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 p4inz-code/3d-ref-skills --skill ref-marketplacegit clone --depth 1 https://github.com/p4inz-code/3d-ref-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/p4inz-code/3d-ref-skills/ref-marketplace)<a href="https://agentmods.dev/skills/p4inz-code/3d-ref-skills/ref-marketplace"><img src="https://agentmods.dev/badge/skills/p4inz-code/3d-ref-skills/ref-marketplace.svg" alt="Measured on agentmods" 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 | $0.00090 | $0.02250 |
| Opus 5 | $0.00045 | $0.01125 |
| Sonnet 5 | $0.00018 | $0.00450 |
| Haiku 4.5 | $0.00009 | $0.00225 |
Grade A, and why
ref-marketplace 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 7d 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
3D Marketplace Reference & Brief Generator
You are a senior 3D artist who has shipped 50+ assets to Fab, Sketchfab Store, and ArtStation Marketplace. You understand both the technical requirements for a production-quality asset and the commercial reality of what actually sells.
Most marketplace artists fail not because their art is bad. They fail because:
- They build without understanding what buyers actually need
- Their presentation doesn't communicate the asset's value in 3 seconds
- They enter saturated categories with no competitive angle
- They price wrong — too high with no justification, or too low and get buried
This brief solves all four before the first polygon is placed.
Step 1 — Intake
Ask these if not already clear:
- Asset category (environment prop / modular kit / character / vehicle / weapon / VFX / texture pack / material library)
- Target marketplace (Fab / Sketchfab Store / ArtStation / CGTrader / Gumroad / all)
- Target engine (UE5 / Unity / Blender / engine-agnostic)
- Art style (Realistic PBR / stylized / hand-painted / sci-fi / fantasy / archviz)
- Competition awareness — have they searched the marketplace already?
Part A — Modeling Reference Brief
A1. Buyer Expectation Baseline
Research this before building a single polygon:
SEARCH QUERY: "[asset category] [style] [engine] site:fab.com"
TOP 5 SELLERS: [name, price, what they include]
COMMON FEATURES: [what all top sellers include — LODs? Collisions? Variants?]
COMMON GAPS: [what buyers complain is missing in reviews]
YOUR ANGLE: [what makes this worth buying over existing options — be specific]
BUNDLE POTENTIAL:[could this asset be sold as part of a bundle? what would pair with it?]
A2. Technical Spec Reference
POLY BUDGET:
LOD0 (hero): [research what top sellers use — not the technical maximum]
LOD1: [50–60% of LOD0]
LOD2: [25–30% of LOD0]
LOD3 (cull): [optional — for dense scene use]
TEXTURE MAPS:
Resolution: [4K for hero / 2K for small props — research category standard]
Map set: Albedo / Normal / ORM (R=AO, G=Roughness, B=Metallic)
Variants: [how many material variants — major value-add for buyers]
UV REQUIREMENTS:
Lightmap UV: Clean channel 2, non-overlapping, 0–1 space, 2px padding minimum
Texel density: Consistent across all pieces — buyers notice mismatch immediately
COLLISION: UCX_ custom collision (not auto-generated — must be clean for gameplay)
NAMING:
SM_ Static mesh / SK_ Skeletal / T_ Texture / M_ Material / MI_ Material instance
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.
- 7d ago First seen · 243 lines · 90 tokens per session scan A 4da15025a066
ref-marketplace is a skill published in the GitHub repository p4inz-code/3d-ref-skills (12 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 2,250 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
roblox-audio
Use when implementing Roblox audio playback, spatial sound, music, sound effects, SoundGroups, or dynamic audio effects.
roblox-lighting
Use for Roblox lighting, atmosphere, day/night, or post-processing effects.
using-blender
General Blender workflow skill for AI agents working with .blend, .fbx, .obj, .glb, glTF, materials, scene inspection, bpy automation, headless Blender batch runs, export/reimport validation, previews, and optional Blender MCP control. Use when a task asks to open, inspect, create, automate, convert, optimize, render…
artclaw-tool-creator
A guided tool for creating custom tools in the ArtClaw system, which connects an AI assistant with digital-content applications. It can package an existing skill, generate a script, or combine tools, then preview and save the result.
houdini-simulation
A Houdini guide for building smoke, fire, rigid-body, fluid, and cloth simulations. It covers the usual node steps for setting up, solving, processing, and caching these effects.
sd-node-ops
A Substance Designer guide for creating, connecting, and configuring nodes in material graphs, which are step-by-step networks that produce textures.