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 ifBars/blender-agent-studio --skill blender-modeling-workflowgit clone --depth 1 https://github.com/ifBars/blender-agent-studioWrote 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/ifbars/blender-agent-studio/blender-modeling-workflow)<a href="https://agentmods.dev/skills/ifbars/blender-agent-studio/blender-modeling-workflow"><img src="https://agentmods.dev/badge/skills/ifbars/blender-agent-studio/blender-modeling-workflow.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.01504 |
| Opus 5 | $0.00032 | $0.00752 |
| Sonnet 5 | $0.00013 | $0.00301 |
| Haiku 4.5 | $0.00006 | $0.00150 |
Grade A, and why
blender-modeling-workflow 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 today.
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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender Modeling Workflow
Read the shared execution guidance once per task for autonomous decisions, evidence cadence, and long-task continuity.
Create the asset as source-controlled Python plus generated .blend and .glb outputs. Treat the script as the durable source and Blender as the execution runtime.
For a render-only scene, route final delivery through the rendering workflow:
source, self-contained .blend, images and render manifest are sufficient.
Require GLB and fresh-import gates when a downstream asset/export is part of the
contract. Do not imply that procedural shaders, atmospheric volumes or Cycles
lighting survive a GLB export unchanged.
Establish the contract
- Resolve the exact Blender executable and record
blender --version. - Resolve routine visual and technical choices from context and state useful
defaults. Use
$blender-agent-studio:blender-art-direction-intakewhen an unresolved decision would cause substantial rework and context provides no reasonable default, or when the user explicitly requests a brief/concept. - Convert the request into a short modeling contract before editing:
- required parts and visible relationships;
- intended style and materials;
- intended finish quality and whether low-poly is actually requested;
- dimensions and an appropriate triangle range or performance target;
- moving parts, pivots, or required contexts;
- named stages, review evidence, and any user approval gates;
- deliverables and evidence views.
- Keep subjective goals as explicit review questions. Do not silently turn them into arbitrary geometry thresholds.
- Read references/modeling-contract.md for the contract shape.
Default to a finished-quality asset
Treat “game-ready,” “stylized,” and “optimized” as quality constraints, not as synonyms for visibly low-poly.
- Unless the user explicitly requests low-poly, blockout-only, voxel, faceted, PS1-era, or an unusually strict platform budget, target a polished smooth model with clean silhouettes, bevels or support geometry, appropriate subdivision or curve resolution, and readable secondary and tertiary forms.
- Use the lowest density that preserves the intended finish from every evidence view. Do not optimize away the shape language, material breaks, or contact detail that makes the asset feel complete.
- Preserve an explicitly requested low-poly style. Do not smooth or subdivide away intentional planar forms merely because the normal default is polished.
- A triangle ceiling is a limit, not a target. Do not celebrate being far under budget when the result still reads as a blockout.
What ships with it
5 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.
- today Changed · +18 lines 3be4f5470168
- 7d ago First seen · 119 lines · 64 tokens per session scan A 10adb43bf498
blender-modeling-workflow is a skill published in the GitHub repository ifBars/blender-agent-studio (14 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 1,504 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
dcc-mcp-blender-setup
Set up dcc-mcp-blender for an agent or operator: install Blender Python dependencies with Blender's bundled interpreter, install a startup bridge, generate MCP host configuration, and run a first live-tool smoke prompt.
blender-import-to-scene
Blender cross-DCC asset import skill — consumes an AssetDescriptor, opens the asset file in Blender, and returns an ImportToSceneResult. Use as the receiving end of the asset import pipeline after an asset-source skill resolves the descriptor.
3d-asset-quality
Model what a 3D object is, not merely its outline, and prove quality with geometry-only close-up renders plus a manifest. Use before building, generating, importing, cleaning, reviewing, or signing off on meshes, props, buildings, terrain, environments, levels, dioramas, and set dressing in Blender, game engines, glTF…
asset-judge-loop
The build→judge→rebuild loop for MULTI-asset 3D work — whenever a scene, environment, village, level, diorama or any batch of more than 3 assets is being built (in Blender, via MCP, procedurally, or by generation), and especially when builder subagents are doing the work. The parent orchestrates; builders never…
blender-mcp
Drive Blender via the catalog blender MCP, with bpy recipes.
blender-interchange
Blender interchange skill for typed FBX/OBJ/USD imports, GLTF/USD/Alembic exports, and repeatable batch exports. Use for moving assets between DCC, game, and pipeline tools before falling back to scripting.