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 RemakeBench/skills --skill 3d-asset-qualitygit clone --depth 1 https://github.com/RemakeBench/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/remakebench/skills/3d-asset-quality)<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.
<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>- 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 | $0.00107 | $0.03803 |
| Opus 5 | $0.00053 | $0.01902 |
| Sonnet 5 | $0.00021 | $0.00761 |
| Haiku 4.5 | $0.00011 | $0.00380 |
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.
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 — 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
- List the functional parts — before any geometry exists.
- Build from that list, working from the image target if there is one, iterating on cheap viewport screenshots.
- Stage the acceptance test locally with
scripts/acceptance_setup.py(clay override, eye-height cameras). It renders nothing. - Render every frame for every asset as one batch, using a remote backend when local rendering is constrained.
- Look at the returned frames, answer the three questions per asset, write the manifest.
- Anything that failed goes back to 1 and gets rebuilt.
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.
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 · 263 lines · 107 tokens per session scan A 27a763535923
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.
Other skills, from other repositories
blender-interchange
Blender interchange skill for typed FBX/OBJ/USD imports, GLTF/USD/Alembic exports, and repeatable batch exports. Use for moving assets between DCC, game, and pipeline tools before falling back to scripting.
blender-physics
Blender rigid body, soft body, cloth, collision, force fields, particle systems, constraints, and simulation cache tools.
blender-asset-source
Blender asset source discovery — search filesystem and asset libraries for importable 3D assets.
blender-light-rig
Blender reusable light rigs, HDRI/world setup and rotation animation, light grouping, and render-view controls.
blender-rigging
Blender authoring skill for armatures, bones, constraints, armature binding, shape keys, drivers, and simple retargeting. Use this for character setup before falling back to blender-scripting.
blender-camera
Blender camera management — create, configure and set active cameras.