Tracely-ai: Skill for Claude Code

.agents/skills/threejs-r3f/SKILL.md

threejs-r3f is a skill for Claude Code, Codex from Jwuthri/Tracely-ai. It costs 26 tokens per session (1,848 once invoked), scanned A, original, MIT.

A guide to building 3D scenes and visual effects for websites with Three.js, a JavaScript 3D engine, and React Three Fiber, its React-based renderer.

In plain words
What is it for?
Use it to create React-based 3D scenes with models, lights, controls, loaders, shaders, and postprocessing, or decide when direct Three.js, CSS, Canvas, or WebGL is more suitable.
Why use it?
It helps choose the right web graphics approach for full 3D scenes, simple transformations, particles, or shader effects.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Jwuthri/Tracely-ai's own configuration. It tells Claude Code and Codex how to work on Tracely-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Tracely-ai configures →

About the project

Tracely is a CI/CD system for AI agents that turns failed production traces into replayable regression tests. Development teams use it to detect and group agent failures, run the resulting cases on pull requests, and block changes that reproduce those failures. The catalogue entries provide skills for operating this trace-based testing and observability workflow.

Jwuthri/Tracely-ai · 1,221 stars · on GitHub · tracely-ai.com

Reuse

Borrowing it

Nothing to install: this file belongs to Jwuthri/Tracely-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Jwuthri/Tracely-ai/master/.agents/skills/threejs-r3f/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Jwuthri/Tracely-ai

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 threejs-r3f

README.md
[![agentmods](https://agentmods.dev/badge/skills/jwuthri/tracely-ai/threejs-r3f/github.svg)](https://agentmods.dev/skills/jwuthri/tracely-ai/threejs-r3f)
Your own site
<a href="https://agentmods.dev/skills/jwuthri/tracely-ai/threejs-r3f"><img src="https://agentmods.dev/badge/skills/jwuthri/tracely-ai/threejs-r3f/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 threejs-r3f

Your own site · 80×15
<a href="https://agentmods.dev/skills/jwuthri/tracely-ai/threejs-r3f"><img src="https://agentmods.dev/badge/skills/jwuthri/tracely-ai/threejs-r3f.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,848 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 $0.00026 $0.01848
Opus 5 $0.00013 $0.00924
Sonnet 5 $0.00005 $0.00370
Haiku 4.5 $0.00003 $0.00185

Measured 10d ago against content hash aeee54f83cd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

threejs-r3f 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 10d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.agents/skills/threejs-r3f/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Three.js & React Three Fiber

3D on the web. Three.js is the engine, R3F is the React renderer. Concise rules here. Deep-dive in references/.


When to Use What

Need Tool Why
Full 3D scene (models, lights, physics) R3F + drei Declarative, React-friendly, ecosystem
Vanilla 3D (no React) Three.js direct Lighter, no React overhead
Simple 3D transforms on UI CSS transform3d GPU-composited, no WebGL context
2D particles / generative Canvas 2D Simpler API, less GPU overhead
Shader-only visuals (no scene graph) Raw WebGL / ShaderMaterial Maximum control, minimal abstraction

Scene Setup Patterns

import { Canvas } from '@react-three/fiber'
import { Environment, OrbitControls } from '@react-three/drei'
import { Suspense } from 'react'

<Canvas camera={{ position: [0, 2, 5], fov: 45 }} dpr={[1, 2]} gl={{ antialias: true }}>
  <Suspense fallback={null}>
    <Environment preset="studio" />
    <OrbitControls makeDefault />
    <Scene />
  </Suspense>
</Canvas>

Rules:

  • Always wrap scene content in <Suspense> -- loaders (GLTF, textures, HDRI) need it
  • Set dpr={[1, 2]} to clamp pixel ratio (Retina without melting GPUs)
  • Keep the Canvas parent component minimal -- re-renders propagate into the scene

R3F Hooks

Hook Purpose Gotcha
useFrame((state, delta) => {}) Per-frame logic (animation, physics) Never setState inside
useThree() Access gl, scene, camera, size, viewport, pointer Destructure only what you need
useLoader(TextureLoader, url) Load any Three.js resource Wrap parent in Suspense
useGraph(scene) Extract nodes/materials from loaded scene Useful after useGLTF

useFrame Tips

useFrame((state, delta) => {
  // Use delta for framerate-independent animation
  meshRef.current.rotation.y += delta * 0.5
  // Access clock for time-based effects
  material.uniforms.uTime.value = state.clock.elapsedTime
})

Read the full file on GitHub · 244 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. 10d ago First seen · 244 lines · 26 tokens per session scan A aeee54f83cd7

Subscribe to this mod's changes

threejs-r3f is a skill published in the GitHub repository Jwuthri/Tracely-ai (1,221 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,848 once invoked, about $0.0001 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

add-error-tracking

Add Temps error tracking to applications using the Sentry-compatible SDK. Temps exposes a Sentry-compatible DSN that works with the official Sentry SDK for each language/framework — no code changes beyond initialization are required. Use when the user wants to: (1) Add error tracking to any app (React, Next.js, Vue…

gotempsh/temps · 182 tokens

add-react-analytics

Add Temps analytics to React applications with comprehensive tracking capabilities including page views, custom events, scroll tracking, engagement monitoring, session recording, and Web Vitals performance metrics. Use when the user wants to: (1) Add analytics to a React app (Next.js App Router, Next.js Pages Router…

gotempsh/temps · 167 tokens

temps-design-system

Build or review console UI so it reads as Temps: the paper-and-ink operator design system (@temps-sdk/ds primitives, the operator ink v1 skin, the Ledger / Detail / Settings page templates, the status vocabulary and the record recipe). Invoke when a task adds or redesigns a console screen, a landing section or a…

gotempsh/temps · 148 tokens

add-session-recording

Add privacy-aware session recording and replay to React applications using the Temps SDK. Captures user interactions for playback while respecting privacy through input masking, element blocking, and GDPR-compliant consent flows. Use when the user wants to: (1) Add session recording to their app, (2) Implement session…

gotempsh/temps · 148 tokens

deploy-to-temps

Deploy applications to the Temps platform with automatic framework detection, Dockerfile generation, and container orchestration. Supports Next.js, Vite, React, Node.js, Python, Go, Rust, Java, and C# applications. Use when the user wants to: (1) Deploy their app to Temps, (2) Set up CI/CD with Temps, (3) Configure…

gotempsh/temps · 141 tokens

bun-sveltekit

Use when building or running SvelteKit apps on Bun, including SSR, adapters, and Bun-specific APIs.

secondsky/claude-skills · 26 tokens