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 agentmods add skills/ifbars/blender-agent-studio/blender-simulation-workflownpx skills add ifBars/blender-agent-studio --skill blender-simulation-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-simulation-workflow)<a href="https://agentmods.dev/skills/ifbars/blender-agent-studio/blender-simulation-workflow"><img src="https://agentmods.dev/badge/skills/ifbars/blender-agent-studio/blender-simulation-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 | $0.00066 | $0.00721 |
| Opus 5 | $0.00033 | $0.00360 |
| Sonnet 5 | $0.00013 | $0.00144 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
blender-simulation-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 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender Simulation Workflow
Simulation is a cache-producing build step. Preserve the setup and cache provenance; a visually plausible single frame is not proof that it is stable.
Define the simulation contract
Record the simulation type, solver, timeline, scale, gravity/forces, collision objects, emitters, domain bounds, desired behavior, cache location, resolution or substeps, and deliverable format. State the frames that establish onset, peak interaction, and settle. For fluids, explicitly distinguish liquid from gas/fire/smoke and whether a mesh, particles, or volume is the deliverable.
Use a project-local cache directory outside source control. Never overwrite an existing approved bake without creating a new output location or explicit user approval.
Build a controlled setup
- Apply or account for object scale; use real-world scene scale and record units. Mis-scaled colliders and domains invalidate tuning conclusions.
- Name domain, flow/emitter, effector/collider, force, cache, and output objects semantically. Keep a collection for inputs separate from generated mesh, volume, particles, or bake artifacts.
- Start with a short, coarse preview cache to prove the causal setup, collision direction, and timing. Do not begin a costly final bake before opening preview evidence.
- For fluid/smoke/fire, bound the domain tightly enough to control cost while leaving required motion margin. Use Modular or Final cache intentionally; document the ordered bake stages when applicable.
- For rigid, cloth, soft-body, particle, or hair work, establish collider thickness, substeps, damping/friction, self-collision, and pin/attachment constraints before aesthetic forces or turbulence.
- Set seeds explicitly for stochastic effects. Preserve cache settings and simulator version alongside the generation script.
Bake and validate
- Bake the preview, then inspect the specified critical frames from at least two useful cameras.
- Check that emitters and colliders affect the result at the intended time; that domains do not clip it; that collision does not tunnel, explode, or penetrate; and that mass, drag, settling, and scale read plausibly.
- Change one causal parameter group at a time, invalidate the affected cache, and rebake the smallest frame interval that proves the change.
- Bake final data only after the preview passes. Verify every expected cache stage/file is present and the timeline reads it rather than recomputing an implicit temporary state.
- Render the requested critical frames and, when timing matters, an encoded
preview or final sequence using
$blender-agent-studio:blender-rendering-workflow.
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.
- 5d ago First seen · 65 lines · 66 tokens per session scan A eddf2091d350
blender-simulation-workflow is a skill published in the GitHub repository ifBars/blender-agent-studio (10 stars, last pushed 18d ago), licensed MIT. It adds 66 tokens to every session and 721 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…
grok-subagent
Run xAI Grok as a second-model subagent from Claude Code for independent review, cross-checking, structured output, or parallel fanout. Use when the user asks to consult Grok or xAI, when Claude and Codex need a third vote, or when multiple files or candidates benefit from independent passes. Includes safe wrappers…
blender-mcp
Drive Blender via the catalog blender MCP, with bpy recipes.