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 agents/acheron-ai/angular-upgrade-kit/ui-testergit clone --depth 1 https://github.com/Acheron-AI/angular-upgrade-kitWhat 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 | $0.00080 | $0.00869 |
| Opus 5 | $0.00040 | $0.00434 |
| Sonnet 5 | $0.00016 | $0.00174 |
| Haiku 4.5 | $0.00008 | $0.00087 |
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.
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
- Ensure Playwright MCP is enabled:
claude mcp enable playwright - 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
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 · 101 lines · 80 tokens per session scan A 94fdd9b18106
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.
Other agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
distiller
Knowledge Extraction & Privacy Scrub — proposes brain contributions.
Code
Autonomous task implementation on feature branch. Implements, tests, and commits.
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
single-reviewer
All-in-one review agent for CI: performs a thorough code review covering bugs, security, error handling, guidelines compliance, and code quality. Used by --single mode for cost-effective reviews.
mcp
The page outline agents read for line offsets, the in-browser WebMCP bridge and when to run it yourself, the rate limits, and how the surfaces are tested.