By jandersoncrb
Generate UI image assets (heroes, avatars, illustrations, og:images, etc.) by delegating to the Codex MCP server. Bundles a slash command and an auto-triggering skill.
A Claude Code plugin that generates UI image assets — hero images, avatars, illustrations, og:images, broken <img> placeholders, and so on — by delegating the actual generation to the Codex MCP server.
Claude does the prompt engineering, picks dimensions, and wires the generated file into your codebase. Codex is treated as a dumb image-generation pipe: it takes a verbatim prompt, produces a PNG, saves it to disk, and reports back. No API keys, no model selection, no post-processing.
codex-images) — auto-triggers when Claude detects the current task involves producing or replacing an image asset (UI work, broken image references, explicit image-generation requests)./codex-images) — manual invocation when you want to force it.Both share the same workflow: analyse the context → decide what images are needed → write rich prompts → call the codex MCP tool → wire the saved files into your code.
You need the Codex MCP server registered in Claude Code:
# Install the codex CLI first (https://github.com/openai/codex)
claude mcp add --scope user codex -- codex mcp-server
claude mcp list # should show: codex ✓ Connected
That's it. No OPENAI_API_KEY setup required on Claude's side — Codex handles all of that internally.
claude plugin marketplace add https://github.com/JandersonCRB/codex-images
claude plugin install codex-images@codex-images
git clone https://github.com/JandersonCRB/codex-images ~/dev/codex-images
claude plugin marketplace add ~/dev/codex-images
claude plugin install codex-images@codex-images
Restart Claude Code so the skill is picked up.
Auto-triggered — just describe what you're building. Examples that fire the skill:
<img src="/hero.png"> is broken, fix it."Manual — invoke explicitly:
/codex-images
…then describe what you want. The skill walks through context analysis, prompt construction, and file wiring.
Drop reference images on disk under your project root (e.g. ./refs/style.png) and mention them in the request. The skill instructs Codex to read them and condition the generation on style/palette/logo/likeness.
The skill's prompt to Codex is locked down so Codex doesn't slip into agent mode:
MIT — see LICENSE.
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.
npx claudepluginhub jandersoncrb/codex-images --plugin codex-imagesComprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.