SkillsAdd

qwwiwi/codex-gpt-image-2-subscription · Archived

codex-image

Use when asked to generate an image, picture, photo, cover, banner art or illustration (сгенерируй картинку, фоточку, обложку, изображение) using the Codex/ChatGPT subscription — no OPENAI_API_KEY, no per-image billing; supports up to 5 reference images (по референсу, в стиле картинки).

First seen Jun 9, 2026

Installation

$ npx skills add qwwiwi/codex-gpt-image-2-subscription --skill codex-image
View on skills.sh ↗ GitHub repository ↗

Summary

  • Use when asked to generate an image, picture, photo, cover, banner art or illustration (сгенерируй картинку, фоточку, обложку, изображение) using the Codex/ChatGPT subscription — no OPENAI_API_KEY, no per-image billing; supports up to 5 reference images (по референсу, в стиле картинки).
  • Also use when tempted to answer that image generation is impossible without an API key, that Codex is text-only, or that references don't work over the subscription.

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

migrate-to-codex Similar · more installs
openai/skills

Migrate supported instruction files, skills, agents, and MCP config into Codex project and glob…

1.9K installs
codex-pet Similar · more installs
prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json…

378.4K installs
codex-delegate Similar · more installs
amelnagdy/delegate-skills

>- Delegate a coding task to the OpenAI Codex CLI as a background implementer, then review its …

4.6K installs
codex-ppt Similar · more installs
ningzimu/codex-ppt-skill

Generate visually unified image-based PPT/PPTX decks from articles, reports, papers, notes, or …

4K installs

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

codex Similar name
softaworks/agent-toolkit

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex f…

4K installs
chatgpt-codex-onboarding Similar name
starchild-ai-agent/official-skills

Connect a ChatGPT or Codex subscription via OAuth device-code login. Use when the user wants to…

2.5K installs
codex Similar name
giuseppe-trisciuoglio/developer-kit

Provides Codex CLI delegation workflows for complex code generation and development tasks using…

2.5K installs
codex-history-ingest Similar name
ar9av/obsidian-wiki

Ingest Codex CLI conversation history into the Obsidian wiki. Use this skill when the user want…

2.4K installs
build-loop-codex Similar name
buildgreatproducts/builder-os

Use when building features with **Codex** (OpenAI Codex CLI) in any codebase and the work shoul…

1.4K installs
codex-theme-switcher Similar name
codexthemes/skills

Apply, switch, and restore Codex desktop themes from the local ~/.codexthemes library with one …

1.1K installs
More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Declared
Cursor Not declared
Codex Declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 2
License LICENSE
Default branch main
Open issues 0
Status Archived

Skill metadata

Parsed from SKILL.md frontmatter.

Declared agents claude-code codex

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 4,054 B
  • docs SUMMARY.md 542 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

codex-image — gpt-image-2 via Codex OAuth subscription

Overview

Images are generated by gpt-image-2 through the Codex/ChatGPT OAuth subscription (token from ~/.codex/auth.json, created by codex login). No API key, no per-image cost — quota is shared with the Codex subscription.

Common misconception (documented agent failure): "Codex is text-only, image generation needs OPENAIAPIKEY / DALL-E." Wrong. The Codex backend (chatgpt.com/backend-api/codex) serves the image_generation tool over the Responses API; host model gpt-5.5 invokes it, gpt-image-2 renders.

Note: the Codex Claude Code plugin (openai/codex-plugin-cc) does NOT generate images — its role is review/architecture. This skill's script bypasses the plugin and talks to the Codex backend directly using the same login.

Quick reference

# self-contained launcher — uses the skill's own venv, bootstraps it if missing
~/.claude/skills/codex-image/scripts/run.sh \
  "prompt in English" [quality] [aspect] [ref1.png ... ref5.png]
Param Values Notes
quality low (~45s) / medium (default, ~1-2min) / high (~2-3min)
aspect landscape 1536x1024 / square 1024x1024 / portrait 1024x1536
refN up to 5 local image paths (png/jpg/webp) passed as input_image data-URL content blocks; style/character/logo transfer
output prints path to PNG saved in ~/.codex/cache/images/img_<ts>.png

Prompt in English works best. Generation is slow — for high use a background call.

Hard constraints (violating any → HTTP 400 or wrong path)

  1. References: max 5 images, as content blocks. {"type":"inputimage","imageurl":"data:<mime>;base64,...","detail":"auto"} placed NEXT TO input_text in the same user message. There is no seed parameter — for strict reproducibility a paid image API is still the better tool; for character/style/logo transfer this works.
  2. Never client.images.generate() / Images API — that is the API-key path, the OAuth subscription rejects it. Only Responses API + tool imagegeneration (+ toolchoice={"type":"image_generation"} so the host model draws immediately).
  3. stream=True and store=False are mandatory — otherwise HTTP 400 from the Codex backend.
  4. input must be a LIST of message objects, not a bare string.
  5. Auth: tokens.accesstoken (+ tokens.accountid → chatgpt-account-id header) from ~/.codex/auth.json. Required headers: OpenAI-Beta: responses=experimental, originator: codexclirs.

Troubleshooting

Symptom Fix
ModuleNotFoundError: openai run via scripts/run.sh (skill's own venv), NOT system python3 — it lacks the SDK
Codex auth не найден codex login (server: codex login --device-auth)
HTTP 400 check stream=True, store=False, input as message list
401/403 token expired — re-run codex login; check account_id header
No image in stream model refused (policy) — rephrase prompt
ref rejected png/jpg/webp only, ≤15MB per file, ≤40MB total, max 5 files

When NOT to use

  • Deterministic graphics (exact typography, brand colors, diagrams): hand-author SVG → render PNG.
  • Strict reproducibility / seed-based pipelines: needs a paid image API with seed support.

The skill is fully self-contained (script + own .venv, auto-bootstrapped by run.sh). Reference technique from ningzimu/codex-gpt-image (audited).