Agent Skills: codex-imagegen

Generate or edit raster images (photos, illustrations, mockups, logos, product shots, game/UI assets, textures, infographics) using Codex's built-in image_gen tool — driven headlessly through `codex exec`. Billed via the user's ChatGPT/Codex login, so it needs NO OpenAI API key. Use whenever the user wants to create a brand-new image from a text prompt, edit an existing local image (background swap, lighting/weather change, object add/remove, restyle), or produce several image variants. Trigger on "generate an image", "make a picture/illustration/logo/mockup of X", "create a hero image", "edit this image", "change the background of X", "turn this photo into Y", "imagegen", "use codex to make an image". Do NOT use for vector/SVG icon systems, diagrams better built in code/HTML/CSS, or when the user explicitly wants the OpenAI Image API directly (that's the gpt-image CLI path).