24 plugins in our Design & Frontend shelf (Pixels, CSS and terminal UIs.), ordered by what we can actually measure: our editor's picks first, then GitHub stars (checked 2026-10-26). Archived repos go to the bottom.
Stars measure popularity, not quality or safety. We haven't installed or audited these; every description is the project's own. Read the code before you install anything. Paid placements never affect this order.
Most-starred right now: Remove AI Watermarks by wiltodelta.
Identify and remove AI watermarks and provenance metadata (Gemini and Veo marks, SynthID, C2PA, EXIF) in images and video you generated yourself, plus provenance metadata in audio.
★ 6,134 · by wiltodelta#2Manage image history in Codex desktop and Claude Desktop Code with on-demand image retrieval, pinned references, and search by description or feedback.
★ 532 · by chipfighter#3STOP UI SLOP. Gives Codex 800,000+ real web and iOS screens, a product-specific design contract, and a hard finish gate before generic UI ships; connect it at https://uizze.com.
★ 68 · by uizze#4Plug-and-play MCP that gives your coding agent UI superpowers: design references, intent routing and a static anti-slop gate, no API key.
★ 49 · by PyModel#5Interface understanding and design-system memory for Codex, Claude Code, Cursor, and MCP agents with UI audits, Tailwind token extraction, shadcn registry workflows, and a bundled Codex plugin.
★ 49 · by sarveshsea#6UI/UX design plugin for AI coding agents with product-flow routing, platform-native interface guidance, asset planning, and shipped-reference analysis before code.
★ 31 · by f0d010c#7Route image-generation prompts to 30+ models (DALL-E, Stable Diffusion, Flux, Midjourney, and more) through a single MCP interface. Install: `npm install -g prompt-to-asset`.
★ 24 · by MohamedAbdallah-14#813 skills for image, video, and audio generation using 100+ models - FLUX, Midjourney v7, Veo3, Kling 3.0, Suno, and HunyuanVideo via muapi.ai.
★ 23 · by SamurAIGPT#9Create and finish AI images and videos through Magic Hour's MCP or API with reusable media workflows, output review, and account-credit requirements.
★ 12 · by magichourhq#10Intent-driven workflow skills for coding agents: describe what done looks like, not the steps. Triage-first design keeps token costs low across design, TDD, debug, review, and release.
★ 12 · by ouonet#11Build and deploy serverless TypeScript on Val Town from Codex — hosted MCP server plus skills for HTTP vals, cron, SQLite, email, OAuth, and React UI.
★ 10 · by val-town#12Cross-agent UX and product-design marketplace with a root Codex collection plugin, five focused plugin bundles, and 137 Agent Skills for design review, accessibility, layout, interaction, cognition, and product polish.
★ 9 · by HDeibler#13Local Codex bridge for Antigravity desktop with setup checks, model limit summaries, DevTools UI automation, and safe project/chat handoff.
★ 5 · by comprono#14Read local images, videos, web pages, and Windows screenshots through Doubao, GLM, or Qwen-compatible vision APIs.
★ 4 · by ZXY1240#15macOS-only local camera plugin for explicit snapshots, streaming controls, and file-backed image input.
★ 3 · by zfifteen#16Settles CSS values, layout, and motion by eye: draws candidates that differ in one property side by side in the browser, then applies the one you pick to your code.
★ 3 · by Dessert99#17Agent Skills for Amazon sellers and advertisers — Ads audits, search-term mining, budget pacing, DSP and AMC, listings, images, repricing, FBA inbound, and profitability, through Kuudo's Amazon Ads and SP-API MCP servers.
★ 3 · by KuudoAI#18Generate and edit AI images, video, audio, and 3D on the WaveSpeed platform with a bundled MCP server and CLI skill, including live catalog search, local-file upload, and price quotes before running.
★ 3 · by WaveSpeedAI#19Generate and edit raster images through any OpenAI-compatible image API, with model discovery, reference-image editing, masks, and provider configuration support.
★ 2 · by zlsbksdxl#20Task-aware spec/react/flash working-contract plugin that fixes DeepSeek weak default reasoning inside Codex, with a measured BigCodeBench harness included.
★ 1 · by hccccc01333#21Create original anime reaction stickers with image-generated pose sheets, expressive timing, and looping GIF and MP4 exports.
★ 0 · by LIghtJUNction#22Eight skills that audit and fix image and video delivery for Core Web Vitals, plus Sirv image CDN, 360 spin, and AI Studio workflows.
★ 0 · by IgorVaryvoda#23Makes Xiaohongshu and X share-image sets that look native, with App Store poster layouts, real screenshots and app-UI mocks.
★ 0 · by jack-reson8#24Takes an app or product from idea to launch with phase gates for naming and domain checks, references, style frames, UI loop, GTM and shipping.
★ 0 · by jack-reson8