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 alivirgo/Major-AI-Skills --skill blendergit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote 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/alivirgo/major-ai-skills/blender)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/blender"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/blender/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/alivirgo/major-ai-skills/blender"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/blender.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 | $0.00034 | $0.01667 |
| Opus 5.5 | $0.00014 | $0.00667 |
| Sonnet 5.5 | $0.00007 | $0.00333 |
| Haiku 4.5 | $0.00003 | $0.00167 |
Grade A, and why
blender 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 1mo 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender 4.x 3D Creation Suite AI Skill Guide (Claude)
Overview & Engine Architecture
Blender 4.2 LTS / 4.3+ / 5.x is an open-source DCC suite. Agent automation runs through bpy (Python), CLI background mode, and optional Geometry Nodes procedural graphs. Render engines: Cycles (path-traced, farm-friendly) and EEVEE (real-time; identifier changed across 4.2→5.0 — resolve at runtime, do not hardcode BLENDER_EEVEE_NEXT).
Claude acts as a Principal Technical Artist / Pipeline TD: headless blender --background, deterministic stills, idempotent scene scripts, addon packaging (bl_info), and export validation (glTF/FBX/USD).
┌─────────────────────────────────────────────────────────────┐
│ Blender automation stack │
│ bpy.data / RNA → depsgraph → Cycles|EEVEE → files │
│ CLI: -b blend -P script.py | -E CYCLES -f N -a (last!) │
│ Determinism: cycles.seed, fixed samples, no animated seed │
└─────────────────────────────────────────────────────────────┘
Version pins (document in every pipeline README): pin Blender minor (e.g. 4.2.11 LTS). GPU backends: CUDA / OPTIX / HIP / ONEAPI / METAL after -- (see CLI render docs).
When to use / when not to
Use when
- Batch stills/animations, asset conversion, procedural scene generation, CI smoke renders.
- Geometry Nodes or modifier stacks must be evaluated headlessly.
- You need reproducible Cycles output (golden frames, A/B materials).
Do not use when
- Real-time game runtime (use Unity/Godot/Unreal skills).
- Legal/commercial work requires Autodesk-only formats without conversion — validate export importers downstream.
- Host has no GPU and Cycles GPU is mandatory without CPU fallback plan.
Operational Capabilities & Agent Directives
- Data API first: Mutate
bpy.data,scene, object properties; usebpy.opsonly with explicit context overrides in--background. - CLI argument order: Put
-o,-F,-E, frame range before-f/-a; render flags must be last or Blender ignores them. - Deterministic Cycles: Set
scene.cycles.seed, disable animated seed, fix sample count (turn off adaptive sampling for golden tests); document OIDN availability — headless Linux builds often lack OpenImageDenoise and abort if denoise stays enabled. - Color management: Set
scene.view_settings.view_transform,look, and export color space explicitly; linear EXR for comp, sRGB/Rec.709 for web stills — never assume default OCIO matches farm workers. - Engine resolution:
scene.render.engine = bpy.context.preferences.addons['cycles'].preferences...or iteratebpy.types.RenderEngine— EEVEE enum names differ by version. - Exit codes: Wrap
main(); on failuresys.exit(1)so CI fails; logblender --versionat job start.
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.
- 1mo ago Changed · -9 lines 31055315b673
- 1mo ago Changed · -2 tokens per session 917b6d244858
- 2mo ago First seen · 149 lines · 36 tokens per session scan A 97afd228f939
blender is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,667 once invoked, about $0.0001 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 2026-08-31.
blender compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| blenderalivirgo/Major-AI-Skills | Skill | 2 | yesterday | MIT | A | 34 | Claude Code |
| blenderznlgis/opengis-skills | Skill | 76 | 10d ago | MIT | B | 98 | Claude Code, Codex |
| blender-mcpGGbond-bo/MemOmics-Agent | Skill | 31 | yesterday | MIT | A | 17 | Claude Code, Codex |
| using-blenderellmos-ai/skills | Skill | 9 | 4d ago | MIT | A | 94 | Codex |
| blender-mcpmath-inc/OpenGauss | Skill | 1.3k | 7mo ago | MIT | A | 54 | Claude Code, Codex |
| blender-mcpnativ3ai/hermes-agent-camel | Skill | 193 | yesterday | MIT | A | 53 | Claude Code, Codex |
| blender-mcpraphaelmansuy/edgecrab | Skill | 93 | 3mo ago | none | A | 53 | Claude Code, Codex |