No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by dreiachse-cyber · Codex Skill · ★ 283
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is image-cockpit-for-codex-workflows safe to install? View the security audit →
Image Cockpit for Codex Workflows Local image production cockpit for Codex-era workflows. This project is unofficial and not affiliated with OpenAI. It is a local workspace for generating pixel art, then turning selected pixel-art assets into animation frames and sprite sheets. Product Boundary Image Cockpit is designed to run on a local machine where Codex is installed. The app itself does not call OpenAI APIs and does not require an API key. Pixel art generation is routed through the local Codex handoff. When can use the skill / built-in path, complex prompts can produce real raster images and return them to . The app itself still does not call OpenAI APIs directly. For development and fallback checks, the app also includes a built-in procedural PNG generator. It is local and deterministic, meant to keep API and import flows testable without external services. It is not the primary image-quality path and is not a replacement for Codex imagegen. Instead, the cockpit writes local handoff jobs for Codex: Codex, the user, or another local workflow can read the inbox job, create or revise assets, and place results in the outbox. Results can then be imported through the Lo
| Stars | 283 |
| Forks | 38 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 67.4543130373343/100 |
| Last Updated | 2026-07-28 |
| Created | 2026-06-23 |
| Platforms | codex, node |
| Est. Tokens | ~16k |
These tools work well together with image-cockpit-for-codex-workflows for enhanced workflows:
Looking for a image-cockpit-for-codex-workflows alternative? If you're comparing image-cockpit-for-codex-workflows with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Generate clean 2D game sprites & animation atlases — component-row pipeline: state rows, alpha cleanup, frame
UltraGameStudio - AI coding agent for game development: engine workflows, gameplay code, and asset generation.
FreeUltraCode - AI coding agent for game development: engine workflows, gameplay code, and asset generation.
🚀 A real-time monitoring dashboard for Claude Code & Codex, built with SQLite3, Node.js, Express, React, Vite
Skills for Claude Code CLI such as full stack dev Cloudflare, React, Tailwind v4, and AI integrations.
73 game-dev skills for AI coding agents — Godot, Unity, Unreal, Phaser, PixiJS, three.js, Bevy, pygame, LÖVE,
Explore other popular codex skill tools:
image-cockpit-for-codex-workflows is Local cockpit for Codex imagegen, pixel art, image editing, animation, and sprite-sheet workflows.. It is categorized as a Codex Skill with 283 GitHub stars.
image-cockpit-for-codex-workflows is primarily written in TypeScript. It covers topics such as codex, game-dev, image-generation.
You can find installation instructions and usage details in the image-cockpit-for-codex-workflows GitHub repository at github.com/dreiachse-cyber/image-cockpit-for-codex-workflows. The project has 283 stars and 38 forks, indicating an active community.
image-cockpit-for-codex-workflows is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to image-cockpit-for-codex-workflows on Agent Skills Hub include sprite-gen, UltraGameStudio, FreeUltraCode. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: