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 perniemann/pnCore --skill pn-blender-scriptinggit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/perniemann/pncore/pn-blender-scripting)<a href="https://agentmods.dev/skills/perniemann/pncore/pn-blender-scripting"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-blender-scripting/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/perniemann/pncore/pn-blender-scripting"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-blender-scripting.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 | $0.00048 | $0.01281 |
| Opus 5 | $0.00024 | $0.00641 |
| Sonnet 5 | $0.00010 | $0.00256 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
pn-blender-scripting 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 6d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender scripting skill
When to use
- Writing Python scripts for Blender (bpy API)
- Creating export pipelines (FBX, GLTF, custom formats)
- Automating asset preparation or batch operations
- Building Blender add-ons (operators, panels, preferences)
- Setting up headless Blender for CI or batch rendering
Python scripting (bpy API)
- Context: Use
bpy.contextfor scene, object, selection. Be aware of mode (Object, Edit, Sculpt); switch when needed. - Data access:
bpy.datafor meshes, materials, etc. Create and link to scene. Avoid orphan data. - Operators: Call
bpy.ops.*for built-in actions. Usebpy.ops.object.mode_set(mode='EDIT')etc. Check poll conditions. - Cleanup: Unlink and remove temporary objects; run
bpy.ops.outliner.orphans_purge()when appropriate. - No absolute paths: Use relative paths or
os.path.joinwith project root from env or config. Avoid hardcodedC:\or/home/.
Export pipeline
- FBX/GLTF: Use
bpy.ops.export_scene.fbxorbpy.ops.export_scene.gltf. Set scale, axes, and options via operator props. - Batch processing: Iterate over objects or files; run export in loop. Use
bpy.ops.wm.open_mainfileandbpy.ops.wm.save_mainfilefor batch. - Naming conventions: Use consistent prefixes (e.g.
SM_for static mesh,SK_for skeleton). Match target engine conventions. - Script structure: Parse args (e.g.
sys.argv) for input/output paths when running headless.
Asset preparation
- UV unwrapping: Use
bpy.ops.uv.unwrapor smart project. Ensure no overlapping UVs for lightmaps. Document conventions. - Materials: Set up for target engine (PBR: base color, roughness, metallic, normal). Use node groups for reuse.
- LOD generation: Use Decimate modifier or manual meshes. Name LOD0, LOD1, etc. Export with correct naming.
- Origin: Set object origin to center or pivot as required. Use
bpy.ops.object.origin_set().
Scene organization
- Collections: Use hierarchy (e.g. Environment, Characters, Props). Name clearly.
- Naming: Consistent naming for objects, materials, meshes. Avoid spaces; use underscores.
- Cleanup: Remove unused materials, orphan data. Apply modifiers before export when needed.
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.
- 6d ago First seen · 70 lines · 48 tokens per session scan A d6e61d21687d
pn-blender-scripting is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 1,281 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 2026-09-03.
Other skills, from other repositories
game-art
Game art principles. Visual style selection, asset pipeline, animation workflow.
game-audio
Game audio principles. Sound design, music integration, adaptive audio systems.
pixel-art
Pixel art w/ era palettes (NES, Game Boy, PICO-8).
typescript
TypeScript coding conventions, best practices, and patterns for writing clean, maintainable code.
pose-library-design
Design reusable 2D character pose libraries, action cycles, and expression states for data-driven animation.
generate-images-with-firebase-ai
Use when generating or editing images from Flutter/Dart with Firebase AI Logic and a Gemini image model (Nano Banana), making the first call work, choosing Gemini Developer API vs Vertex AI, hitting quota, billing or App Check failures, getting empty or image-only responses, sending a user photo as input, controlling…