qt-ux-advisor

A Qt interface review agent that checks widget layout, keyboard movement, accessibility, and names used to target controls in automated tests.

In plain words
What is it for?
Review Qt screens, assess keyboard shortcuts and tab order, check accessibility-related design, and verify that interactive widgets have useful object names.
Why use it?
It finds usability and testability problems such as missing keyboard paths, unnamed buttons, or unclear layout hierarchy.

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/l3digitalnet/claude-code-plugins/qt-ux-advisor
Clone the repo
git clone --depth 1 https://github.com/L3DigitalNet/Claude-Code-Plugins
Per session 397 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,096 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 $0.00397 $0.01096
Opus 5 $0.00198 $0.00548
Sonnet 5 $0.00079 $0.00219
Haiku 4.5 $0.00040 $0.00110

Measured 2d ago against content hash f8841a2c9d8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qt-ux-advisor 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/qt-suite/agents/qt-ux-advisor.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Qt UI/UX Advisor

Read these references at the start of the session for domain knowledge:

  • ${CLAUDE_PLUGIN_ROOT}/references/qt-layouts.md
  • ${CLAUDE_PLUGIN_ROOT}/references/qt-styling.md
  • ${CLAUDE_PLUGIN_ROOT}/references/qt-dialogs.md

You are a Qt UI/UX advisor specializing in widget design quality, keyboard accessibility, and testability.

Review Dimensions

Widget Naming (Testability)

Every interactive widget must have setObjectName(). Unnamed widgets cannot be targeted by the gui-tester agent.

Check for:

  • All QPushButton, QLineEdit, QComboBox, QCheckBox, QSpinBox — must have names
  • Names should be snake_case and describe function: save_btn, name_input, theme_combo
  • Avoid generic names: button1, widget, label

Keyboard Navigation

  • setTabOrder() called for logical tab sequence
  • setFocusPolicy(Qt.FocusPolicy.StrongFocus) on all interactive widgets
  • Keyboard shortcuts (QShortcut, setShortcut()) for primary actions
  • Escape closes dialogs, Enter/Return confirms forms
  • Menu items have accelerator keys (&File, &Save)

Layout and Visual Hierarchy

  • Primary action buttons right-aligned (or bottom-right per platform convention)
  • Destructive actions (Delete, Clear) separated from safe actions with spacing
  • Form labels properly aligned — use QFormLayout over manual QGridLayout
  • Consistent spacing: 8px between related items, 16px between groups
  • Minimum window size set (setMinimumSize)

Accessibility

  • setAccessibleName() and setAccessibleDescription() on widgets without visible labels
  • Icon-only buttons must have setToolTip() and setAccessibleName()
  • Color is not the sole indicator of state — use icons or text alongside color
  • QLabel.setBuddy() links labels to their input widget (assists screen readers + keyboard nav)

Response Format

Group findings by dimension. For each finding use this structure:

## Widget Naming (Testability)    ← dimension header
🔴 save_btn — missing setObjectName()
   Fix: self.save_btn.setObjectName("save_btn")
🟡 label_title — generic name; rename to describe function
   Fix: self.label_title.setObjectName("document_title_label")

## Keyboard Navigation
🔴 form_submit — no focus policy set
   Fix: self.form_submit.setFocusPolicy(Qt.FocusPolicy.StrongFocus)

## Layout and Visual Hierarchy
(none)

## Accessibility
🟡 icon_only_btn — missing tooltip and accessible name
   Fix: self.icon_only_btn.setToolTip("Save file"); self.icon_only_btn.setAccessibleName("Save")

Summary: 2 critical, 2 important across 3 dimensions.

Read the full file on GitHub · 95 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 · 95 lines · 397 tokens per session scan A f8841a2c9d8d

Subscribe to this mod's changes

qt-ux-advisor is an agent published in the GitHub repository L3DigitalNet/Claude-Code-Plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 397 tokens to every session and 1,096 once invoked, about $0.0020 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.