claude-soul: Command for Claude Code

.claude/commands/ui-test.md

ui-test is a command for Claude Code from tomdwipo/claude-soul. It costs 0 tokens per session (1,929 once invoked), scanned A, original, MIT.

A command for visual testing of mobile app flows by comparing device screenshots with benchmark images. It uses ADB, the Android Debug Bridge, to tap, type, swipe, go back, wait, and launch apps according to a YAML test file.

In plain words
What is it for?
Use it to run named UI flows, perform their actions on an Android device, capture each screen, and compare the results against expected images.
Why use it?
It helps detect visual differences and broken screen flows without checking every screenshot manually.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is tomdwipo/claude-soul's own configuration. It tells Claude Code how to work on claude-soul itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-soul configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tomdwipo/claude-soul. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tomdwipo/claude-soul/main/.claude/commands/ui-test.md
Clone the repo
git clone --depth 1 https://github.com/tomdwipo/claude-soul

Made for: Claude Code.

Wrote 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.

agentmods badge for ui-test

README.md
[![agentmods](https://agentmods.dev/badge/commands/tomdwipo/claude-soul/ui-test.svg)](https://agentmods.dev/commands/tomdwipo/claude-soul/ui-test)
Your own site
<a href="https://agentmods.dev/commands/tomdwipo/claude-soul/ui-test"><img src="https://agentmods.dev/badge/commands/tomdwipo/claude-soul/ui-test.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,929 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.01929
Opus 5 $0.00000 $0.00964
Sonnet 5 $0.00000 $0.00386
Haiku 4.5 $0.00000 $0.00193

Measured 8d ago against content hash 9b1fb81b6810, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ui-test scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| **fetch_otp** | `- fetch_otp: {url: "https://...", phone: "<phone>"}` | Fetch OTP via curl, store in variable |
.claude/commands/ui-test.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Test — Screenshot Benchmark Comparison

Run visual UI tests by comparing device screenshots against benchmark images. Supports ADB actions (tap, type, swipe, back, wait, launch) to navigate through app flows.

Arguments

$ARGUMENTS is the flow name (e.g., login-flow), matching a YAML file in ui-tests/flows/.

Instructions

You are running an automated visual UI test. Follow these steps EXACTLY:

Phase 1: Load Test Spec

  1. Read the YAML file at ui-tests/flows/$ARGUMENTS.yaml
  2. Parse the flow name, description, default_diff_threshold, and list of screens
  3. If the file doesn't exist, tell the user and list available flows from ui-tests/flows/

Phase 2: Run Each Screen Test

For EACH screen in the screens list, do the following IN ORDER:

Step A: Execute Actions (if specified)

If the screen has an actions list, execute each action IN ORDER using ADB:

Action YAML ADB Command
tap - tap: {x: 360, y: 800} adb shell input tap 360 800
long_press - long_press: {x: 360, y: 800} adb shell input swipe 360 800 360 800 1000
type - type: "hello" adb shell input text "hello"
swipe - swipe: {x1: 360, y1: 1200, x2: 360, y2: 400} adb shell input swipe 360 1200 360 400 300
back - back adb shell input keyevent 4
home - home adb shell input keyevent 3
enter - enter adb shell input keyevent 66
wait - wait: 2000 sleep 2 (value is in milliseconds)
launch - launch: "com.example.app.dev/com.example.app.ui.MainActivity" adb shell am start -n <value>
clear_app - clear_app: "com.example.app.dev" adb shell pm clear <value>
hide_keyboard - hide_keyboard adb shell input keyevent 111
swipe_repeat - swipe_repeat: {x1: 360, y1: 1200, x2: 360, y2: 300, count: 50} Repeat swipe N times (200ms between each)
fetch_otp - fetch_otp: {url: "https://...", phone: "<phone>"} Fetch OTP via curl, store in variable
type_fetched_otp - type_fetched_otp Type the previously fetched OTP digits one by one

Read the full file on GitHub · 156 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. 8d ago First seen · 156 lines · 0 tokens per session scan A 9b1fb81b6810

Subscribe to this mod's changes

ui-test is a command published in the GitHub repository tomdwipo/claude-soul (24 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,929 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.