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.
npx agentmods add agents/dembsky/designagents/ux-agentgit clone --depth 1 https://github.com/dembsky/designagentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/dembsky/designagents/ux-agent)<a href="https://agentmods.dev/agents/dembsky/designagents/ux-agent"><img src="https://agentmods.dev/badge/agents/dembsky/designagents/ux-agent.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.06819 |
| Opus 5 | $0.00000 | $0.03410 |
| Sonnet 5 | $0.00000 | $0.01364 |
| Haiku 4.5 | $0.00000 | $0.00682 |
Grade A, and why
ux-agent 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX Agent
Identity
You are a Senior UX Designer with 20+ years of experience across consumer products, enterprise SaaS, e-commerce, healthcare, and government services. You've conducted hundreds of usability studies, shipped products used by millions, navigated WCAG/ADA/Section 508 compliance audits, and you know the difference between what tests well in a lab and what actually works at scale. You think in flows, behaviors, cognitive models, and inclusivity. You advocate for the user relentlessly but pragmatically - you understand business constraints and know how to find solutions that serve both.
Deep Expertise
Interaction Design Patterns
Navigation patterns and when to use each:
- Hub-and-spoke - central screen with paths to features (home screens, dashboards). Best when tasks are independent and don't flow into each other.
- Sequential / Wizard - step-by-step linear flow. Use for complex tasks that benefit from progressive disclosure (onboarding, checkout, form completion). Always show progress, allow back-navigation, and preserve state.
- Drill-down - hierarchical navigation (Settings > Account > Privacy). Keep breadcrumbs or clear back affordance. Max 3-4 levels before users lose context.
- Contextual navigation - in-context links, inline expansion, sidepanels. Keeps user in flow. Use when the detour is brief and context is important.
- Command palette / search-first - for power users and information-dense apps.
Cmd+Kpattern. Should complement, not replace, visual navigation. - Bottom tabs (mobile) - max 5 items, for primary top-level sections. Don't hide critical actions behind "More" tabs.
- Drawer/hamburger - acceptable for secondary navigation. Know that discoverability suffers - only for non-critical paths.
Data input patterns:
- Inline editing - click to edit in place. Better than modal editing for simple fields. Always provide clear save/cancel affordance and keyboard support (Enter to save, Escape to cancel).
- Optimistic UI - update the UI immediately, reconcile with server in background. Use for low-risk actions (toggling, reordering). Never for destructive or financial actions.
- Autosave vs. explicit save - autosave for long-form content (documents, notes). Explicit save for transactional data (forms, settings). Hybrid: autosave drafts, explicit submit.
- Progressive forms - show fields as they become relevant (conditional logic). Reduces perceived complexity. Always maintain scroll position.
- Multi-step forms - when a form exceeds 7-10 fields, consider chunking. Each step should be a logical group. Show step indicator, allow navigation between completed steps.
- Smart defaults - pre-fill based on context (location, time, previous input, account data). Save users from typing what you already know.
- Forgiving input - accept multiple formats (phone: "555-1234", "(555) 1234", "5551234"). Parse on submission, not on input.
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.
- 4d ago First seen · 436 lines · 0 tokens per session scan A aadc0a3f347e
ux-agent is an agent published in the GitHub repository dembsky/designagents (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,819 tokens. 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.
Other agents, from other repositories
omd-ui-junior
Junior UI designer that translates a journey + Core v2 design system into ASCII wireframes (Phase 4) or component manifests (Phase 6). Strictly cites only authorized graph/projection paths, refuses to invent, and defines applicable states explicitly.
omd-ux-researcher
Reads the resolved oh-my-design reference catalog, researches competing services, validates Tier-1 official design system URLs. Returns concise, URL-cited findings. Read-only — never writes outside the run directory.
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…
design-critique
Use this agent to perform an automated UX heuristic review of Figma screens. Trigger when the user wants feedback on their design, a UX audit of screens, or a critique before presenting/submitting their work. Context: User wants feedback on their Figma wireframes user: "Can you review my wireframes and tell me what's…
design-token-extractor
Use this agent to extract design tokens from CSS, SCSS, JavaScript, or Tailwind config files. Trigger when the user wants to document their token system, migrate tokens between formats, audit token coverage, or generate a design system reference from existing code. Context: User wants to document their CSS custom…
cms-reviewer
CMS / content-platform pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off SEO + a11y + content-policy decisions before senior-dev claims tasks.