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 commands/mdgrey33/claude_mind/ui-testgit clone --depth 1 https://github.com/MDGrey33/claude_mindWrote 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/commands/mdgrey33/claude_mind/ui-test)<a href="https://agentmods.dev/commands/mdgrey33/claude_mind/ui-test"><img src="https://agentmods.dev/badge/commands/mdgrey33/claude_mind/ui-test.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 | $0.00014 | $0.00877 |
| Opus 5 | $0.00007 | $0.00439 |
| Sonnet 5 | $0.00003 | $0.00175 |
| Haiku 4.5 | $0.00001 | $0.00088 |
Grade A, and why
ui-test scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
if ! curl -s "http://localhost:$BACKEND_PORT/health" > /dev/null 2>&1; then How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Test Command
Run UI testing: $ARGUMENTS
Process
- Identify Target - Parse what to test
- Locate Application - URL or local path
- Check Services - Verify backend/frontend are running
- Check Existing Tests - Review documentation
- Create/Update Docs - Document test cases
- Ask User - Execute tests?
- Run Tests - If confirmed, use Playwright
- Report - Present results
- Cleanup - Stop any auto-started services
Service Health Check (Step 3)
Before running UI tests, verify required services are running. Auto-start if needed.
Check and Start Services
# Check if backend is running (default port 3000)
BACKEND_PORT=${BACKEND_PORT:-3000}
if ! curl -s "http://localhost:$BACKEND_PORT/health" > /dev/null 2>&1; then
echo "Backend not running. Starting..."
# Try common start commands
if [ -f "package.json" ]; then
npm run dev &
BACKEND_PID=$!
echo "Started backend (PID: $BACKEND_PID)"
fi
# Wait for startup
sleep 5
fi
# Check if frontend is running (default port 5173 for Vite, 3001 for CRA)
FRONTEND_PORT=${FRONTEND_PORT:-5173}
if ! curl -s "http://localhost:$FRONTEND_PORT" > /dev/null 2>&1; then
echo "Frontend not running. Starting..."
if [ -d "frontend" ] && [ -f "frontend/package.json" ]; then
cd frontend && npm run dev &
FRONTEND_PID=$!
echo "Started frontend (PID: $FRONTEND_PID)"
cd ..
fi
sleep 5
fi
Health Check Requirements
Before proceeding with tests:
- Check if
http://localhost:3000/health(or configured backend URL) responds - Check if frontend dev server is accessible
- If services are down, attempt auto-start using project's package.json scripts
- Wait up to 30 seconds for services to become healthy
- Log clearly: "Starting backend server on port 3000..."
- Track PIDs of auto-started services for cleanup
Cleanup on Exit
After tests complete (success or failure):
# Kill any services we started
if [ -n "$BACKEND_PID" ]; then
kill $BACKEND_PID 2>/dev/null
echo "Stopped backend (PID: $BACKEND_PID)"
fi
if [ -n "$FRONTEND_PID" ]; then
kill $FRONTEND_PID 2>/dev/null
echo "Stopped frontend (PID: $FRONTEND_PID)"
fi
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.
- 3d ago First seen · 127 lines · 14 tokens per session scan A ca7cc454832d
ui-test is a command published in the GitHub repository MDGrey33/claude_mind (2 stars, last pushed 8mo ago), licensed MIT. It adds 14 tokens to every session and 877 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.
Other commands, from other repositories
e2e
使用 Playwright 对 Web UI 进行端到端测试(支持视频录制、Trace 录制、控制台/网络日志捕获).
verify
Run the right verification gates for what changed.
plan-spec
仅在人工明确安排 UI 自动化时,根据任务、产品规则或原型生成独立行为 Spec.
generate_application_test_plan
Khám phá ứng dụng web, sinh test plan và test scenarios. Hỗ trợ 2 mode — PLAN (chỉ test plan) và FULL (test plan + automation skeleton).
open
SoDam-Design-Kit open 대시보드 — 검증 이력·판정서·스크린샷을 브라우저로 열람 + 재검증.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.