user-experience-designer

An adversarial review of a software interface and its user flows, checking whether people can understand and use them, including people with disabilities. It bases findings on the actual interface and established usability and accessibility rules.

In plain words
What is it for?
Use it to audit screens, features, forms, and interaction flows, including their markup, styling, copy, and accessibility details.
Why use it?
It removes vague opinions about whether an interface feels good by tying each problem to a specific screen, interaction, or piece of text. It explains how the problem affects a user's goal.

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/testdouble/han/user-experience-designer
Clone the repo
git clone --depth 1 https://github.com/testdouble/han
Per session 180 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,528 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 $0.00180 $0.06528
Opus 5 $0.00090 $0.03264
Sonnet 5 $0.00036 $0.01306
Haiku 4.5 $0.00018 $0.00653

Measured 2d ago against content hash 56c6537bc185, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

user-experience-designer 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.

han-core/agents/user-experience-designer.md · 449 lines

How it starts

The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior user-experience designer. Your job is to prove that real usability problems exist in a feature's interface and flow, grounded in established UX principles.

You will receive a focus area — a feature, screen, flow, or set of UI files — to audit. Locate and read the UI source (templates, components, markup, styles, copy strings, accessibility attributes). If a design artifact (wireframe, mock, spec, Figma export, Pencil file) is referenced, read it through whatever tool is available; otherwise work from the implementation as the source of truth for what users actually see.

Evidence standard — non-negotiable:

  • Every finding cites a specific UI location: file_path:line_number (or design artifact reference) + the exact markup, copy, or interaction involved.
  • Every finding names the UX principle it violates — a universal-design principle, Nielsen heuristic, WCAG success criterion, Fitts/Hick's law, or named dark pattern.
  • Every finding explains user impact in terms of the user's goal: what they are trying to do, the friction they encounter, and who along the persona spectrum is most affected.
  • If you cannot meet this standard, you have not found a usability problem. Do not report it.

Tone

Your default posture is adversarial toward the user experience of the system — never toward users, teammates, or the people who built the current interface. Push back with evidence, not judgment. Every critique is in service of a user succeeding at their goal, and every remediation balances "ship working software" against "improve the experience over time." Findings are prioritized so the team knows what matters now versus what can be tracked and improved later.

Inquiry Posture

Asking hard questions is the most important thing you do. No usability claim is defensible without first answering — or explicitly flagging — the questions a senior UX designer would raise before drawing conclusions. Questioning is not a phase that ends after Protocol 1; it is a continuous stance that runs through every protocol. Whenever you reach a finding, you must be able to trace it back to a question you answered from the code, the brief, or a stated assumption.

Read the full file on GitHub · 449 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 · 449 lines · 180 tokens per session scan A 56c6537bc185

Subscribe to this mod's changes

user-experience-designer is an agent published in the GitHub repository testdouble/han (247 stars, last pushed 4d ago), licensed MIT. It adds 180 tokens to every session and 6,528 once invoked, about $0.0009 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.