gsplat-optimizer

gsplat-optimizer is a skill for Claude Code from ckorhonen/claude-skills. It costs 64 tokens per session (2,991 once invoked), scanned A, original, MIT.

A guide to making 3D Gaussian Splatting scenes run in real time on Apple devices. Gaussian Splatting represents a 3D scene as many small, soft points instead of a traditional 3D model.

In plain words
What is it for?
Use it with .ply or .splat files to plan point removal, level of detail, compression, and Metal rendering checks for iOS, macOS, and visionOS.
Why use it?
Large scenes can use too much GPU power, storage, or bandwidth, especially on phones and headsets. This helps identify ways to reduce that cost while preserving the scene’s usefulness.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the claude-skills plugin — 62 skills, 4 commands, 7 agents shipped together

Good fit Use it with .ply or .splat files to plan point removal, level of detail, compression, and Metal rendering checks for iOS, macOS, and visionOS.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ckorhonen/claude-skills/gsplat-optimizer
Install

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.

Any agent
npx skills add ckorhonen/claude-skills --skill gsplat-optimizer
Clone the repo
git clone --depth 1 https://github.com/ckorhonen/claude-skills

Made for: Claude Code.

Or install claude-skills, the plugin that ships this one along with the rest of its 62 skills, 4 commands, 7 agents.

Wrote 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.

agentmods badge for gsplat-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/ckorhonen/claude-skills/gsplat-optimizer/github.svg)](https://agentmods.dev/skills/ckorhonen/claude-skills/gsplat-optimizer)
Your own site
<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/gsplat-optimizer"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/gsplat-optimizer/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.

agentmods 80×15 button for gsplat-optimizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/gsplat-optimizer"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/gsplat-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,991 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.02991
Opus 5 $0.00032 $0.01496
Sonnet 5 $0.00013 $0.00598
Haiku 4.5 $0.00006 $0.00299

Measured 11d ago against content hash 858067d11325, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

gsplat-optimizer 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/analyze_splat.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/gsplat-optimizer/SKILL.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gaussian Splat Optimizer

Optimize 3D Gaussian Splatting scenes for real-time rendering on Apple platforms (iOS, macOS, visionOS) using Metal.

When to Use

  • Optimizing .ply or .splat files for mobile/Apple GPU targets
  • Reducing gaussian count for performance (pruning strategies)
  • Implementing Level-of-Detail (LOD) for large scenes
  • Compressing splat data for bandwidth/storage constraints
  • Profiling and optimizing Metal rendering performance
  • Targeting specific FPS goals on Apple hardware

Quick Start

Input: Provide a .ply/.splat file path, target device class, and FPS target.

# Analyze a splat file
python ~/.claude/skills/gsplat-optimizer/scripts/analyze_splat.py scene.ply --device iphone --fps 60

Output: The skill provides:

  1. Point/gaussian pruning plan (opacity, size, error thresholds)
  2. LOD scheme suggestion (distance bins, gaussian subsets)
  3. Compression recommendation (if bandwidth/storage bound)
  4. Metal profiling checklist with shader/compute tips

Optimization Workflow

Step 1: Analyze the Scene

First, understand your scene characteristics:

  • Gaussian count: Total number of splats
  • Opacity distribution: Histogram of opacity values
  • Size distribution: Gaussian scale statistics
  • Memory footprint: Estimated GPU memory usage

Step 2: Determine Target Device

Device Class GPU Budget Max Gaussians (60fps) Storage Mode
iPhone (A15+) 4-6GB unified ~2-4M Shared
iPad Pro (M1+) 8-16GB unified ~6-8M Shared
Mac (M1-M3) 8-24GB unified ~8-12M Shared/Managed
Vision Pro 16GB unified ~4-6M (stereo) Shared
Mac (discrete GPU) 8-24GB VRAM ~10-15M Private

Step 3: Apply Pruning

If gaussian count exceeds device budget:

  1. Opacity threshold: Remove gaussians with opacity < 0.01-0.05
  2. Size culling: Remove sub-pixel gaussians (< 1px at target resolution)
  3. Importance pruning: Use LODGE algorithm for error-proxy selection
  4. Foveated rendering: For Vision Pro, reduce density in peripheral view

Read the full file on GitHub · 299 lines

Files

What ships with it

5 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.

Changes

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.

  1. 11d ago First seen · 299 lines · 64 tokens per session scan A 858067d11325

Subscribe to this mod's changes

gsplat-optimizer is a skill published in the GitHub repository ckorhonen/claude-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 2,991 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

sceneview-ios

Build 3D and AR apps on Apple platforms (iOS, macOS, visionOS) with SceneViewSwift — the SwiftUI wrapper around RealityKit. Use whenever the user asks for "3D in SwiftUI", "AR with ARKit in SwiftUI", a model viewer for iOS, or any Apple-platform 3D/AR app where the dependency is the SceneViewSwift Swift Package from…

sceneview/sceneview · 148 tokens

sceneview

Build 3D and AR apps with the SceneView SDK in Jetpack Compose, SwiftUI (iOS/macOS/visionOS via SceneViewSwift), Web (Filament.js), Flutter and React Native. Use whenever the user asks for "3D in Compose", "AR with ARCore in Compose", a model viewer, or any cross-platform 3D/AR app where the dependency is…

sceneview/sceneview · 156 tokens

build-mobile-threejs-games

Build, tune, or test a Three.js game for mobile web. Use for touch movement, action controls, target selection, touch inventory, safe areas, portrait/landscape layouts, responsive HUD, battery/performance budgets, and real mobile browser QA.

MengTo/Skills · 57 tokens

building-mobile-game

Build mobile games and game-like interactive experiences in React Native and Expo. Use when Codex is creating or refactoring arcade, puzzle, casual, action, physics-based, or animation-heavy gameplay, including Expo game setup with the with-reanimated template, sprite-sheet generation and extraction, frame-based…

Intelligent-Internet/ii-agent · 91 tokens

mobile-development

Use when targeting Android/iOS — export and signing, permissions, plugins, in-app purchases, ads, app lifecycle, device features, and mobile performance.

jame581/GodotPrompter · 33 tokens

media-higgsfield-assets

A Higgsfield workflow for creating or processing media beyond ordinary image and video generation. It covers 3D GLB models, rigging and animation, audio, video analysis, upscaling, reframing, outpainting, and background removal.

modu-ai/moai-cowork · 293 tokens