Three.js-Claude-Skill-Package: Instructions file for Claude Code

CLAUDE.md

Three.js-Claude-Skill-Package CLAUDE.md is an instructions file for Claude Code from Impertio-Studio/Three.js-Claude-Skill-Package. It costs 2,822 tokens per session, scanned A, original, MIT.

Project instructions for a Three.js skill package, where Three.js is a JavaScript library for creating 3D graphics in web pages.

In plain words
What is it for?
Use it when developing or maintaining this Three.js skill package, including its roadmap, requirements, decisions, sources, and GitHub publication workflow.
Why use it?
It tells the coding agent how to resume work, research official documentation, delegate tasks, and check the package against strict quality rules.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is Impertio-Studio/Three.js-Claude-Skill-Package's own configuration. It tells Claude Code how to work on Three.js-Claude-Skill-Package 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 Three.js-Claude-Skill-Package configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Impertio-Studio/Three.js-Claude-Skill-Package. 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/Impertio-Studio/Three.js-Claude-Skill-Package/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Impertio-Studio/Three.js-Claude-Skill-Package

Made for: Claude Code.

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 Three.js-Claude-Skill-Package CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/impertio-studio/three.js-claude-skill-package/claude-md.svg)](https://agentmods.dev/instructions/impertio-studio/three.js-claude-skill-package/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/impertio-studio/three.js-claude-skill-package/claude-md"><img src="https://agentmods.dev/badge/instructions/impertio-studio/three.js-claude-skill-package/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,822 This file is loaded in full into every session.
When invoked 2,822 The same file — it is already loaded in full.
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 $0.02822 $0.02822
Opus 5 $0.01411 $0.01411
Sonnet 5 $0.00564 $0.00564
Haiku 4.5 $0.00282 $0.00282

Measured 8d ago against content hash f8b121ea5f39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Three.js-Claude-Skill-Package CLAUDE.md 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 8d 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.

CLAUDE.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Three.js Skill Package — CLAUDE.md

Master configuration for the Three.js Claude Code Skill Package. This file is automatically loaded by Claude Code at session start.


Standing Orders — READ THIS FIRST

Mission: Build a complete, production-ready skill package for Three.js and publish it under the OpenAEC Foundation on GitHub. This is your standing order for every session in this workspace.

How: Follow the 7-phase research-first methodology. Delegate ALL execution to agents. You are the ARCHITECT — you think, plan, validate, and delegate. Agents do the actual work.

What you do on session start:

  1. Read ROADMAP.md → determine current phase and next steps
  2. Read all core files (LESSONS.md, DECISIONS.md, REQUIREMENTS.md, SOURCES.md)
  3. Continue where the previous session left off
  4. If Phase 1 is incomplete → create the raw masterplan first
  5. If Phase 2+ → follow the methodology, delegating in batches of 3 agents

Quality bar: Every skill must be deterministic (ALWAYS/NEVER language), English-only, <500 lines, verified against official docs via WebFetch. No hallucinated APIs. No vague language.

End state: A published GitHub repo at https://github.com/OpenAEC-Foundation/Three.js-Claude-Skill-Package with:

  • All skills created, validated, and organized
  • INDEX.md with complete skill catalog
  • README.md with installation instructions and skill table
  • Social preview banner (1280x640px) with OpenAEC branding
  • Release tag (v1.0.0) and GitHub release
  • Repository topics set (claude, skills, threejs, 3d, webgl, webgpu, ai, deterministic, openaec)

Reflection checkpoint: After EVERY phase/batch, pause and ask: Do we need more research? Should we revise the plan? Are we meeting quality standards? Update core files before proceeding.

Consolidate lessons: Any workflow-level insight (not tech-specific) should also be noted for consolidation back to the Workflow Template repo (C:\Users\Freek Heijting\Documents\GitHub\Skill-Package-Workflow-Template).

Read the full file on GitHub · 254 lines

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. 8d ago First seen · 254 lines · 2,822 tokens per session scan A f8b121ea5f39

Subscribe to this mod's changes

Three.js-Claude-Skill-Package CLAUDE.md is an instructions file published in the GitHub repository Impertio-Studio/Three.js-Claude-Skill-Package (12 stars, last pushed 2mo ago), licensed MIT. It adds 2,822 tokens to every session, about $0.0141 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens