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 BlackBeltTechnology/pi-agent-dashboard --skill blendergit clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboardWrote 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/blackbelttechnology/pi-agent-dashboard/blender)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/blender"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/blender/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/blackbelttechnology/pi-agent-dashboard/blender"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/blender.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 | $0.00109 | $0.01747 |
| Opus 5.5 | $0.00044 | $0.00699 |
| Sonnet 5.5 | $0.00022 | $0.00349 |
| Haiku 4.5 | $0.00011 | $0.00175 |
Grade A, and why
blender 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Headless Blender — 3D modelling and GLB export
pi-blender runs the published Blender WebAssembly build inside Node: no native Blender, no GUI, no GPU.
The runtime (~175 MB) is downloaded once, verified against a pinned hash, and cached. It is a stdio MCP
server (blender-wasm) with one persistent Blender session per server.
When to use it
- Build or edit 3D geometry with Python (
bpy): primitives, modifiers, materials, hierarchies. - Convert or inspect 3D files:
.glb.gltf.fbx.obj.stl.ply.svg.blend. - Produce a
.glbfor a web viewer, game engine or AR.
Not for rendering images (no rendering here) or for anything needing a GUI.
Setup (once per machine, once per project)
pi-blender ensure # download + verify the runtime NOW; otherwise the first tool call is slow
pi-blender status # what is cached, JSPI support (never downloads)
pi-blender mcp --register # in the project root: writes .pi/mcp.json -> "blender-wasm"
pi-blender mcp --register --root assets # confine file access to ./assets instead of the project
Registration is opt-in and project-local; pi loads project MCP servers only after the project is trusted,
and only when started in the project root. ensure needs Node 24 or newer (WebAssembly JSPI); on
older Node it exits 69 saying so — do not retry, tell the user to use Node 24+.
Tools
| Tool | Use |
|---|---|
blender_scene |
List objects (name, type, parent, transform, dimensions, materials, mesh counts). limit default 200. Start here to see what exists. |
blender_python |
Run bpy Python. inputs stages root-relative files at /in/<same path>; anything written under /out/ is saved to outputDir (default blender-out). print() output is returned. |
blender_import |
Import one file by extension. A .blend replaces the whole scene. |
blender_export |
Export the scene by extension of the target path. selectedOnly exports the selection (not for .blend). |
blender_reset |
mode: "factory" (default cube/light/camera scene) or "empty". |
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 · 108 lines · 109 tokens per session scan A fb34085228a9
blender is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (331 stars, last pushed today), licensed MIT. It adds 109 tokens to every session and 1,747 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-25.
Other skills, from other repositories
goga-cookbook
Principles for applying DSL specification in cell and CODEMANIFEST design.
goga-review-plan
Verify execution plan completeness and correctness.
goga-define-challenge
Challenge the complete product definition before the PRD is generated.
goga-define-project
Understand the current project before defining a product change that must fit into an existing product.
goga-define-requirements
Define the product requirements that describe what the product must do to deliver the established user experience and achieve the agreed product goals.
goga-prototype
Pipeline orchestrator for prototyping the cells architecture.