codex-image
/codex-image
Generate or edit raster images (photos, illustrations, mockups, hero images, product shots, bitmap icons, transparent cutouts) with OpenAI GPT Image 2 by triggering the local Codex CLI, billed to the user's ChatGPT subscription — no API key needed. Use when the user says "generate an image", "make a picture/illustration/mockup", "use codex / gpt image / gpt-image-2", "edit this image", "remove the background", or a project needs a bitmap asset. Not for video, SVG, or graphics better built in code.
- Author
- mishagavura ↗
- Repository
- claude-code-image-generation ↗
- Licence
- MIT
- Last repository change
- 30.09.2026
Assessment and security
- Files in this package
- 2
- Scripts
- 1
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 30.09.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
- 1 scripts in this package. Review them before installing, as Claude may execute them.
Scripts: gen.sh
What it does and when to use it
Generate or edit raster images (photos, illustrations, mockups, hero images, product shots, bitmap icons, transparent cutouts) with OpenAI GPT Image 2 by triggering the local Codex CLI, billed to the user's ChatGPT subscription — no API key needed. Use when the user says "generate an image", "make a picture/illustration/mockup", "use codex / gpt image / gpt-image-2", "edit this image", "remove the background", or a project needs a bitmap asset. Not for video, SVG, or graphics better built in code.
Triggers from the description
Original author description
Generate or edit raster images (photos, illustrations, mockups, hero images, product shots, bitmap icons, transparent cutouts) with OpenAI GPT Image 2 by triggering the local Codex CLI, billed to the user's ChatGPT subscription — no API key needed. Use when the user says "generate an image", "make a picture/illustration/mockup", "use codex / gpt image / gpt-image-2", "edit this image", "remove the background", or a project needs a bitmap asset. Not for video, SVG, or graphics better built in code.
How it works
- Command
- Workflow
- Troubleshooting
SKILL.md preview
--- name: codex-image description: Generate or edit raster images (photos, illustrations, mockups, hero images, product shots, bitmap icons, transparent cutouts) with OpenAI GPT Image 2 by triggering the local Codex CLI, billed to the user's ChatGPT subscription — no API key needed. Use when the user says "generate an image", "make a picture/illustration/mockup", "use codex / gpt image / gpt-image-2", "edit this image", "remove the background", or a project needs a bitmap asset. Not for video, SVG, or graphics better built in code. --- # codex-image Runs Codex CLI non-interactively. Codex calls its built-in `image_gen` tool (GPT Image 2) and the script copies the result to the path you choose. Each call takes roughly 30–90 seconds. The script is `gen.sh` in this skill's base directory (shown when the skill loads), referred to below as `<skill-dir>`. ## Command ```bash <skill-dir>/gen.sh -o <out.png> [options] "<prompt>" ``` | Option | Meaning | |---|---| | `-o PATH` | Output file (required). Put project assets inside the project; otherwise use a temp/scratch folder. | | `-n N` | 1–4 variants → `out-1.png`, `out-2.png`, … | | `-r FILE` | Reference image for style/composition (repeatable) | | `-e FILE` | Image to edit — only what the prompt asks changes | | `-t` | Transparent background | | `-a square\|portrait\|landscape` | Aspect ratio | Prints the saved absolute path(s). Never overwrites: an existing name gets a time suffix. Give the Bash call a timeout of at least 300000 ms (600000 for `-n 3` or `-n 4`). For several different images, run separate commands in parallel instead of describing them all in one prompt — parallel runs are safe. ## Workflow 1. Turn the request into a clear prompt: subject, style/medium, composition, lighting, palette, exact text in quotes, and what to avoid. Keep the user's specifics; add detail only when the ask is vague. 2. Run `gen.sh`. 3. **Look at the output image** and check it matches (subject, spelling of any text, framing). If it's off, rerun with one targeted prompt change, or use `-e` on the result for a small fix. 4. Report the saved path(s) and the final prompt. If the image is for a project, reference it from the code. ## Troubleshooting - `codex CLI not found` → the user needs `npm i -g @openai/codex`. - `Codex is not logged in` → the user runs `codex login` and signs in with ChatGPT. - `No image was generated` → the ChatGPT plan's image limit may be used up, or the prompt was refused. Say so; don't retry in a loop. - `-t` output can have semi-transparent blotches. Check it; if dirty, regenerate on a plain white background without `-t` and remove the background separately.
Files in this package (2)
- SKILL.md 3 KB
- gen.sh 4 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · mishagavura/claude-code-image-generation | 100 | MIT |
| sevenevesai/skills | 100 | MIT |
| openminis/minisskills | 100 | MIT |
Database snapshot: 13.11.2026 · package version a5b7fb9ae6ef (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100codex-image-generator
Default image generation path. Generate or edit raster images (hero images, illustrations, textures, product shots, mockups, transparent cutouts) through the Codex CLI's built-in image_gen tool, run in a subagent. Use whenever the user asks for an image, picture, illustration,… - 100codex-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.… - 100generate-image
Generate images with OpenAI GPT Image 2 via the Codex CLI, billed through the user's ChatGPT Plus subscription (no OpenAI API key, no per-image API cost). Use when the user asks to create, generate, or make an image, picture, illustration, icon, hero graphic, or concept art from a text prompt. - 95gpt-image-2
Generate or edit a raster image with OpenAI's gpt-image-2 through the Codex CLI, billed to the ChatGPT subscription rather than an API key. Use whenever the user asks for a photo, illustration, mockup, texture, marketing visual, or an edit to an existing image file, including… - 95generate-image
Generate new raster images and edit existing ones via fal.ai (GPT Image 2.5, Nano Banana 2.1) — illustrations, product photos, hero art, UI mockups, background removal. Use whenever the user asks to generate/create/make an image, produce a photo or illustration for a page, get a… - 84generate-image
Generate images (icons, logos, banners, illustrations, mockups, photos, textures, diagrams-as-art) with OpenAI gpt-image-2 through the locally installed Codex CLI, using the user's existing ChatGPT login — no API key. Use whenever the user asks to generate, create, draw, or mock…