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 skills add Bbeierle12/Skill-MCP-Claude --skill particles-physicsgit clone --depth 1 https://github.com/Bbeierle12/Skill-MCP-ClaudeWrote 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/bbeierle12/skill-mcp-claude/particles-physics)<a href="https://agentmods.dev/skills/bbeierle12/skill-mcp-claude/particles-physics"><img src="https://agentmods.dev/badge/skills/bbeierle12/skill-mcp-claude/particles-physics/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.
<a href="https://agentmods.dev/skills/bbeierle12/skill-mcp-claude/particles-physics"><img src="https://agentmods.dev/badge/skills/bbeierle12/skill-mcp-claude/particles-physics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00050 | $0.04505 |
| Opus 5 | $0.00025 | $0.02253 |
| Sonnet 5 | $0.00010 | $0.00901 |
| Haiku 4.5 | $0.00005 | $0.00451 |
Grade A, and why
particles-physics 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.
How it starts
The opening of the file, as written. The whole thing — 555 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Particle Physics
Apply forces, fields, and constraints to create dynamic particle motion.
Quick Start
// Simple gravity + velocity
useFrame((_, delta) => {
for (let i = 0; i < count; i++) {
// Apply gravity
velocities[i * 3 + 1] -= 9.8 * delta;
// Update position
positions[i * 3] += velocities[i * 3] * delta;
positions[i * 3 + 1] += velocities[i * 3 + 1] * delta;
positions[i * 3 + 2] += velocities[i * 3 + 2] * delta;
}
geometry.attributes.position.needsUpdate = true;
});
Force Types
Gravity (Constant Force)
function applyGravity(
velocities: Float32Array,
count: number,
gravity: THREE.Vector3,
delta: number
) {
for (let i = 0; i < count; i++) {
velocities[i * 3] += gravity.x * delta;
velocities[i * 3 + 1] += gravity.y * delta;
velocities[i * 3 + 2] += gravity.z * delta;
}
}
// Usage
const gravity = new THREE.Vector3(0, -9.8, 0);
applyGravity(velocities, count, gravity, delta);
Wind (Directional + Noise)
function applyWind(
velocities: Float32Array,
positions: Float32Array,
count: number,
direction: THREE.Vector3,
strength: number,
turbulence: number,
time: number,
delta: number
) {
for (let i = 0; i < count; i++) {
const x = positions[i * 3];
const y = positions[i * 3 + 1];
const z = positions[i * 3 + 2];
// Base wind
let wx = direction.x * strength;
let wy = direction.y * strength;
let wz = direction.z * strength;
// Add turbulence (using simple noise approximation)
const noise = Math.sin(x * 0.5 + time) * Math.cos(z * 0.5 + time);
wx += noise * turbulence;
wy += Math.sin(y * 0.3 + time * 1.3) * turbulence * 0.5;
wz += Math.cos(x * 0.4 + time * 0.7) * turbulence;
velocities[i * 3] += wx * delta;
velocities[i * 3 + 1] += wy * delta;
velocities[i * 3 + 2] += wz * delta;
}
}
Drag (Velocity Damping)
function applyDrag(
velocities: Float32Array,
count: number,
drag: number, // 0-1, higher = more drag
delta: number
) {
const factor = 1 - drag * delta;
for (let i = 0; i < count; i++) {
velocities[i * 3] *= factor;
velocities[i * 3 + 1] *= factor;
velocities[i * 3 + 2] *= factor;
}
}
// Quadratic drag (more realistic)
function applyQuadraticDrag(
velocities: Float32Array,
count: number,
coefficient: number,
delta: number
) {
for (let i = 0; i < count; i++) {
const vx = velocities[i * 3];
const vy = velocities[i * 3 + 1];
const vz = velocities[i * 3 + 2];
const speed = Math.sqrt(vx * vx + vy * vy + vz * vz);
if (speed > 0) {
const dragForce = coefficient * speed * speed;
const factor = Math.max(0, 1 - (dragForce * delta) / speed);
velocities[i * 3] *= factor;
velocities[i * 3 + 1] *= factor;
velocities[i * 3 + 2] *= factor;
}
}
}
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.
- 9d ago First seen · 555 lines · 50 tokens per session scan A 7ad32c51d731
particles-physics is a skill published in the GitHub repository Bbeierle12/Skill-MCP-Claude (8 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 4,505 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 2026-08-31.
Other skills, from other repositories
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…
paper-illustration
A workflow for generating academic illustrations, such as architecture diagrams and method visuals, with image generation and repeated review. Claude plans and checks the figure during the process.
paper-illustration-image2
Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to paper-illustration, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.
pysr
Use when fitting equations to data with PySR or SymbolicRegression.jl, when a user wants an interpretable formula, symbolic model, scaling law, or empirical relation discovered from numeric data, or when debugging a PySR search that is slow, stuck, or giving poor equations.
paper-2-web
Use when converting academic papers into dissemination assets such as Paper2Web websites, Paper2Video video abstracts, or Paper2Poster conference posters from LaTeX or PDF sources.
rocm-kernels
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…