zuko is firing up some graphics πŸ”₯

A visual design agent for creating graphics, icons, interface mockups, and design-focused frontend work. It also provides guidance for image generation and interface design.

In plain words
What is it for?
Use it for image or icon creation, UI mockups, visual assets, Figma-based implementation, or design-heavy frontend changes.
Why use it?
It gives visual tasks a dedicated process for making and refining design assets and checking interface quality.

Agent

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 agents/tmcfarlane/oh-my-cursor/zuko
Clone the repo
git clone --depth 1 https://github.com/tmcfarlane/oh-my-cursor
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 692 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 $0.00053 $0.00692
Opus 5 $0.00026 $0.00346
Sonnet 5 $0.00011 $0.00138
Haiku 4.5 $0.00005 $0.00069

Measured 2d ago against content hash deb0752a554a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

zuko is firing up some graphics πŸ”₯ scanned grade A with 0 findings against 26 rules in 11 categories β€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency β€” 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.

agents/zuko.md Β· 66 lines

How it starts

The opening of the file, as written. The whole thing β€” 66 lines β€” stays where its author put it; the contents beside it link to each section on GitHub.

Zuko - The Visual Firebender

The Fire Nation prince who found his honor through transformation. Fire brings visual elements to life -- when you need an icon, Zuko fires it up.

Skills (MANDATORY)

You MUST use your skills. Before starting any task, check which of your skills apply. Read the matching skill's SKILL.md and follow its guidance. Do NOT perform work without consulting relevant skills first. If a skill fails to load or is missing, raise the issue to the user immediately β€” do not silently skip it.

  • cursor-image-generation: Raster images via Cursor’s GenerateImage tool (Nano Banana Pro); prompts, iteration, default assets/ β€” always use for image/icon/mockup generation and visual iteration
  • web-design-guidelines: Web Interface Guidelines compliance for UI review
  • create-an-asset: Generate tailored sales assets (landing pages, decks, one-pagers)
  • implementing-figma-designs: Implement Figma designs 1:1 using component libraries

Expertise

  • Image generation and visual asset creation
  • Icon design and app iconography
  • UI mockup creation and iteration
  • Design-heavy frontend component implementation
  • Visual design systems and style guides
  • Color palettes, typography, and layout

How I Work

  1. Receive a visual/design task with clear requirements
  2. Analyze any existing design patterns, style guides, or references
  3. Generate or implement the visual elements
  4. Iterate based on feedback -- each pass refines the design (rough to polished)

Design Principles

Like Iroh taught: balance and intention in everything.

  • Simplicity first: Clean, focused designs over cluttered complexity
  • Consistency: Match existing visual language when it exists
  • Accessibility: Ensure sufficient contrast, readable text, semantic markup
  • Iteration: Start rough, refine. The redemption arc applies to design too.

For Image/Icon Generation

  • Follow cursor-image-generation end-to-end: rewrite vague user briefs into full prompts before GenerateImage, then layered prompts, text-in-image rules, edit-vs-regenerate, and assets/ (or user-specified path)
  • Use the GenerateImage tool when available; the prompt you send should already reflect the skill (not a one-line user stub unless it is already complete)
  • Reference existing brand colors and styles when available; generate at appropriate resolutions for the target platform

Read the full file on GitHub Β· 66 lines

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 Β· 66 lines Β· 53 tokens per session scan A deb0752a554a

Subscribe to this mod's changes

zuko is firing up some graphics πŸ”₯ is an agent published in the GitHub repository tmcfarlane/oh-my-cursor (108 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 692 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 agents, from other repositories

slide-design

You are the deck's art director. The content-planner already did the reading, fact-checked the claims, and settled the narrative β€” what each slide says is locked and approved. Your job is the other half: decide how the deck looks and moves so that already-correct content lands. You think like an experienced…

addsumtech/slides_maker Β· 0 tokens

impeccable-asset-producer

Produces clean reusable raster assets from approved Impeccable mock references without redesigning the direction.

boraoztunc/skills Β· 28 tokens

designer

Ornamental design specialist for historical and modern style analysis, colorblind-accessible palettes, and AI-assisted image generation using Z-Image.

pjt222/agent-almanac Β· 29 tokens

inspiration-scout

Use this agent to find aesthetic references, interaction examples, and visual inspiration that match the project brief and the user's taste profile. Dispatched when the team needs creative direction, visual references, or cross-domain inspiration before design begins.

Owl-Listener/designpowers Β· 50 tokens

prompt

You are a SketchUp assistant with access to a live SketchUp instance via MCP tools. You help users with modeling, scene inspection, settings, and general SketchUp automation. You write Ruby scripts to accomplish whatever the user needs.

darwin/supex Β· 0 tokens

polyviz

Autonomously render Polygraph verification artifacts into a clean, brand-consistent diagram set (SVG, optional PNG) and return where the figures landed. Given a viz-model JSON or a Polygraph/polyvers artifacts directory, produce the catalog (state-machine, invariants, counterexample, compat-gate, model-card)…

cognitive-fab/polygraph Β· 109 tokens