particles-gpu

particles-gpu is a skill for Claude Code, Codex from Bbeierle12/Skill-MCP-Claude. It costs 48 tokens per session (3,932 once invoked), scanned A, original, MIT.

GPU-based particle rendering patterns for displaying large numbers of small points or objects efficiently with Three.js and React Three Fiber.

In plain words
What is it for?
Use it for snow, rain, stars, and abstract particle effects, with point, instanced-mesh, or custom-shader rendering approaches.
Why use it?
They move repeated particle work to the graphics processor, helping applications handle effects made from many particles.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for snow, rain, stars, and abstract particle effects, with point, instanced-mesh, or custom-shader rendering approaches.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bbeierle12/skill-mcp-claude/particles-gpu
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 Bbeierle12/Skill-MCP-Claude --skill particles-gpu
Clone the repo
git clone --depth 1 https://github.com/Bbeierle12/Skill-MCP-Claude

Made for: Claude Code, Codex.

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 particles-gpu

README.md
[![agentmods](https://agentmods.dev/badge/skills/bbeierle12/skill-mcp-claude/particles-gpu/github.svg)](https://agentmods.dev/skills/bbeierle12/skill-mcp-claude/particles-gpu)
Your own site
<a href="https://agentmods.dev/skills/bbeierle12/skill-mcp-claude/particles-gpu"><img src="https://agentmods.dev/badge/skills/bbeierle12/skill-mcp-claude/particles-gpu/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 particles-gpu

Your own site · 80×15
<a href="https://agentmods.dev/skills/bbeierle12/skill-mcp-claude/particles-gpu"><img src="https://agentmods.dev/badge/skills/bbeierle12/skill-mcp-claude/particles-gpu.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,932 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00048 $0.03932
Opus 5 $0.00024 $0.01966
Sonnet 5 $0.00010 $0.00786
Haiku 4.5 $0.00005 $0.00393

Measured 9d ago against content hash 7c0db2ff1e62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

particles-gpu 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 9d 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.

skills/particles-gpu/SKILL.md · 524 lines

How it starts

The opening of the file, as written. The whole thing — 524 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GPU Particles

Render massive particle counts (10k-1M+) efficiently using GPU instancing and custom shaders.

Quick Start

import { useRef, useMemo } from 'react';
import { useFrame } from '@react-three/fiber';
import * as THREE from 'three';

function Particles({ count = 10000 }) {
  const points = useRef<THREE.Points>(null!);
  
  const positions = useMemo(() => {
    const pos = new Float32Array(count * 3);
    for (let i = 0; i < count; i++) {
      pos[i * 3] = (Math.random() - 0.5) * 10;
      pos[i * 3 + 1] = (Math.random() - 0.5) * 10;
      pos[i * 3 + 2] = (Math.random() - 0.5) * 10;
    }
    return pos;
  }, [count]);
  
  return (
    <points ref={points}>
      <bufferGeometry>
        <bufferAttribute
          attach="attributes-position"
          count={count}
          array={positions}
          itemSize={3}
        />
      </bufferGeometry>
      <pointsMaterial size={0.05} color="#ffffff" />
    </points>
  );
}

Rendering Approaches

Approach Particle Count Complexity Use Case
Points 10k - 500k Low Simple particles, stars
Instanced Mesh 1k - 100k Medium 3D geometry particles
Custom Shader 100k - 10M High Maximum control

Points Geometry

Simplest approach—each particle is a screen-facing point sprite.

Basic Points

function BasicPoints({ count = 5000 }) {
  const positions = useMemo(() => {
    const pos = new Float32Array(count * 3);
    for (let i = 0; i < count; i++) {
      const theta = Math.random() * Math.PI * 2;
      const phi = Math.acos(2 * Math.random() - 1);
      const r = Math.cbrt(Math.random()) * 5;
      
      pos[i * 3] = r * Math.sin(phi) * Math.cos(theta);
      pos[i * 3 + 1] = r * Math.sin(phi) * Math.sin(theta);
      pos[i * 3 + 2] = r * Math.cos(phi);
    }
    return pos;
  }, [count]);
  
  return (
    <points>
      <bufferGeometry>
        <bufferAttribute
          attach="attributes-position"
          count={count}
          array={positions}
          itemSize={3}
        />
      </bufferGeometry>
      <pointsMaterial
        size={0.1}
        sizeAttenuation={true}
        transparent={true}
        opacity={0.8}
        depthWrite={false}
        blending={THREE.AdditiveBlending}
      />
    </points>
  );
}

Read the full file on GitHub · 524 lines

Files

What ships with it

2 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. 9d ago First seen · 524 lines · 48 tokens per session scan A 7c0db2ff1e62

Subscribe to this mod's changes

particles-gpu is a skill published in the GitHub repository Bbeierle12/Skill-MCP-Claude (8 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 3,932 once invoked, about $0.0002 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.