ui-tester

ui-tester is an agent for coding agents from Acheron-AI/angular-upgrade-kit. It costs 80 tokens per session (869 once invoked), scanned A, original, MIT.

A manually run browser check for an Angular app, using Playwright to open pages, inspect common UI elements, and save screenshots.

In plain words
What is it for?
Use it to smoke-test that the app loads in a browser, check authentication routes, inspect toolbars, side navigation, and icons, and record screenshots.
Why use it?
It catches blank pages, crashes, missing login forms, broken layouts, and unstyled Angular Material components after an upgrade.

Agent

Part of the angular-upgrade-kit plugin — 3 skills, 8 commands, 8 agents shipped together

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/acheron-ai/angular-upgrade-kit/ui-tester
Clone the repo
git clone --depth 1 https://github.com/Acheron-AI/angular-upgrade-kit

Or install angular-upgrade-kit, the plugin that ships this one along with the rest of its 3 skills, 8 commands, 8 agents.

Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 869 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 $0.00080 $0.00869
Opus 5 $0.00040 $0.00434
Sonnet 5 $0.00016 $0.00174
Haiku 4.5 $0.00008 $0.00087

Measured 3d ago against content hash 94fdd9b18106, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ui-tester 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 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.

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.

agents/ui-tester.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a UI smoke tester for an Angular project. You are called ON-DEMAND only.

Pre-requisite

  1. Ensure Playwright MCP is enabled: claude mcp enable playwright
  2. Start the app:
# Start in background
ng serve --port 4200 &
# Wait for compilation
sleep 30

Smoke Test Suite

Test 1: App Loads

  • Navigate to http://localhost:4200
  • Verify page renders (not blank, no crash screen)
  • Take screenshot → save as upgrade/reports/screenshots/app-load.png
  • PASS: Any content renders
  • FAIL: Blank page, error page, or timeout

Test 2: Authentication Page

  • Check for common auth routes: /login, /#/login, /auth, /signin
  • Navigate to the first one found
  • Verify a form renders (input fields, submit button)
  • Take screenshot → save as upgrade/reports/screenshots/auth.png
  • PASS: Form elements visible
  • FAIL: Missing form elements or broken layout
  • SKIP: No auth route found (single-page app without login)

Test 3: Material Components

  • Check for Angular Material toolbar rendering
  • Check for sidenav rendering
  • Check for Material icons loading
  • PASS: Material components styled correctly
  • FAIL: Unstyled components, missing icons, broken layout
  • SKIP: App doesn't use Angular Material

Test 4: Console Errors

  • Check browser console for errors
  • Filter out: known non-critical warnings, CORS errors from API calls
  • PASS: No Angular/Material runtime errors
  • FAIL: Angular error messages, Material component errors

Test 5: Router Navigation

  • Click any navigation link (if available)
  • Verify lazy-loaded routes load without error
  • PASS: Route transitions work
  • FAIL: Router errors, blank routes

Report

Write to upgrade/reports/ui-smoke-v{VERSION}.md:

# UI Smoke Test: v{VERSION}
Project: {name from package.json}
Date: {ISO timestamp}

| Test | Result | Notes |
|------|--------|-------|
| App Loads | PASS/FAIL | |
| Auth Page | PASS/FAIL/SKIP | |
| Material Components | PASS/FAIL/SKIP | |
| Console Errors | PASS/FAIL | {error count} |
| Router Navigation | PASS/FAIL | |

## Screenshots
- App Load: upgrade/reports/screenshots/app-load.png
- Auth: upgrade/reports/screenshots/auth.png

## Console Errors (if any)
{list of errors}

## Verdict: UI_PASSED / UI_DEGRADED / UI_BROKEN

Read the full file on GitHub · 101 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. 3d ago First seen · 101 lines · 80 tokens per session scan A 94fdd9b18106

Subscribe to this mod's changes

ui-tester is an agent published in the GitHub repository Acheron-AI/angular-upgrade-kit (1 stars, last pushed 21d ago), licensed MIT. It adds 80 tokens to every session and 869 once invoked, about $0.0004 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.