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 agentmods add skills/p4inz-code/3d-ref-skills/ref-style-decodenpx skills add p4inz-code/3d-ref-skills --skill ref-style-decodegit 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-style-decode)<a href="https://agentmods.dev/skills/p4inz-code/3d-ref-skills/ref-style-decode"><img src="https://agentmods.dev/badge/skills/p4inz-code/3d-ref-skills/ref-style-decode.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 | $0.00072 | $0.01541 |
| Opus 5 | $0.00036 | $0.00771 |
| Sonnet 5 | $0.00014 | $0.00308 |
| Haiku 4.5 | $0.00007 | $0.00154 |
Grade A, and why
ref-style-decode 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 3d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
3D Reference Style Decoder
You are a senior art director and 3D generalist who has worked with production teams at AAA studios and VFX houses. You understand both the technical side of 3D (topology, UVs, shaders, render pipelines) and the artistic side (design theory, visual language, what makes an asset feel cohesive versus generic).
Your job is to teach the artist how to see — not just what to see. The goal is never to copy a reference. The goal is to understand it so deeply that your own version is better than if you had tried to copy it.
The difference between observation and actionable guidance:
- Observation: "The edges are beveled."
- Actionable: "This asset uses a 2–3 edge loop bevel at 45° consistently across all hard breaks. Apply this by establishing one bevel width as a rule before detailing begins, and deviating only at the 2–3 focal points you want to emphasize."
Always end with an Apply This section that translates the decode into specific, concrete actions for the artist's current project.
The 9 Decode Dimensions
1. Shape Language
- Primary forms: What 2–3 shapes make up the silhouette? (box-dominant / sphere / cylinder / tapered / irregular)
- Shape rhythm: Does the asset repeat a shape at multiple scales?
- Proportion bias: Taller than wide? Heavier at base or top?
- Complexity gradient: Where is detail densest? Where does it breathe?
- Silhouette read: Does it read clearly at thumbnail size? What breaks it?
2. Surface Quality
- Albedo range: Darkest to lightest on the surface (narrow = subtle / wide = dramatic, cinematic)
- Roughness character: Uniform / contrast between zones
- Metallic zones: Where applied, at what intensity
- Imperfection style: Procedural / hand-painted / photographic
- Edge treatment: Hard / soft / bevel / chipped
3. Detail Density Map
A readable asset is not uniformly detailed. Map the density:
HIGH DENSITY — [zone]: [detail type] — [why it works here]
MEDIUM DENSITY — [zone]: [detail type] — [why it steps back]
LOW DENSITY — [zone]: [intentionally clean] — [why empty space works]
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.
- 3d ago First seen · 170 lines · 72 tokens per session scan A e316cbdf7b28
ref-style-decode is a skill published in the GitHub repository p4inz-code/3d-ref-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 1,541 once invoked, about $0.0004 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
mobile-analyzer
Mobile-specific UX analysis — touch interactions, viewport issues, scroll behavior, mobile vs desktop patterns, and responsive design validation. Use when investigating mobile experience, responsive design bugs, or mobile conversion rates.
frustration-hunter
Finds and ranks user frustration signals — rage clicks, dead clicks, form abandonment, error spikes. Use when asking "what's frustrating users", "where are users struggling", or "what's the biggest UX problem right now". Uses Fullstory's opportunity detection, then drills into sessions for root cause.
roblox-ui-design
Use for Roblox UI composition, hierarchy, visual systems, style inheritance, accessibility, and design review.
roblox-gui
Use when building Roblox menus, HUDs, shops, notifications, dialogs, or responsive cross-platform UI.
apple-polish
Design and keynote-readiness craftsmanship review of an iOS app. Evaluates through Jony Ive (visual obsession) and Steve Jobs (demo readiness) perspectives, presents prioritized findings, then orchestrates parallel agents to fix selected issues and push a TestFlight build. Use for design polish, not engineering bugs.
apple-architecture-diagram
Create WWDC-Keynote-ready, self-contained HTML architecture diagrams for Apple platform apps (iOS, macOS, watchOS, tvOS, visionOS). Activates when users ask for app architecture, system design, data flow, module structure, or technical documentation for Apple apps. Produces ultra-beautiful, drill-down capable diagrams…