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-art-direction-intakegit 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-art-direction-intake)<a href="https://agentmods.dev/skills/ifbars/blender-agent-studio/blender-art-direction-intake"><img src="https://agentmods.dev/badge/skills/ifbars/blender-agent-studio/blender-art-direction-intake/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/ifbars/blender-agent-studio/blender-art-direction-intake"><img src="https://agentmods.dev/badge/skills/ifbars/blender-agent-studio/blender-art-direction-intake.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 | $0.00061 | $0.00574 |
| Opus 5 | $0.00030 | $0.00287 |
| Sonnet 5 | $0.00012 | $0.00115 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
blender-art-direction-intake 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 3d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender Art Direction Intake
Read the shared execution guidance once per task for autonomous decisions, evidence cadence, and long-task continuity.
Resolve the visual contract from the request, supplied references, and existing scene. Record routine assumptions and start authorized work; a missing field does not by itself require a question or a user-approved contract.
Clarify the brief
Consider these decisions, asking only about consequential unresolved choices for which context provides no reasonable default:
- subject, purpose, platform, scale, and export target;
- art style, reference period/genre, level of realism, and visual priorities;
- required parts, materials, colors, logos/text, motion, and interaction;
- camera/view requirements, lighting/mood, and whether the result is for a single shot, turntable, animation, or runtime asset;
- performance, topology, rigging, simulation, and delivery constraints.
If a choice is still open, use a concrete default and label it as an assumption. Wait on the dependent work only when a missing answer would cause substantial rework and no reasonable default is available. Continue independent work. Respect explicit requests for consultation or approval at stage boundaries.
Offer optional concept generation
Reference retrieval is part of ordinary preparation for recognizable subjects; it does not require a concept-generation offer. Follow the shared guidance to find complementary angles and separate observed structure from intended style. Use existing user references first and record what remains uncertain.
When requested, or when a concept would resolve a consequential visual ambiguity, offer an optional image-generation pass. Do not routinely interrupt an actionable modeling brief with a concept offer. A concept is not a prerequisite for geometry:
I can generate a concept/mockup reference before modeling; it will guide silhouette, materials, palette, and camera—not become the final 3D asset.
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.
- 3d ago Changed · +5 lines 973a765c9a7b
- 4d ago Changed · +8 lines dc4e4b7694bb
- 12d ago First seen · 46 lines · 61 tokens per session scan A 70adc511b133
blender-art-direction-intake is a skill published in the GitHub repository ifBars/blender-agent-studio (18 stars, last pushed 4d ago), licensed MIT. It adds 61 tokens to every session and 574 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.
blender-mesh-ops
Blender authoring skill for verified cross-DCC modeling verbs, polygon mesh inspection, cleanup, topology mutation, UV generation, material assignment, hierarchy, and modifier workflows. Use this before falling back to blender-scripting whenever a workflow models or edits mesh topology.
blender-physics
Blender rigid body, soft body, cloth, collision, force fields, particle systems, constraints, and simulation cache tools.
blender-geometry-nodes
Blender Geometry Nodes groups, modifiers, exposed inputs, and revision-guarded interface socket editing.
blender-render
Blender rendering — render scenes, run observable background animation jobs, capture viewport images, and configure output.