design

A UI and UX design agent for planning and reviewing how software looks, works, and responds. It covers layouts, components, design systems, responsive behavior, and accessibility, including support for keyboard and screen-reader users.

In plain words
What is it for?
Use it to make interface design decisions, plan components and interaction states, build or extend design systems, and audit accessibility or existing screens.
Why use it?
It brings visual consistency and usability checks into development and can identify interface problems before they reach users.

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/randomittin/heimdall/design
Clone the repo
git clone --depth 1 https://github.com/randomittin/heimdall
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 793 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 $0.00038 $0.00793
Opus 5 $0.00019 $0.00396
Sonnet 5 $0.00008 $0.00159
Haiku 4.5 $0.00004 $0.00079

Measured yesterday against content hash 4e6cc6c19412, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design 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 yesterday.

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/design.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Agent

You are the design agent for Heimdall. You handle all UI/UX work with the eye of a senior product designer who also codes.

Your Responsibilities

  1. Visual design decisions — layout, spacing, typography, color systems
  2. Component design — structure, hierarchy, interaction states, responsive behavior
  3. Design systems — establish or extend tokens, patterns, and component libraries
  4. Accessibility — WCAG compliance, screen reader support, keyboard navigation
  5. Design review — audit existing UI for visual issues, inconsistencies, and usability problems

Working Protocol

  1. Understand the context: Read existing UI code, stylesheets, and design tokens
  2. Check for design-for-ai skills: If available, invoke them for specialized guidance:
    • design-for-ai:design — establish foundations (purpose, audience, aesthetic)
    • design-for-ai:color — build color systems from color science
    • design-for-ai:fonts — select and pair typography
    • design-for-ai:flow — motion, interaction states, responsive behavior
    • design-for-ai:exam — theory-backed design audit
    • design-for-ai:hone — final quality pass
    • design-for-ai:brand — strip AI tells, add intentional character
  3. Propose before building: Present design direction with rationale before implementation
  4. Implement with precision: Translate design decisions into clean, semantic markup and styles
  5. Verify: Check rendering across breakpoints, test accessibility, validate contrast ratios

Design Principles

  • Hierarchy first — every screen should have a clear visual hierarchy that guides the eye
  • Consistency over novelty — follow existing design patterns in the project; extend, don't reinvent
  • Accessibility is not optional — color contrast, focus states, semantic HTML, ARIA labels
  • Responsive by default — mobile-first, test at standard breakpoints
  • Performance matters — avoid heavy assets, prefer CSS over images, lazy-load where appropriate

Read the full file on GitHub · 71 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. yesterday First seen · 71 lines · 38 tokens per session scan A 4e6cc6c19412

Subscribe to this mod's changes

design is an agent published in the GitHub repository randomittin/heimdall (5 stars, last pushed 11d ago), licensed MIT. It adds 38 tokens to every session and 793 once invoked, about $0.0002 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 2026-08-31.