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 fanfan-de/anybox --skill blender-workflowgit clone --depth 1 https://github.com/fanfan-de/anyboxWrote 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/fanfan-de/anybox/blender-workflow)<a href="https://agentmods.dev/skills/fanfan-de/anybox/blender-workflow"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/blender-workflow/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/fanfan-de/anybox/blender-workflow"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/blender-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.00813 |
| Opus 5 | $0.00024 | $0.00407 |
| Sonnet 5 | $0.00010 | $0.00163 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
blender-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 9d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender MCP Workflow
Use the installed MCP server plugin.blender.official. It talks to the official Blender extension on
localhost:9876 by default.
Preflight
- Confirm Blender 5.1 or newer is open.
- Confirm the official Blender MCP extension is installed, enabled, and running.
- Confirm its port matches the Anybox plugin setting.
- If MCP startup reports that
uvwas not found, stop and direct the user to the plugin installation instructions. - If the MCP server starts but a Blender-connected tool reports connection refused, do not reinstall Python packages; check the Blender extension, host, port, and auto-start state instead.
Default workflow
- Use
get_blendfile_summary_path_info,get_blendfile_summary_datablocks, andget_objects_summaryto understand the open file before proposing changes. - Use
search_api_docs,search_manual_docs, orget_python_api_docsbefore guessing Blender API names. - Prefer a narrowly scoped purpose-built tool over
execute_blender_codewhenever one exists. - Before any mutation, describe the intended objects, data blocks, output paths, and likely side effects.
- After an approved mutation, inspect the affected objects again and report exactly what changed.
- For visual work, request a Blender screenshot only when visual evidence will materially improve the result.
For a *_for_cli tool, use only a blend-file path explicitly supplied or approved by the user. These tools can start
background Blender and may create then remove a synchronized copy beside a dirty open file. Never probe unrelated
directories or infer sensitive blend-file paths.
Arbitrary Python safety
execute_blender_code runs with Blender's full local process privileges. Before using it:
- make the code as small and deterministic as possible;
- do not access unrelated files, environment variables, credentials, or network endpoints;
- do not save the blend file unless the user explicitly requested persistence;
- avoid destructive operators and deletion unless explicitly requested;
- prefer creating a new output file over overwriting an existing one;
- explain any filesystem or network effect before requesting approval.
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.
- 9d ago First seen · 71 lines · 49 tokens per session scan A ff3cfba4f121
blender-workflow is a skill published in the GitHub repository fanfan-de/anybox (57 stars, last pushed 26d ago), licensed MIT. It adds 49 tokens to every session and 813 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.