3d-asset-quality

3d-asset-quality is a skill for Claude Code from RemakeBench/skills. It costs 107 tokens per session (3,803 once invoked), scanned A, original, MIT.

A quality-checking guide for 3D models and game assets. It requires the model to show how the real object is built and used, including thickness, joins, supports and working parts.

In plain words
What is it for?
Use it when creating, importing, cleaning, reviewing or approving meshes such as props, buildings, terrain, environments, levels and dioramas in Blender or game engines.
Why use it?
It helps prevent assets that are only textured shapes or outlines. Close-up renders with textures disabled provide visible proof that each asset is understandable from its geometry alone.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; positional $N argument.

Part of the remakebench-skills plugin — 8 skills shipped together

Good fit Use it when creating, importing, cleaning, reviewing or approving meshes such as props, buildings, terrain, environments, levels and dioramas in Blender or game engines.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/remakebench/skills/3d-asset-quality
Install

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.

Any agent
npx skills add RemakeBench/skills --skill 3d-asset-quality
Clone the repo
git clone --depth 1 https://github.com/RemakeBench/skills

Made for: Claude Code.

Or install remakebench-skills, the plugin that ships this one along with the rest of its 8 skills.

Wrote 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.

agentmods badge for 3d-asset-quality

README.md
[![agentmods](https://agentmods.dev/badge/skills/remakebench/skills/3d-asset-quality/github.svg)](https://agentmods.dev/skills/remakebench/skills/3d-asset-quality)
Your own site
<a href="https://agentmods.dev/skills/remakebench/skills/3d-asset-quality"><img src="https://agentmods.dev/badge/skills/remakebench/skills/3d-asset-quality/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.

agentmods 80×15 button for 3d-asset-quality

Your own site · 80×15
<a href="https://agentmods.dev/skills/remakebench/skills/3d-asset-quality"><img src="https://agentmods.dev/badge/skills/remakebench/skills/3d-asset-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,803 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00107 $0.03803
Opus 5 $0.00053 $0.01902
Sonnet 5 $0.00021 $0.00761
Haiku 4.5 $0.00011 $0.00380

Measured 9d ago against content hash 27a763535923, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

3d-asset-quality 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/acceptance_setup.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/3d-asset-quality/SKILL.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model the thing, not its outline

The rule

Model what the object is, not what its outline looks like: every asset must show the parts that would exist because it functions in the real world — how it is joined, supported, opened, carried, loaded, worn or maintained — because those parts are what separate an asset from a primitive with a texture. Apply this equally to every asset with no hero/background tiering, bevel every edge that catches light, and give every surface real thickness. An asset is only finished when it passes this test: rendered close-up at viewer height, a person unfamiliar with the project can identify what it is, how it is built, and how it is used — from geometry alone, with textures disabled. Anything that still reads as a primitive with a texture applied has failed and must be rebuilt, not adjusted. The deliverable is a close-up render of every asset plus a manifest, not the asset files — files existing on disk is not evidence of quality.

Every clause is load-bearing. The four that agents most often quietly drop: no hero/background tiering, rebuilt not adjusted, geometry alone with textures disabled, and files on disk are not evidence.

Why the rule exists

A reference-built .blend with shopfronts recessed into their reveals, individually modelled roof-tile rolls, deep eaves, and visible rafters reads as a place rather than a collection of boxes.

A different project generated its village from ~14,500 lines of Python, then spent ten hours on shader work, and still reads as boxes. Shading is a multiplier on geometry; a multiplier applied to nothing is nothing. That asymmetry is the entire reason the acceptance test turns textures off — it measures the half of the work that can't be bought back later.

The loop

  1. List the functional parts — before any geometry exists.
  2. Build from that list, working from the image target if there is one, iterating on cheap viewport screenshots.
  3. Stage the acceptance test locally with scripts/acceptance_setup.py (clay override, eye-height cameras). It renders nothing.
  4. Render every frame for every asset as one batch, using a remote backend when local rendering is constrained.
  5. Look at the returned frames, answer the three questions per asset, write the manifest.
  6. Anything that failed goes back to 1 and gets rebuilt.

Read the full file on GitHub · 263 lines

Files

What ships with it

4 files 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.

Changes

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.

  1. 9d ago First seen · 263 lines · 107 tokens per session scan A 27a763535923

Subscribe to this mod's changes

3d-asset-quality is a skill published in the GitHub repository RemakeBench/skills (6 stars, last pushed 8d ago), licensed MIT. It adds 107 tokens to every session and 3,803 once invoked, about $0.0005 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 2026-08-31.