🎯

codex-pet

🎯Skill

from agentspace-so/runcomfy-agent-skills

What it does

Generates custom Codex Pets for OpenAI Codex using RunComfy's GPT Image 2 edit endpoint. Turns a single reference image into a Codex-compatible spritesheet (1536x1872, 9 animation states) and pet.json manifest with just one API call, requiring only a RUNCOMFY_TOKEN — no Codex Pro or OPENAI_API_KEY needed.

Overview

A skill that generates custom OpenAI Codex Pets using the RunComfy CLI and GPT Image 2's edit endpoint. Codex Pets are pixel-art animated companions that float over your desktop while Codex codes, reacting to mouse interaction and Codex status. This skill takes a single reference image and produces a complete Codex Pet package: a 1536x1872 spritesheet (8 columns x 9 rows of 192x208 cells with 9 animation states) and a pet.json manifest. It requires only a RUNCOMFY_TOKEN and ImageMagick, with no Codex Pro subscription or OPENAI_API_KEY needed.

Key Features

Single-call generation pipeline that produces a canonical chibi pose via one GPT Image 2 edit call, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms
Full Codex Pet specification compliance outputting the exact atlas format Codex expects: 1536x1872 PNG/WebP, 8 columns x 9 rows, 192x208 cells covering idle, running, waving, jumping, failed, waiting, and review states
Drop-in installation where the output files go directly to ~/.codex/pets/<name>/ and Codex picks them up alongside the 8 built-in pets
No Codex Pro or OPENAI_API_KEY required since generation runs through the RunComfy CLI with just a RUNCOMFY_TOKEN

Who is this for?

OpenAI Codex users who want custom animated desktop pets but do not have Codex Pro or access to the built-in $imagegen system
Developers entering Codex Pet contests or building batch pet generation from a folder of source images
Anyone who wants a personalized Codex Pet built from their own reference image using the RunComfy model API

📦

Same repository

agentspace-so/runcomfy-agent-skills(30 items)

codex-pet

Installation

Vibe Index InstallInstalls to .claude/skills/

npx vibeindex add agentspace-so/runcomfy-agent-skills --skill codex-pet

skills.sh Install⚠ Installs to .agents/skills/

npx skills add agentspace-so/runcomfy-agent-skills --skill codex-pet

Manual InstallCopy SKILL.md content and save to the path below

~/.claude/skills/codex-pet/SKILL.md

SKILL.md

196,659Installs

AddedMay 9, 2026

View on GitHub Back to Skills

More from this repository10

🎯

video-edit🎯Skill

A smart intent-routing skill for video editing on RunComfy that selects the best model based on the user's intent. Routes to Wan 2.7 Edit-Video for restyle and background swaps, Kling 2.6 Pro for precise motion transfer, or Lucy Edit for lightweight identity-stable restyle and outfit swaps.

🎯

image-to-video🎯Skill

A smart intent-routing skill for image-to-video generation on RunComfy that automatically selects the best model for the task. Routes to HappyHorse 1.0 I2V for general animations, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition from image, video, and audio references.

🎯

image-edit🎯Skill

A smart intent-routing skill for image editing on RunComfy that selects the best model based on the editing task. Routes to Nano Banana Edit for batch edits up to 20 images, GPT Image 2 for multilingual text rewrite, Flux Kontext Pro for single-shot precise edits, or Z-Image Turbo for mask-driven inpainting.

🎯

flux-kontext🎯Skill

Edit images with Black Forest Labs' Flux 1 Kontext Pro on RunComfy, specializing in single-reference precise local edits with high-fidelity source preservation. Ideal for targeted changes like adding objects or modifying details while keeping the rest of the image unchanged.

🎯

nano-banana-2🎯Skill

A RunComfy skill that generates images using Google Nano Banana 2, the flash-tier text-to-image model in the Gemini family. Optimized for rapid iteration, social thumbnails, and in-image typography with configurable resolution tiers and safety tolerance.

🎯

nano-banana-edit🎯Skill

Edit images with Google Nano Banana 2 on RunComfy, supporting batch edits of up to 20 images per call with strong identity preservation. Features localized edits using spatial language, background swaps, and configurable resolution up to 4K.

🎯

happyhorse-1-0🎯Skill

Generate text-to-video with HappyHorse 1.0 on RunComfy, currently ranked #1 on Artificial Analysis Video Arena. Supports native 1080p with in-pass synchronized audio, multi-shot character consistency, and 6-language prompt support via the RunComfy CLI.

🎯

wan-2-7🎯Skill

Generate text-to-video with Wan-AI's Wan 2.7 on RunComfy, featuring multi-reference conditioning and audio-driven lip-sync via custom audio tracks. Supports prompt expansion, negative prompts, and up to 1080p resolution through the RunComfy CLI.

🎯

seedance-v2🎯Skill

Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy, supporting multi-modal references including up to 9 images, 3 videos, and 3 audio tracks. Features native lip-synced audio generation and is ideal for brand-consistent multi-language narratives.

🎯

gpt-image-edit🎯Skill

Edit images with OpenAI GPT Image 2 on RunComfy, excelling at multilingual in-image text editing across any script (Latin, kana, CJK, Cyrillic, Arabic) and multi-reference composition with up to 10 input images. Ideal for identity-preserving edits and layout-precise repositioning.