Claude Code plugin for GPT Image 2-first image generation and editing workflows, with Codex convenience routing and direct OpenAI Images API execution.
Create visual mockups for landing pages, product heroes, dashboards, mobile screens, app store creatives, and UI marketing shots. Use when the user wants a frontend concept image rather than production code.
Generate game visual assets such as icons, props, key art, item sheets, stylized environments, and concept art. Use when the user is doing game ideation or asset creation and needs actual image outputs.
Generate or edit raster images for product design, frontend concepts, game assets, marketing visuals, and conceptual paper figures. Use when Claude should create a real image file through Codex or the OpenAI Images API instead of only suggesting prompts.
Edit existing images with background removal, style changes, reference-guided cleanup, product isolation, compositing, or localized visual changes. Use when the user wants a real edit applied to an existing image.
Create conceptual paper visuals, system diagrams, pipeline illustrations, cover-style research art, and non-numeric figure concepts. Use when the user wants a scientific or technical visual but not a code-native plot of measured data.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
codex_modelModel passed to codex exec when the Codex path is used.
${user_config.codex_model}provider_modeChoose auto, codex, or openai.
${user_config.provider_mode}openai_api_keyOptional API key used when provider mode is openai or when auto falls back to the OpenAI API.
${user_config.openai_api_key}openai_base_urlBase URL for the Images API.
${user_config.openai_base_url}default_output_dirOptional default directory for saved images. Leave blank to save into the current workspace.
${user_config.default_output_dir}openai_image_modelDefault OpenAI image model. Use a GPT Image model your account has access to.
${user_config.openai_image_model}
A Claude Code plugin that gives Claude the ability to generate and edit images using GPT Image 2.
In Claude Code:
plugin marketplace add aymenbouferroum/gpt-imagen
plugin install gpt-imagen@gpt-imagen
/reload-plugins
Then use any of the five included skills:
/gpt-imagen /frontend-mockup /game-asset-lab /paper-figure-visual /image-edit-studio
Full provider setup and local dev install: docs/INSTALL.md
| Skill | What it does |
|---|---|
/gpt-imagen | General-purpose image generation and editing |
/frontend-mockup | Landing pages, dashboards, product heroes, app store screenshots |
/game-asset-lab | Sprites, props, icons, key art, and stylized game visuals |
/paper-figure-visual | Conceptual research figures, pipeline diagrams, cover-style paper art |
/image-edit-studio | Background removal, restyling, compositing, and reference-driven edits |
![]() /frontend-mockup — Dashboard hero |
![]() /game-asset-lab — Fantasy inventory icons |
![]() /paper-figure-visual — Pipeline concept figure |
![]() /gpt-imagen — Product render |
Claude handles orchestration and prompt refinement. GPT Image 2 handles pixels.
GPT Imagen supports two provider paths:
| Provider | Setup | Best for |
|---|---|---|
| OpenAI API (default) | Set openai_api_key in plugin config or OPENAI_API_KEY env var | Full GPT Image 2 control, mask-based edits |
| Codex CLI | Have codex installed and logged in | Zero-config convenience for existing Codex users |
The plugin uses auto mode by default: tries Codex first, falls back to the API.
Full configuration options: docs/INSTALL.md
| Doc | Description |
|---|---|
| Install Guide | Provider setup, local dev install, configuration reference |
| Tutorial | Step-by-step examples for each skill |
| Capabilities | What GPT Imagen can and cannot do |
| Contributing | Development workflow and release process |
| Changelog | Version history |
| Acknowledgments | Credits |
npx claudepluginhub aymenbouferroum/gpt-imagen --plugin gpt-imagenPersistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.