What problem does it solve? Creating a Codex-compatible animated pet requires producing a precise 8x11 spritesheet atlas with 9 animation rows and 16 look directions, plus deterministic QA and packaging, which is error-prone to do manually. ## Core Features & Use Cases - End-to-End Pet Generation: Create a v2 pet from character art, generated images, brand cues, or text concepts, producing a 1536x2288 atlas with spriteVersionNumber 2. - Deterministic Assembly and QA: Use bundled Python scripts to extract frames, mirror running-left, compose atlases, suppress chroma spill, and validate every cell. - Repair and Upgrade Workflows: Repair existing pets, upgrade 8x9 atlases to v2, and run brand discovery for company-inspired mascots. - Use Case: Give the assistant a company name and it researches the brand, generates a mascot base image, produces all animation rows and look directions, validates them, and packages the pet under ~/.codex/pets. ## Quick Start Ask the assistant to hatch a new Codex pet named Sparky from your reference image and package it as a v2 spritesheet.