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 cafe3310/public-agent-skills --skill blender-toolkitgit clone --depth 1 https://github.com/cafe3310/public-agent-skillsWrote 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/cafe3310/public-agent-skills/blender-toolkit)<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/blender-toolkit"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/blender-toolkit/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/cafe3310/public-agent-skills/blender-toolkit"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/blender-toolkit.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 | $0.00031 | $0.04488 |
| Opus 5.5 | $0.00012 | $0.01795 |
| Sonnet 5.5 | $0.00006 | $0.00898 |
| Haiku 4.5 | $0.00003 | $0.00449 |
Grade A, and why
blender-toolkit 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 2d 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 — 601 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ Installation Check (READ THIS FIRST)
IMPORTANT: Before using this skill, check Blender addon installation status.
Config location: Check the shared config file for your installation status:
~/.claude/plugins/marketplaces/dev-gom-plugins/blender-config.json
Always run scripts with --help first to see usage. DO NOT read the source until you try running the script first and find that a customized solution is abslutely necessary. These scripts can be very large and thus pollute your context window. They exist to be called directly as black-box scripts rather than ingested into your context window.
Required actions based on config:
1. If Blender Not Detected (blenderExecutable: null)
Blender was not found during initialization. Please:
- Install Blender 4.0+ from https://www.blender.org
- Restart Claude Code session to trigger auto-detection
- Check logs:
.blender-toolkit/init-log.txt
2. If Multiple Versions Detected (detectedBlenderVersions array)
The system detected multiple Blender installations. If you want to use a different version:
- Open config file (path shown above)
- Edit
blenderExecutablefield to your preferred version path - Restart Claude Code session
Example:
{
"detectedBlenderVersions": [
{"version": "4.2.0", "path": "C:\\Program Files\\Blender Foundation\\Blender 4.2\\blender.exe"},
{"version": "4.1.0", "path": "C:\\Program Files\\Blender Foundation\\Blender 4.1\\blender.exe"}
],
"blenderExecutable": "C:\\Program Files\\Blender Foundation\\Blender 4.2\\blender.exe"
}
3. If Addon Not Installed (addonInstalled: false)
The addon needs to be installed manually. Follow these steps:
Manual Installation Steps:
Method 1: Install from ZIP (Recommended)
# 1. Open Blender 4.0+
# 2. Edit > Preferences > Add-ons > Install
# 3. Select: .blender-toolkit/blender-toolkit-addon-v*.zip
# 4. Enable "Blender Toolkit WebSocket Server"
Method 2: Install from Source
# 1. Open Blender 4.0+
# 2. Edit > Preferences > Add-ons > Install
# 3. Select: plugins/blender-toolkit/skills/addon/__init__.py
# 4. Enable "Blender Toolkit WebSocket Server"
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.
- 2d ago First seen · 601 lines · 31 tokens per session scan A a3a0b88ff4ed
blender-toolkit is a skill published in the GitHub repository cafe3310/public-agent-skills (256 stars, last pushed yesterday), licensed Apache-2.0. It adds 31 tokens to every session and 4,488 once invoked, about $0.0001 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 2026-11-05.
blender-toolkit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| blender-toolkitcafe3310/public-agent-skills | Skill | 256 | yesterday | Apache-2.0 | A | 31 | Claude Code |
| expertsflc1125/skills | Skill | 39 | yesterday | MIT | A | 62 | Claude Code, Codex |
| asyncflc1125/skills | Skill | 39 | yesterday | MIT | A | 52 | Claude Code, Codex |
| github-release-pr-writerflc1125/skills | Skill | 39 | yesterday | MIT | A | 80 | Claude Code, Codex |
| yuqueflc1125/skills | Skill | 39 | yesterday | MIT | A | 72 | Claude Code, Codex |
| getnoteflc1125/skills | Skill | 39 | yesterday | MIT | A | 83 | Claude Code, Codex |
| opentelemetry-go-reviewerflc1125/skills | Skill | 39 | yesterday | MIT | A | 34 | Claude Code, Codex |