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 Kevin-Liu-01/Agent-Machines --skill blender-web-pipelinegit clone --depth 1 https://github.com/Kevin-Liu-01/Agent-MachinesWrote 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/kevin-liu-01/agent-machines/blender-web-pipeline)<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/blender-web-pipeline"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/blender-web-pipeline/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/kevin-liu-01/agent-machines/blender-web-pipeline"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/blender-web-pipeline.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 | $0.00116 | $0.04144 |
| Opus 5 | $0.00058 | $0.02072 |
| Sonnet 5 | $0.00023 | $0.00829 |
| Haiku 4.5 | $0.00012 | $0.00414 |
Grade A, and why
blender-web-pipeline 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 12d 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.
This is a copy
100% identical to blender-web-pipeline — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 614 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender Web Pipeline
Overview
Blender Web Pipeline skill provides workflows for exporting 3D models and animations from Blender to web-optimized formats (primarily glTF 2.0). It covers Python scripting for batch processing, optimization techniques for web performance, and integration with web 3D libraries like Three.js and Babylon.js.
When to use this skill:
- Exporting Blender models for web applications
- Batch processing multiple 3D assets
- Optimizing file sizes for web delivery
- Automating repetitive Blender tasks
- Creating production pipelines for 3D web content
- Converting legacy formats to glTF
Key capabilities:
- glTF 2.0 export with optimization
- Python (bpy) automation scripts
- Texture baking and compression
- LOD (Level of Detail) generation
- Batch processing workflows
- Material and lighting optimization for web
Core Concepts
glTF 2.0 Format
Why glTF for Web:
- Industry-standard 3D format for web
- Efficient binary encoding (.glb)
- PBR materials support
- Animation and skinning
- Extensible with custom data
- Wide library support (Three.js, Babylon.js, etc.)
glTF vs GLB:
.gltf = JSON + external .bin + external textures
.glb = Single binary file (recommended for web)
Blender Python API (bpy)
Access Blender data and operations via Python:
import bpy
# Access scene data
scene = bpy.context.scene
objects = bpy.data.objects
# Modify objects
obj = bpy.data.objects['Cube']
obj.location = (0, 0, 1)
obj.scale = (2, 2, 2)
# Export glTF
bpy.ops.export_scene.gltf(
filepath='/path/to/model.glb',
export_format='GLB'
)
Web Optimization Goals
Target Metrics:
- File size: <5 MB per model (ideal <1 MB)
- Polygon count: <50k triangles for real-time
- Texture resolution: 2048x2048 max (1024x1024 preferred)
- Draw calls: Minimize via texture atlases
- Load time: <2 seconds on average connection
Common Patterns
1. Basic glTF Export (Manual)
# Blender Python Console or script
import bpy
# Select objects to export (optional - exports all if none selected)
bpy.ops.object.select_all(action='DESELECT')
bpy.data.objects['MyModel'].select_set(True)
# Export as GLB
bpy.ops.export_scene.gltf(
filepath='/path/to/output.glb',
export_format='GLB', # Binary format
use_selection=True, # Export selected only
export_apply=True, # Apply modifiers
export_texcoords=True, # UV coordinates
export_normals=True, # Normals
export_materials='EXPORT', # Export materials
export_colors=True, # Vertex colors
export_cameras=False, # Skip cameras
export_lights=False, # Skip lights
export_animations=True, # Include animations
export_draco_mesh_compression_enable=True, # Compress geometry
export_draco_mesh_compression_level=6, # 0-10 (6 recommended)
export_draco_position_quantization=14, # 8-14 bits
export_draco_normal_quantization=10, # 8-10 bits
export_draco_texcoord_quantization=12 # 8-12 bits
)
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.
- 12d ago First seen · 614 lines · 116 tokens per session scan A 788e4c2fa8d5
blender-web-pipeline is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed today), licensed MIT. It adds 116 tokens to every session and 4,144 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to blender-web-pipeline, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
21st-ui
Find, install, and generate UI with 21st.dev. Use when the user asks for a UI component (pricing table, hero, navbar, dashboard, form, etc.), wants design inspiration, needs a brand logo as an SVG component, or wants to generate new UI from a prompt.
harness-design-fuzzing
Reference vocabulary for designing instrumented harnesses that drive vulnerability discovery — design classes (trigger-driven vs coverage-driven), tiered scope (T1 isolated function / T2 multi-component / T3 full build), systematic input exploration, the two-coverage distinction (fuzzer-feedback vs audit)…
workspace-builder
Build ServiceNow App Engine Studio applications — sysscope creation, scoped tables, sysawworkspace with lists/forms, the sysux record chain behind UI Builder workspaces, data brokers, and application export readiness checks. Never create a UI Builder page by inserting a sysuxpage row.
ui-builder-patterns
Build ServiceNow UI Builder / Next Experience pages — macroponents, GraphQL/script data brokers, client state parameters, event handlers (NOWRECORDLIST etc.), and now-record-list/form component configuration.
remotion
Create editable AI video projects with Remotion and React, then preview and render them to MP4. Use for vertical short videos, product demos, story-driven animations, HUD/tech visuals, feed ads, tutorial videos, subtitles, voiceover, sound effects, and code-based video iteration.
widget-coherence
Build Service Portal widgets (spwidget) with synchronized server/client/HTML — data. initialization, ng-click + controller method matching, c.server.get action handlers, and Angular directive usage.