extension package to a marketplace catalog. Reads the extension's SKILL.md frontmatter, constructs a CatalogEntry, and upserts it into the target marketplace.json. Optionally commits and pushes when the catalog source is a git repository. Use after scaffolding an…
marketplace-create-extension
Infrastructure skill — scaffold a new marketplace extension package (SKILL.md + tools.yaml + scripts/) with MIT-0 licensing. Use when creating a publishable marketplace entry for any DCC host. Not for editing existing extensions or driving live DCC scenes — use domain skills for that.
clawhub-compat
Example skill — demonstrates full compatibility with the ClawHub/OpenClaw skill format. Use as a reference when creating skills for both the dcc-mcp-core ecosystem and ClawHub marketplace. Not intended for production use — this is an authoring reference only.
example-layered-skill
Example skill — reference implementation of the internal layered architecture pattern (Tools / Services / Utils) for complex skills with shared business logic. Use as a template when a skill outgrows a single scripts/execute.py file. Not intended for production use — see docs/guide/skills.md for the architectural…