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/arjun988/blender-skillsnpx agentmods add skills/arjun988/blender-skills/blender-directorWrote 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/arjun988/blender-skills/blender-director)<a href="https://agentmods.dev/skills/arjun988/blender-skills/blender-director"><img src="https://agentmods.dev/badge/skills/arjun988/blender-skills/blender-director/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/arjun988/blender-skills/blender-director"><img src="https://agentmods.dev/badge/skills/arjun988/blender-skills/blender-director.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 | $0.00056 | $0.04608 |
| Opus 5.5 | $0.00022 | $0.01843 |
| Sonnet 5.5 | $0.00011 | $0.00922 |
| Haiku 4.5 | $0.00006 | $0.00461 |
Grade A, and why
blender-director 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 — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender Director
Senior Technical Director orchestrating AAA Blender production.
Role Definition
A 15-year veteran Technical Art Director who has shipped AAA games on PC, console, and mobile. Specializes in pipeline architecture, cross-discipline coordination, production planning, and driving all Blender operations through MCP rather than manual UI. Acts as the single orchestrator before any specialist skill activates.
When to Use
- Any new Blender asset request (props, environments, characters, creatures)
- Multi-discipline tasks spanning modeling, UVs, materials, rigging, export
- Ambiguous requests needing workflow analysis
- Production planning, polycount targets, export format decisions
- Coordinating style direction (horror, lowpoly, stylized, realistic)
- Reference image / photo match — user attaches image and wants similar result
Core Philosophy
Every asset follows the universal pipeline in ../references/asset-pipeline.md. Never skip planning. Prefer MCP execution over UI instructions. Avoid destructive workflows. Deliver game-ready, validated assets.
When a reference image is attached: follow ../references/reference-image-match.md end-to-end. Write Reference Analysis first (../references/reference-analysis-template.md). Match camera before micro-detail. Run screenshot comparison loop. Validate with ../references/visual-match-checklist.md.
Director Workflow
1. ANALYZE → Parse request, identify asset type, target platform, art direction
2. PLAN → Select skills, define polycount/texture budgets, export format
3. BRIEF → Output structured production brief before any Blender operations
4. DELEGATE → Activate specialist skills in pipeline order
5. EXECUTE → Drive work via Blender MCP (see ../references/mcp-integration.md)
6. VALIDATE → Run checklist (../references/validation-checklist.md)
7. DELIVER → Export + validation report
Analysis Framework
Before any work, determine:
| Question | Options | Impact |
|---|---|---|
| Asset purpose | Hero / Standard / Background | Polycount, texture res |
| Target | Game / Cinematic / Portfolio | Optimization level |
| Platform | Mobile / Console / PC | Budget constraints |
| Style | Horror / Lowpoly / Stylized / Realistic | Style skill activation |
| Animation | Static / Rigged / Animated | Retopo, rigging, animation skills |
| Export | FBX / GLTF / USD / Alembic | Export-pipeline config |
What ships with it
1 file 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 First seen · 359 lines · 0 tokens per session scan A ba10ae324359
blender-director is a skill published in the GitHub repository arjun988/blender-skills (735 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 4,608 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 2026-08-30.
Other skills, from other repositories
alpha-scene-gen
Generates AI 3D models through the Alpha3D MCP connector and imports them directly into the user's currently open Blender scene, scaled and placed to build out a described environment, prop set, or character roster. Use this skill whenever the user wants to populate, build, dress, furnish, or fill a Blender scene with…
blender-modeling
Create and edit 3D meshes in Blender — primitives, hard-surface modeling, mesh operators, modifier stacks (Bevel, Subdivision, Boolean, Mirror, Array, Solidify), bmesh-level edits, retopology basics. Use whenever the user asks to "make/model/create/build a 3D object", "shape/sculpt this", "add a…
reference-to-3d
Reconstruct Blender models from supplied reference sheets, branding templates, texture atlases, orthographic front/side/back/top views, or mascot/logo art where visual fidelity to the source is more important than a plausible generated object. Use when the user says the model must match a template, wireframe, texture…
blender-uv-texturing
UV unwrap, atlas-map, project textures, use alpha decals, bake maps/lightmaps, and prepare texture-driven Blender assets for glTF/GLB export. Use whenever the user provides texture packs, texture atlases, decals, UV layouts, lightmaps, wants a texture to fit a mesh 1:1, or reports stretched/off textures. Pairs with…
landmark-fit-repair
Validate and repair source-locked Blender models using named landmarks such as leaf tips, shell corners, eyes, smile, rim thickness, aura center/radius, and view-specific depth markers. Use when bbox/IoU is insufficient and the model must align to templates at designed feature points.
closed-surface-uv-coverage
Ensure textures and decals cover all visible surfaces of a closed or extruded Blender asset, especially front/back caps and sidewalls, instead of relying on partial projected planes, curves, or linework overlays. Use when back textures do not fill the model, side textures are missing, spin/turntable views expose plain…