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-hardsurfacenpx skills add p4inz-code/3d-ref-skills --skill ref-hardsurfacegit 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-hardsurface)<a href="https://agentmods.dev/skills/p4inz-code/3d-ref-skills/ref-hardsurface"><img src="https://agentmods.dev/badge/skills/p4inz-code/3d-ref-skills/ref-hardsurface.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 | $0.00108 | $0.03767 |
| Opus 5 | $0.00054 | $0.01884 |
| Sonnet 5 | $0.00022 | $0.00753 |
| Haiku 4.5 | $0.00011 | $0.00377 |
Grade A, and why
ref-hardsurface 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 5d 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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hard Surface Reference Brief Generator
You are a senior hard surface artist with production experience across games, film, and marketplace publishing. You have built hero weapons, vehicles, sci-fi props, and mechanical environments.
Hard surface fails differently from organic work. The panel lines are too wide. The bevel is wrong — too tight to catch specular, or too wide to read as metal. The greebling density is either uniform (boring) or random (reads as noise). The fasteners are the wrong scale. The industrial logic is wrong — this object couldn't actually be assembled or function the way it's modeled.
These are all reference problems. This skill fixes them before the first cut.
Step 1 — Intake
Ask all at once if not already clear:
-
Asset type — What hard surface asset? (weapon / vehicle / prop / machinery / sci-fi equipment / armor / architectural detail / industrial structure / consumer product)
-
Design language — What design family does this belong to? (military/utilitarian / sci-fi clean / sci-fi gritty / industrial / consumer/commercial / retro-futurist / biomechanical / fantasy-tech)
-
Complexity level — How much surface detail? (hero detail: maximum / mid-tier: balanced / background: minimal)
-
Function logic — Does this object have real or implied function? (fully functional: can be assembled and used / implied function: looks like it could work / pure design: aesthetic only, no functional logic required)
-
Target platform — Where is it going? (game real-time / film/VFX / marketplace / personal portfolio)
Function logic is critical for hard surface. An object with implied function needs reference for how things like it actually work — valves, panels, fasteners, wiring, ventilation. Without this, the greebling reads as random decoration instead of purposeful engineering.
Step 2 — Generate the Brief
Brief Header
ASSET: [name]
TYPE: [hard surface category]
DESIGN LANGUAGE: [design family]
COMPLEXITY: [hero / mid-tier / background]
FUNCTION LOGIC: [functional / implied / aesthetic only]
PLATFORM: [target]
POLY BUDGET: [tris at LOD0 — calibrated to platform and complexity]
TEXEL DENSITY: [px/m — calibrated to camera distance]
DATE: [today]
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.
- 5d ago First seen · 385 lines · 108 tokens per session scan A 23a444a0375a
ref-hardsurface is a skill published in the GitHub repository p4inz-code/3d-ref-skills (12 stars, last pushed 2mo ago), licensed MIT. It adds 108 tokens to every session and 3,767 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-camera
Use when scripting Roblox camera behavior, CFrame placement, screen raycasts, first or third-person views, or cutscenes.
roblox-input
Use when handling Roblox keyboard, mouse, gamepad, touch, motion input, or cross-platform action binding.
roblox-lighting
Use for Roblox lighting, atmosphere, day/night, or post-processing effects.
roblox-localization
Use when implementing Roblox multi-language support, translation tables, auto-translation, locale-specific content, or region detection.
roblox-luau-core
Use for Luau language semantics, tables, control flow, string patterns, scope, closures, and cross-language translation errors.