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 product-polishgit 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/product-polish)<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/product-polish"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/product-polish/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/product-polish"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/product-polish.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 | $0.00069 | $0.00699 |
| Opus 5.5 | $0.00028 | $0.00280 |
| Sonnet 5.5 | $0.00014 | $0.00140 |
| Haiku 4.5 | $0.00007 | $0.00070 |
Grade A, and why
blender-product-polish 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender Product Polish
Takes a raw 3D model file (e.g. exported from generative 3D tools) and transforms it into a polished, product-shot-ready scene in Blender via the Blender MCP addon.
Prerequisites
- Blender (5.x+) running with the Blender MCP addon active on port 9876
- A
.glbor.gltffile to import
How to Run
node subskills/product-polish/scripts/blender-product-polish.js --file "/path/to/model.glb"
Options
| Option | Description | Default |
|---|---|---|
--file |
Path to the GLB/GLTF file to import | required |
--port |
Blender MCP port | 9876 |
--preset |
Lighting preset: studio, dramatic, soft |
studio |
--roughness |
Surface roughness (0 = mirror, 1 = matte) | 0.02 |
--coat |
Clearcoat weight (0-1) | 1.0 |
--transmission |
Glass transmission (0-1) | 0.05 |
--no-clean |
Keep existing scene objects | false |
What It Does
- Clears the scene (removes default cube, lights, camera)
- Imports the GLB/GLTF model
- Strips noisy normal/roughness maps from raw exports (these cause dotty reflections)
- Applies a glass-like material — ultra-low roughness, full clearcoat, high IOR
- Adds 4-point studio lighting — key, fill, rim, and bounce lights
- Switches to EEVEE with ray tracing for smooth real-time reflections (no pixelation during camera movement)
- Frames the viewport on the imported model
Lighting Presets
- studio (default): Balanced 4-point setup. Key (350W), Fill (250W), Rim (250W), Bounce (100W). Clean product photography look.
- dramatic: Strong key + rim, minimal fill. High contrast, moody.
- soft: Even lighting from all sides. Minimal shadows, airy feel.
Notes
- Raw model exports often include noisy normal maps and roughness textures that look pixelated/dotty under strong lighting. This skill disconnects those and uses flat material values instead.
- The skill uses EEVEE (not Cycles) to avoid progressive sampling noise during viewport navigation.
- After running, you can orbit freely in Blender without pixelation.
What ships with it
1 file 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.
- 2d ago First seen · 61 lines · 69 tokens per session scan A aaf9a495f3da
blender-product-polish is a skill published in the GitHub repository cafe3310/public-agent-skills (256 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 699 once invoked, about $0.0003 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-product-polish compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| blender-product-polishcafe3310/public-agent-skills | Skill | 256 | yesterday | Apache-2.0 | A | 69 | Claude Code, Codex |
| google-fonts-curatorflc1125/skills | Skill | 39 | yesterday | MIT | A | 61 | Claude Code, Codex |
| preview-svgveelenga/preview-skills | Skill | 9 | 18d ago | MIT | A | 107 | Claude Code |
| android-ui-engineeringGuillemRoca/agent-skills-android | Skill | 5 | 1mo ago | MIT | A | 52 | Claude Code |
| android-accessibilityGuillemRoca/agent-skills-android | Skill | 5 | 1mo ago | MIT | A | 35 | Claude Code |
| design-taste-frontendfirstsun-dev/skills | Skill | 5 | 4d ago | none | A | 61 | Claude Code, Codex |
| imagegen-frontend-mobilefirstsun-dev/skills | Skill | 5 | 4d ago | none | A | 126 | Claude Code, Codex |