What is apolo-cad CLAUDE.md?

A Claude Code instruction file for Genix Apolo CAD, a 3D computer-aided design tool for industrial machinery and robotics. It documents the Python geometry engine, web application, AI integration, command-based document format, and development rules.

Use it when developing or testing Apolo CAD, especially its conveyor and material-handling features, HTTP API, React and three.js interface, geometry generation, or saved .apolo documents.

It gives agents the architectural context needed to change a complex CAD system without breaking its API-first and event-based design.

How mariorojasmz/apolo-cad configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mariorojasmz/apolo-cad. 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/mariorojasmz/apolo-cad/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mariorojasmz/apolo-cad

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mariorojasmz/apolo-cad/claude-md/github.svg)](https://agentmods.dev/instructions/mariorojasmz/apolo-cad/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mariorojasmz/apolo-cad/claude-md"><img src="https://agentmods.dev/badge/instructions/mariorojasmz/apolo-cad/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mariorojasmz/apolo-cad/claude-md"><img src="https://agentmods.dev/badge/instructions/mariorojasmz/apolo-cad/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36,651 This file is loaded in full into every session.

When invoked 36,651 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.

Model	Per session	Once invoked
Fable 5.1	$0.36651	$0.36651
Opus 5	$0.18326	$0.18326
Sonnet 5	$0.07330	$0.07330
Haiku 4.5	$0.03665	$0.03665

Measured 9d ago against content hash ee4068c7015b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

apolo-cad 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 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.

CLAUDE.md · 1,402 lines

How it starts

The opening of the file, as written. The whole thing — 1,402 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Genix Apolo CAD

CAD paramétrico 3D para maquinaria industrial/robótica cuyo diferenciador es el diseño asistido por IA (agente-nativo, también manual). Vertical del MVP: transportadores / manejo de materiales. Stack: Python (build123d/OCCT) + FastAPI + React/three.js. IA: Claude API en la nube vía APOLO_MODEL (por defecto claude-opus-4-8).

Historia detallada: la narrativa completa de cada feature (verificaciones E2E, cirugías de modelos, decisiones de diseño con contexto) vive en docs/devlog.md y en git log. Este archivo conserva SOLO instrucciones, mapa del sistema, convenciones y lecciones — lo que hace falta para trabajar, no la crónica.

Arquitectura (principios que NO se negocian)

API-first / IA-nativa: toda operación es un comando sobre un kernel headless. UI, agente-chat y MCP son clientes iguales de la misma API HTTP.
Documento = log de comandos (event-sourced). .apolo = ZIP (manifest v2 + commands.json + attachments/). La geometría nunca se guarda → archivos de KB, autosave barato, undo/redo por snapshots.
Schema-driven: los JSON Schemas pydantic del REGISTRY generan a la vez la toolbar, los diálogos, el panel Propiedades y las tools del agente. Una sola fuente de verdad. El MCP es THIN: núcleo de escritura mínimo (run_command/run_batch con $k + edit_command/edit_batch + undo/redo cubren TODO el registro; NO hay tool por comando) — auditado: los huecos siempre han sido de LECTURA, no de escritura. Los lotes aceptan CONTRATO (expect, V6.5b): aserciones que deben cumplirse tras el regenerate o el lote se revierte por completo (mata-bucles del flujo mutar→leer→undo).
Expresiones: cualquier campo numérico acepta "=expresión" con variables del proyecto (motor AST en commands/expressions.py). Las variables son comandos set_variable en la cabecera del log; cambiarlas regenera todo.
Selectores declarativos de aristas/caras (todas/direccion/cara/longitud/cerca) para evitar nombrado topológico frágil.
Plantillas de máquina = super-comandos del registro (p. ej. create_conveyor), no scripts: heredan edición paramétrica, undo, BOM y exposición al agente gratis.
Criterio de ingeniería por defecto: el agente diseña como ingeniero/estructurista (el usuario es el CLIENTE) y asume lo obvio —sujeción, montaje/desmontaje con pernos, forma conforme a la función— sin esperar a que se lo pidan. Fuente ÚNICA en core/apolo/design/guidelines.py (design_brief() + design_guidelines()): capa 1 inyectada SIEMPRE en instrucciones MCP y SYSTEM_PROMPT; capa 2 bajo demanda (get_design_guidelines / GET /api/design-guidelines). Un 3D solo vale si es FABRICABLE y se SOSTIENE.

Read the full file on GitHub · 1,402 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.

9d ago First seen · 1,402 lines · 36,651 tokens per session scan A ee4068c7015b

Subscribe to this mod's changes

apolo-cad CLAUDE.md is an instructions file published in the GitHub repository mariorojasmz/apolo-cad (2 stars, last pushed 1mo ago), licensed MIT. It adds 36,651 tokens to every session, about $0.1833 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.

Design and UX

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

apolo-cad: Instructions file for Claude Code