| name | screenshot |
| description | Take visual verification screenshots using agent-browser. Use for UI verification. |
| disable-model-invocation | true |
| allowed-tools | Read, Write, Bash |
Visual Verification Screenshots
Capture and document UI implementations using agent-browser for visual verification.
Prerequisites
Ensure agent-browser is installed and dev server is running:
cd frontend
pnpm exec agent-browser install
pnpm run dev
Step 1: Navigate to Page
cd frontend
pnpm exec agent-browser open http://localhost:3000/<page>
Common pages:
/ - Home page
/dashboard - Dashboard (if exists)
- Custom routes as specified
Step 2: Get Interactive Elements (Optional)
To find clickable elements:
pnpm exec agent-browser snapshot --interactive --compact
Returns element references like @e5 for clicking.
Step 3: Interact (If Needed)
pnpm exec agent-browser click @e5
pnpm exec agent-browser click "Button Text"
sleep 1
Step 4: Take Screenshot
pnpm exec agent-browser screenshot frontend/.dev-screenshots/<name>.png
pnpm exec agent-browser screenshot frontend/.dev-screenshots/<name>.png --full
Naming Convention
| Pattern | Example |
|---|
<feature>-<view>.png | inbox-overview.png |
<feature>-<state>.png | decision-loading.png |
<date>-<feature>.png | 2026-01-21-header.png |
Step 5: Update Gallery
After taking screenshots, update the HTML gallery:
File: frontend/.dev-screenshots/index.html
Add new screenshot card:
<article class="screenshot-card">
<div class="screenshot-header">
<span class="screenshot-title">N. Feature Name</span>
<span class="screenshot-date">filename.png</span>
</div>
<img src="filename.png" alt="Description" class="screenshot-img" onclick="openLightbox(this.src)">
<div class="screenshot-footer">
<ul>
<li>Verified element 1</li>
<li>Verified element 2</li>
</ul>
</div>
</article>
Step 6: View Gallery
Open in browser:
file://[project-path]/frontend/.dev-screenshots/index.html
Or use VS Code Live Server.
Quick Workflow (Copy-Paste)
cd frontend
pnpm exec agent-browser open http://localhost:3000/
pnpm exec agent-browser snapshot --interactive --compact
pnpm exec agent-browser screenshot .dev-screenshots/homepage.png --full
Output Report
After capturing screenshots, provide:
## Screenshots Captured
**Page:** [URL]
**Screenshots:**
- `filename.png` - [Description]
### Verified Elements
- [ ] Element 1 matches PRD
- [ ] Element 2 matches PRD
### Gallery Link
[file://.../.dev-screenshots/index.html]
Notes
- Screenshots are gitignored (
.dev-screenshots/)
- Always update gallery HTML after new captures
- Use
--full flag for full page captures
- Reference PRD for verification checklist
- Link screenshots in chat for user review
- ALWAYS ask user before taking screenshots