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 sandraschi/blender-mcp --skill blender-expertgit clone --depth 1 https://github.com/sandraschi/blender-mcpWrote 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/sandraschi/blender-mcp/blender-expert)<a href="https://agentmods.dev/skills/sandraschi/blender-mcp/blender-expert"><img src="https://agentmods.dev/badge/skills/sandraschi/blender-mcp/blender-expert/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/sandraschi/blender-mcp/blender-expert"><img src="https://agentmods.dev/badge/skills/sandraschi/blender-mcp/blender-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.01614 |
| Opus 5 | $0.00017 | $0.00807 |
| Sonnet 5 | $0.00007 | $0.00323 |
| Haiku 4.5 | $0.00003 | $0.00161 |
Grade A, and why
blender-expert 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 10d ago.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender Expert Skill
Description: Comprehensive Blender expertise covering modeling, animation, materials, rendering, scripting, scene management, and pipeline automation. Handles the full 3D content creation workflow.
Trigger Phrases
- "Create a [object]" / "Model a [object]"
- "Add material to [object]"
- "Render the scene"
- "Animate [object] along a path"
- "Export to [format]"
- "Optimize scene for [platform]"
- "Apply modifier [type] to [object]"
- "Set up lighting for [scenario]"
- "Batch process all [object]"
- "Create a robot / character / building"
- "Grease pencil animation"
- "UV unwrap [object]"
- "Rig [object] for animation"
Tool Categories
Scene & Object Management
blender_status(operation="status")— Server health, Blender connectivityscene_get_hierarchy()— Full scene tree: collections, objects, typesmanage_object_repo(operation=...)— Save/load/search/delete from object depotblender_selection(operation=...)— Select, deselect, toggle objects by type/collection
Modeling & Construction
construct_object(description=..., complexity=..., style_preset=...)— Natural-language 3D construction via LLM samplingblender_mesh(operation=..., ...)— Create/modify/apply mesh primitives, booleansblender_modifiers(operation=..., ...)— Apply decimate, subdivision, mirror, array, solidify, bevel, etc.blender_sculpt(operation=..., ...)— Sculpting operations (remesh, dyntopo, detail flood)blender_geometry_nodes(operation=..., ...)— Geometry node groups, inputs, execution
Materials & Textures
blender_materials(operation=..., ...)— Create/assign/edit PBR materials, node-based shadersblender_shader(operation=..., ...)— Shader node graph operationsblender_textures(operation=..., ...)— Texture baking, image managementmaterial_apply(object=..., material=...)— Quick material assignmentblender_uv(operation=..., ...)— UV unwrap, pack, smart project
Animation
blender_animation(operation=..., ...)— Keyframes, motion paths, NLA tracks, F-curvesblender_rigging(operation=..., ...)— Armature, bone constraints, IK/FK, weight paintblender_shapekeys(operation=..., ...)— Shape key create/edit/animate
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.
- 10d ago First seen · 127 lines · 34 tokens per session scan A f11a867bec14
blender-expert is a skill published in the GitHub repository sandraschi/blender-mcp (42 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 1,614 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
threebrowser-studio-mcp
Author, inspect, render, validate, animate, and save Three.js WebGPU projects in the native ThreeBrowser Studio through its real threestudio MCP tools. Use whenever Codex is asked to build or edit a ThreeBrowser Studio scene, material, Blender-style shader or texture graph, animation, lighting setup, camera, or…
mcp-musescore
Use the ghchen99/mcp-musescore MCP server to inspect, navigate, compose, and edit an open MuseScore score through its QML WebSocket plugin.
blender-mcp
Drive Blender via the catalog blender MCP, with bpy recipes.
create-3d-model
Create and refine portable 3D models from text prompts, one or more reference images, wireframes, orthographic views, templates, texture atlases, or existing 3D assets. Use whenever the dsh agent must model or reconstruct geometry, match visual references, create materials and UVs, rig or animate a model, validate…
quality-refinement-autoloop
Run a self-refinement loop when a Blender result is subpar, user expectations are not met, validation fails, or repeated issues reveal missing skill depth. The loop diagnoses the gap, decides whether to repair the artifact or acquire/refine a generic skill, sanitizes lessons for reusable publication, updates…
blender-mcp
Control Blender directly from Gauss via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.