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 metaspartan/cybara --skill blender-headlessgit clone --depth 1 https://github.com/metaspartan/cybaraWrote 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/metaspartan/cybara/blender-headless)<a href="https://agentmods.dev/skills/metaspartan/cybara/blender-headless"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/blender-headless.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 | $0.00036 | $0.00559 |
| Opus 5 | $0.00018 | $0.00280 |
| Sonnet 5 | $0.00007 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
blender-headless 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender Headless Modeling
Use this when the user wants a 3D model, scene, or render produced locally with Blender and no Blender MCP server is configured.
Locate Blender
- Try
which blender, then platform defaults:/Applications/Blender.app/Contents/MacOS/Blender,/usr/bin/blender,/snap/bin/blender,%ProgramFiles%\Blender Foundation\Blender*\blender.exe. - Confirm with
<blender> --versionand note the major version; the Python API changes between releases.
Build with a script
- Write one
build_<name>.pythat resets the scene (bpy.ops.wm.read_factory_settings(use_empty=True)), builds geometry withbpy.ops.mesh.primitive_*orbmesh, assigns materials, adds a camera and lights, setsscene.render.filepathto an absolute path, and renders withbpy.ops.render.render(write_still=True). - Keep every file write comfortably under the model output limit: build large scripts in parts (a base file, then
editcalls that append helpers) instead of one hugewrite. A tool call cut off by the output limit loses its arguments. - Run
<blender> --background --python build_<name>.pywith a timeout of at least 300 seconds and capture stdout and stderr; Blender prints Python tracebacks there. - Prefer
BLENDER_EEVEE(Blender 4.2+ removed the_NEXTsuffix) orCYCLESwith a low sample count for verification renders; render around 1400x900 PNG. - Save the
.blendwithbpy.ops.wm.save_as_mainfile(filepath=...)so the user can open the result.
Verify visually, then iterate
- Render at least two views (side and three-quarter) to separate PNG files.
- Inspect each render with the
imagetool and compare it with the requested object: proportions, missing parts, floating geometry, exposure, framing. - Fix the script for each discrepancy, re-render, and inspect again. Do not report success from script output alone.
- Do not delete or overwrite renders you already reported to the user; write new versions to new file names.
Report
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 First seen · 34 lines · 36 tokens per session scan A 6c7eef40a95d
blender-headless is a skill published in the GitHub repository metaspartan/cybara (28 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 559 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 2026-09-07.
Other skills, from other repositories
uiux-banner-design
Skill "uiux-banner-design" from KornLabs/truss, covering banner design - multi-format creative banner system, when to activate, prerequisites, workflow and step 1: gather requirements (askuserquestion).
image-authoring
Author images and diagrams as code — SVG, Pillow, Excalidraw, mermaid. Load when asked to draw, illustrate, or make an image, icon, logo, poster, or diagram.
deck-obsidian-claude
A visual design template for presentation slides with a dark GitHub-like background, colored lighting, gradient headings, and code-style formatting.
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, UI mockups, product shots, or transparent-background cutouts. Use when the result should be an image asset rather than repo-native SVG, HTML/CSS, or canvas.
infographic-generator
An image-making workflow that turns a writing topic and outline into HTML pages and PNG screenshots. It includes four visual styles for different kinds of content.
dynamic-archify
Create professional architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as standalone animated HTML files with SVG graphics, flowing animation effects, a built-in dark/light theme toggle, and one-click export to PNG / JPEG / WebP / SVG / GIF / WebM. Accepts plain-language descriptions or pasted…