From codex-image
Generates images using Codex CLI's built-in imagegen skill, optionally with reference images. Useful for creating visuals from natural language requests.
How this skill is triggered — by the user, by Claude, or both
Slash command
/codex-image:generate [--ref <reference-image> ...] <natural-language image request>[--ref <reference-image> ...] <natural-language image request>This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Leading `--ref <path>`, `--reference <path>`, or `--image <path>` arguments are reference images for generation, not edit targets. Repeat the flag for multiple references (max 5); quote paths with spaces.
Leading --ref <path>, --reference <path>, or --image <path> arguments are reference images for generation, not edit targets. Repeat the flag for multiple references (max 5); quote paths with spaces.
Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-image.mjs" generate "$ARGUMENTS"
Output rules:
SAVED: <absolute path> line per saved image.npx claudepluginhub kinggyusuh/codex-image-in-cc --plugin codex-imageGenerates raster images (icons, illustrations, textures, app icons) from text prompts by driving the Codex CLI image tool and extracting the PNG from session rollout data. Use when an agent has no native image-generation tool.
Generates and edits images via GPT Image 2 using a packaged CLI. Activates on text-to-image, reference editing, inpainting, posters, typography, UI mockups, and diagrams.
Generates and edits images using OpenAI Image API via bundled Python CLI for project assets like website heroes, UI mockups, logos, concept art, covers, and batch variants. Requires OPENAI_API_KEY.