GPT Image 2 — image generation through your ChatGPT subscription
💳 Paid subscription required — generate images with GPT Image 2 inside Claude Code through the local Codex CLI and your existing ChatGPT Plus/Pro plan: text-to-image, image-to-image editing, style transfer, and multi-reference composition
- What
- 💳 Paid subscription required — generate images with GPT Image 2 inside Claude Code through the local Codex CLI and your existing ChatGPT Plus/Pro plan: text-to-image, image-to-image editing, style transfer, and multi-reference composition
- Cost
- Free
- Needs
- a paid ChatGPT Plus or Pro subscription with image-generation entitlement, and the local `codex` CLI installed and logged in (`codex login`) — no free tier; python3 on PATH
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @agentspace-so's gpt-image-2 skill, listed here with credit to its creator: generate images with GPT Image 2 (ChatGPT Images 2.0) inside your agent, through your existing ChatGPT Plus or Pro subscription — no separate OpenAI access, no per-image billing. A single bash script runs `codex exec` with the right flags, then extracts the generated image from the persisted session rollout: text-to-image, image-to-image editing, style transfer, and multi-reference composition, with the user's prompt passed through raw (no rewriting, no silent fallbacks to other models or mockups). It documents the hard constraints honestly — the local `codex` CLI must be installed and logged in with a ChatGPT plan that carries the image-generation entitlement; `--enable image_generation` is required; `--ephemeral` must not be used — plus exit codes, a careful data-handling story (only session files created by its own run are read; no other Codex conversations are touched; no telemetry), and a browser-based fallback (RunComfy) if you lack the subscription. Honest caveats: 💳 requires a paid ChatGPT Plus/Pro subscription with image entitlement and the local Codex CLI logged in — there is no free tier and nothing here works without it; one call per invocation (serialized); generation quality is whatever OpenAI's model returns. MIT licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: a paid ChatGPT Plus or Pro subscription with image-generation entitlement, and the local `codex` CLI installed and logged in (`codex login`) — no free tier; python3 on PATH Install "GPT Image 2 — image generation through your ChatGPT subscription" for me. It gives my agent @agentspace-so's GPT Image 2 workflow: run a single bash script through the local Codex CLI to generate images with my existing ChatGPT subscription — text-to-image, image-to-image editing with repeatable --ref flags, style transfer, and multi-reference composition — with my prompt passed through raw (no rewriting, no silent substitution of another model or HTML mockups), plus exit-code diagnostics, data-handling guarantees (only its own session files are read), and the hard constraints documented (--enable image_generation required; --ephemeral forbidden). MIT licensed. Repository: https://github.com/agentspace-so/agent-skills/blob/main/gpt-image-2/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code — it reuses my existing Codex login and reads only its own session rollouts. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "gpt-image-2". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. install the Codex CLI and run `codex login` with my ChatGPT Plus/Pro account; check the image-generation entitlement; make sure python3 is on PATH). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.