Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/OpenDCAI/GameFactory-3Anpx agentmods add skills/opendcai/gamefactory-3a/3d_objectWrote 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/opendcai/gamefactory-3a/3d_object)<a href="https://agentmods.dev/skills/opendcai/gamefactory-3a/3d_object"><img src="https://agentmods.dev/badge/skills/opendcai/gamefactory-3a/3d_object/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/opendcai/gamefactory-3a/3d_object"><img src="https://agentmods.dev/badge/skills/opendcai/gamefactory-3a/3d_object.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 | $0.00000 | $0.06257 |
| Opus 5.5 | $0.00000 | $0.02503 |
| Sonnet 5.5 | $0.00000 | $0.01251 |
| Haiku 4.5 | $0.00000 | $0.00626 |
Grade A, and why
3d_object 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 1mo 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 — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated Asset Review
Judge whether a generated mesh is fit to ship in a browser game, from the same rendered sheet the orientation review uses.
A generation model optimises for resemblance to one image. A game needs
several other things that no image-to-3D metric measures, and every one
of them is visible in five orthographic views. Run this immediately after
Gen3DObjectOperator.run_art_plan, on the sheet at
result["preview_sheet"].
Choose The Route First
Three routes produce a 3D asset. The cheapest applicable one wins:
| Route | Use when | Cost |
|---|---|---|
Spec (funcs/code_asset.py) |
the object is exactly describable — a crate, sign, wheel, rifle, railing | seconds, no GPU, no API key |
Asset pack (funcs/asset_pack.py) |
a CC0 model of it already exists | seconds, one download |
| Generate (Tripo / Meshy / TRELLIS.2) | the surface is the point — a face, creature, tree, cloth | paid or GPU-bound, minutes |
suits_code_asset(subject) returns code, generate or ambiguous. It
declines rather than guesses: a procedurally "described" face wastes a
correction loop discovering what one call could have said.
It decides by how a subject assembles, not by whether it sounds hard-surfaced — a rifle and a suit of armour are both hard-surfaced and route differently:
| Topology | Means | Route |
|---|---|---|
composed |
parts sit beside each other, joined by adjacency — a rifle, a car | code |
nested |
layers sit on a host that must exist and be measured first — armour on a body | generate the host, state the layers (hybrid) |
surface |
one inseparable surface, no assembly — a face, a tree | generate |
The result also carries topology, claimed_by and builder, which is what
a hybrid build acts on: a nested claim names the module that fits the layers
onto the generated host.
Prefer a spec for rigid assemblies — a race car, a pistol, anything whose
parts hold a fixed structure. Generate a figure whole: composing one burns
iterations for a worse result — the composed knight took 8 human-agent rounds
over 12 hours to come out roughly right — so send a character straight to an
image-to-3D model instead. See
<REPO_PATH>/agent_skills/asset_qa/3d_object/composition_examples.md.
What ships with it
2 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.
- 1mo ago First seen · 510 lines · 0 tokens per session scan A bf5138e790c4
3d_object is a skill published in the GitHub repository OpenDCAI/GameFactory-3A (928 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 6,257 tokens. 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
scenario-blender-retopology
Use when turning a dense sculpt, scan or AI-generated mesh into clean topology in Blender, for animation, subdivision or a game low poly with a triangle budget. Also when choosing between QuadriFlow or voxel remesh and manual retopo, placing loops around eyes, mouth and joints, deciding pole placement, setting up a…
scenario-maya-retopology-uv
Use when turning a dense sculpt, scan, ZBrush export or AI-generated mesh into animation-ready or game-ready topology in Maya without a mouse ("clean up this AI mesh", "retopo this character", Quad Draw, Retopologize), testing it deforms before rigging (bad elbow or wrist bend, lids popping through the eyes), or…
scenario-zbrush-expert
Use when an agent drives Maxon ZBrush 2026 for any task (sculpt in ZBrush, DynaMesh, ZRemesher, UVs, export, polypaint, posing, 3D print, clean up an AI mesh in ZBrush), when writing ZBrush Python (zbrush.commands) or ZScript, when the ZBrush bridge is not answering, a palette path or set() does nothing, a scripted…
scenario-godot-expert
Use when an agent drives Godot 4.7 on macOS or Windows for any task: headless --script jobs, --import, --check-only, command-line exports, GUT tests, windowed screenshots, the headless editor (-e) or an MCP server into a running editor; when a run hangs or fails silently, a capture is black, Godot 3 code breaks in…
scenario-godot-multiplayer
Use when a Godot 4 game goes online or co-op: host and join with ENet, WebSocket for a web build, RPCs (@rpc, rpcid, anypeer), MultiplayerSpawner and MultiplayerSynchronizer, player authority, lobbies and login, a dedicated or headless server export, lag, rubber-banding, prediction or netfox, cheating, bandwidth…
scenario-blender-hair
Use when grooming hair or fur in Blender with hair curves, such as a character hairstyle, animal fur, procedural fur in geometry nodes, or hair cards and mesh hair for games. Also covers the Essentials hair node assets (Interpolate, Clump, Curl, Frizz, Noise, Trim), density masks, bald spots, parting lines, strand…