visual

A command for testing a Qt/PySide6 desktop application, including its visible interface. Qt is a desktop UI framework, and PySide6 is its Python binding.

In plain words
What is it for?
Use it to launch a Qt app in a headless environment, interact with its interface, verify behavior, and produce a test report.
Why use it?
It checks the live application through screenshots, clicks, and text entry, so interface behavior can be tested without opening a display manually.

Command

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 commands/l3digitalnet/claude-code-plugins/visual
Clone the repo
git clone --depth 1 https://github.com/L3DigitalNet/Claude-Code-Plugins
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,046 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 $0.00040 $0.01046
Opus 5 $0.00020 $0.00523
Sonnet 5 $0.00008 $0.00209
Haiku 4.5 $0.00004 $0.00105

Measured yesterday against content hash 0ef954ff4752, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visual 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.

plugins/qt-suite/commands/visual.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/qt-suite:visual — Headless GUI Testing

Launch the application headlessly and run visual tests using the Qt Pilot MCP server. Claude interacts with the live UI, verifies behavior, and writes a test report.

Step 1: Prerequisites Check

Run the prerequisites check before attempting to launch:

bash "${CLAUDE_PLUGIN_ROOT}/scripts/check-prerequisites.sh"

If Xvfb is missing, stop and report the install instructions — do not proceed.

Step 2: Find App Entry Point

Determine the application entry point:

  1. If an argument was provided that looks like a file path (e.g., /qt-suite:visual src/main.py), use it.
  2. Read .qt-test.json — use app_entry field if set.
  3. If no config, search for common entry points:
    • Glob for main.py, app.py, __main__.py in project root and src/
    • Choose the one that imports QApplication (Grep for QApplication)
  4. Resolve to an absolute path.

Step 3: Check If App Is Already Running

Call the Qt Pilot get_app_status MCP tool. If running: true, attach to the existing session. If not running (or crashed), launch fresh.

Step 4: Launch the App

Call launch_app with the resolved entry point:

launch_app(script_path="/abs/path/to/main.py")

Or for module-based apps:

launch_app(module="myapp.main", working_dir="/abs/path/to/project")

Wait for success: true. If launch fails, call get_app_status to retrieve stderr output and report the error with the full stderr content — do not attempt workarounds.

Step 5: Discover the UI

Before testing, always discover available widgets:

find_widgets("*")        → lists all named widgets
list_actions()           → lists all menu/toolbar actions

If the argument provided describes a specific UI scenario (e.g., "test the file open dialog"), use list_all_widgets to discover the full hierarchy including unnamed elements.

Step 6: Execute the Test Scenario

If a scenario was provided in the argument, execute it. For example, if the user says /qt-suite:visual test the save workflow:

Read the full file on GitHub · 135 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 · 135 lines · 40 tokens per session scan A 0ef954ff4752

Subscribe to this mod's changes

visual is a command published in the GitHub repository L3DigitalNet/Claude-Code-Plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 1,046 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.