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/corosolto/client/threejs-aaa-graphics-buildernpx skills add corosolto/client --skill threejs-aaa-graphics-buildergit clone --depth 1 https://github.com/corosolto/clientWrote 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/corosolto/client/threejs-aaa-graphics-builder)<a href="https://agentmods.dev/skills/corosolto/client/threejs-aaa-graphics-builder"><img src="https://agentmods.dev/badge/skills/corosolto/client/threejs-aaa-graphics-builder.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 | $0.00140 | $0.01318 |
| Opus 5 | $0.00070 | $0.00659 |
| Sonnet 5 | $0.00028 | $0.00264 |
| Haiku 4.5 | $0.00014 | $0.00132 |
Grade A, and why
threejs-aaa-graphics-builder 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
17 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.
- agents/openai.yaml 792 B
- assets/scorecard-anchors/scene-1.jpg 30 KB
- assets/scorecard-anchors/scene-2.jpg 61 KB
- assets/scorecard-anchors/scene-3.jpg 66 KB
- references/checklists/aaa-game-quality-gate.md 2.1 KB
- references/checklists/aaa-visual-scorecard.md 1.2 KB
- references/checklists/material-lighting-quality.md 1.1 KB
- references/checklists/performance-safe-visual-detail.md 1020 B
- references/checklists/procedural-model-quality.md 1.2 KB
- references/checklists/technical-art-quality.md 1.6 KB
- references/implementation-blueprint.md 9.2 KB
- references/model-recipes.md 6.8 KB
- references/prompt-templates.md 10 KB
- references/render-recipes.md 4.4 KB
- references/shader-cookbook.md 16 KB
- references/technical-art.md 8.7 KB
- references/visual-scorecard.md 8.1 KB
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 · 61 lines · 140 tokens per session scan A 62a66c3d9cf3
threejs-aaa-graphics-builder is a skill published in the GitHub repository corosolto/client (234 stars, last pushed 5d ago), licensed AGPL-3.0. It adds 140 tokens to every session and 1,318 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
vtj-ui-integration
Integrates Vue UI with Three.js while maintaining strict separation. Use when building HUDs, menus, or handling UI-to-scene communication via events.
vtj-camera-system
Configures third-person camera systems with collision avoidance. Use when adjusting follow behavior, implementing camera modes, or handling cave/obstacle detection.
vtj-input-system
Handles mouse, keyboard, and touch input via the IMouse and InputManager systems. Use when implementing controls, raycasting, or FPS-style PointerLock.
vtj-raycasting-system
Implements ray picking and collision detection. Use when selecting objects, detecting block interactions, or optimizing raycaster performance.
vtj-shader-development
Creates custom GLSL shaders with vite-plugin-glsl. Use when writing vertex/fragment shaders, managing uniforms, or adding ShaderMaterial debug panels.
vtj-anti-patterns
Prevents common mistakes and prohibited practices in vite-threejs projects. Use before writing code to avoid bugs, memory leaks, and maintenance issues.