banana-web

A tool for generating visual assets for websites, such as hero backgrounds, card images, banners, section dividers, and motion-design keyframes. It uses Gemini and considers whether the design is for a dark or light interface.

In plain words
What is it for?
Use it to create landing-page visuals, hero images, banners, section graphics, UI mockups, or motion keyframes.
Why use it?
It turns a short design brief into an image-generation setup that accounts for where the asset appears and where website text needs open space.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/agentic-dev3o/devx-plugins/banana-web
Any agent
npx skills add agentic-dev3o/devx-plugins --skill banana-web
Clone the repo
git clone --depth 1 https://github.com/agentic-dev3o/devx-plugins

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,021 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00070 $0.01021
Opus 5 $0.00035 $0.00511
Sonnet 5 $0.00014 $0.00204
Haiku 4.5 $0.00007 $0.00102

Measured 2d ago against content hash be559e131617, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

banana-web scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/nano-banana-ultimate/skills/banana-web/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Design Assets

Input: $ARGUMENTS (optional — asset type and visual description)

If $ARGUMENTS is provided, use it as the design brief and skip to prompt building. If empty, ask about the asset type and theme.

Requirements

Workflow

  1. Understand — Parse the user's request. Identify the asset type (hero, card, section divider, banner, motion keyframe), its placement context, and intended visual tone. Ask whether the asset targets dark mode or light mode if not specified. If the subject or intent is unclear, ask ONE clarifying question.
  2. Build prompt — Construct a detailed Gemini prompt using the Prompt Formula below. Ensure the prompt specifies negative space placement and focal point offset for headline overlay compatibility.
  3. Configure — Choose aspect ratio, resolution, and model based on the Asset Type Defaults table. Use defaults unless the user specifies otherwise.
  4. Generate — Run the script.
  5. Deliver — Report the saved file path. Do NOT read the image file back. Offer to iterate: adjust palette, composition, theme, or prompt.

Prompt Formula

Build every web design asset prompt using this structure:

[UI Element/Scene] + [Visual Hierarchy Direction] + [Theme Context: dark/light] + [Wide Cinematic Composition] + [Modern Digital Art / Gradient Mesh / 3D Abstract]

Rules

  • Positive framing: Describe what IS in the image, never what is absent.
  • Strong verb opener: Start with Design, Compose, Render, Create, Generate.
  • Background-first thinking: Generate assets that work as backgrounds — large negative space, non-centered focal point positioned to allow headline overlay.
  • Dark/light mode awareness: Always consider the target theme. Dark mode assets use deep bases (#0a0a0a to #1a1a2e) with luminous accents. Light mode assets use soft whites and pastels with subtle depth.
  • Modern aesthetics: Favor gradient meshes, abstract 3D shapes, glassmorphism elements, soft glows, and volumetric lighting.
  • Composition: Offset the focal point to one side or corner, leaving generous negative space for text content.

Read the full file on GitHub · 88 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 88 lines · 70 tokens per session scan A be559e131617

Subscribe to this mod's changes

banana-web is a skill published in the GitHub repository agentic-dev3o/devx-plugins (11 stars, last pushed 14d ago), licensed MIT. It adds 70 tokens to every session and 1,021 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens