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/poorvith-mp/skills-gamedevnpx agentmods add skills/poorvith-mp/skills-gamedev/blender-toolingWrote 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/poorvith-mp/skills-gamedev/blender-tooling)<a href="https://agentmods.dev/skills/poorvith-mp/skills-gamedev/blender-tooling"><img src="https://agentmods.dev/badge/skills/poorvith-mp/skills-gamedev/blender-tooling/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/poorvith-mp/skills-gamedev/blender-tooling"><img src="https://agentmods.dev/badge/skills/poorvith-mp/skills-gamedev/blender-tooling.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 | $0.01536 |
| Opus 5 | $0.00017 | $0.00768 |
| Sonnet 5 | $0.00007 | $0.00307 |
| Haiku 4.5 | $0.00003 | $0.00154 |
Grade A, and why
blender-tooling 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 5d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
blender-tooling
Core Philosophy
Manual 3D asset preparation—clicking through 14 menus to apply transforms, rename 40 bones, fix inverted normals, and export FBX files one by one—is an enormous drain on game studio productivity. High-performance art pipelines rely on custom Python automation within Blender (bpy). Professional Blender tooling builds robust, headless CLI batch exporters, automated asset validation linters, custom UI panels, and asset post-processors that eliminate human error.
4-Step Blender Python Tooling Architecture
Step 1: The Blender Python API Anatomy (bpy)
- Core Submodules:
bpy.context: Active selection, active mode, active scene.bpy.data: Datablocks (meshes, armatures, materials, textures, actions).bpy.ops: Operator execution (e.g.bpy.ops.object.transform_apply()).bpy.types: Base classes for creating custom Operators, Panels, and Property Groups.
- The Safe Operator Rule:
- Avoid calling
bpy.opsinside heavy loops (it is slow and requires active 3D context). Mutatebpy.dataand mesh attributes directly via Python data APIs where possible.
- Avoid calling
Step 2: Automated Asset Validation Linters
- Pre-Export Linter Checks:
- Write automated scripts that assert:
- Unapplied Scale:
obj.scale != Vector((1.0, 1.0, 1.0)). - Ngon Count:
any(len(poly.vertices) > 4 for poly in mesh.polygons). - Missing Materials / Textures: Materials with missing image filepaths.
- Origin Alignment: Origin not at
(0, 0, 0)for static props.
- Unapplied Scale:
- Write automated scripts that assert:
- The Hard Blocker Gate:
- If a validation check fails, abort export and display an error modal listing exact offender object names.
Step 3: Custom Add-On Development (bl_info Standard)
- Add-On Architecture:
- Structure add-ons with formal registration:
bl_info = { "name": "Studio Pipeline Exporter", "author": "Technical Art Team", "version": (1, 2, 0), "blender": (4, 1, 0), "category": "Pipeline", }
- Structure add-ons with formal registration:
- Custom UI Panels in the 3D Viewport:
- Create a dedicated sidebar tab (
N-Panel) exposing 1-click batch actions: "Sanitize Asset", "Bake Normal Map", "Export Game-Ready FBX".
- Create a dedicated sidebar tab (
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.
- 5d ago First seen · 154 lines · 34 tokens per session scan A a3e2bf9a48ef
blender-tooling is a skill published in the GitHub repository poorvith-mp/skills-gamedev (4 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 1,536 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 2026-09-06.
Other skills, from other repositories
unity-shader-artist
!cat skills/shared/game-visual-foundations.md 2>/dev/null || echo "=== Visual Foundations not loaded ===" !cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/game-test-protocol.md 2>/dev/null || true !cat skills/shared/protocols/quality-gate.md 2>/dev/null || true !cat…
assets-shader-get-data
Get detailed data about a shader asset — properties, subshaders, passes, compilation messages, and supported status. Supports token-saving path-scoped reads via paths or viewQuery. Use 'assets-find' with t:Shader or 'assets-shader-list-all' to locate the shader first.
gameobject-component-modify
Modify a specific Component on a GameObject in opened Prefab or in a Scene. Allows direct modification of component fields and properties without wrapping in GameObject structure. Use 'gameobject-component-get' first to inspect the component structure before modifying. Three modification surfaces are available…
editor-selection-get
Get information about the current Selection in the Unity Editor — active object, active transform, selected GameObjects, transforms, instance IDs, and asset GUIDs (each enrichment is opt-in). Pair with 'editor-selection-set' to change the selection.
object-modify
Modify a Unity UnityEngine.Object's serializable fields/properties. Three modification surfaces are available (objectDiff, pathPatches, jsonPatch) — see the skill body. Use 'object-get-data' first to inspect the object structure.
script-execute
Compiles and executes C# code dynamically using Roslyn. Supports a full-code mode (default) and a body-only mode — see the skill body for the difference and for how to pass Unity object references as parameters.