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 skills/band-app/band/web-testnpx skills add band-app/band --skill web-testgit clone --depth 1 https://github.com/band-app/bandWrote 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/skills/band-app/band/web-test)<a href="https://agentmods.dev/skills/band-app/band/web-test"><img src="https://agentmods.dev/badge/skills/band-app/band/web-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 | $0.00077 | $0.00882 |
| Opus 5 | $0.00039 | $0.00441 |
| Sonnet 5 | $0.00015 | $0.00176 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
web-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 4d 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.
allowed-tools: Bash(pnpm dev:web*), Bash(lsof *), Bash(kill *), Bash(npx agent-browser *), Bash(agent-browser *), Bash(curl *), Read How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web App Testing with Screenshots
Test the Band web application by starting the dev server and using agent-browser to navigate pages and capture screenshots.
Steps
1. Start the dev server and detect the port
Run from the repo root (/Users/amirilovic/Projects/band). Do NOT kill any existing server — Vite will automatically pick another port if 3456 is occupied.
pnpm dev:web &
IMPORTANT: Read the Vite startup output and parse the actual port from the Local: line, e.g.:
Local: http://localhost:3456/
or if 3456 was busy:
Local: http://localhost:3457/
Use whatever port Vite reports for all subsequent steps. Do NOT hardcode 3456.
Wait for the server to be ready by polling the detected port:
for i in $(seq 1 30); do
curl -sf http://localhost:<PORT> > /dev/null 2>&1 && break
sleep 1
done
If it does not respond after 30 seconds, report an error and stop.
2. Navigate and take screenshots
Use agent-browser to open pages and capture screenshots. Always wait for the page to fully load before taking a screenshot.
Use the port detected in step 1 for all URLs.
Desktop viewport (default 1280x720):
agent-browser open http://localhost:<PORT> && agent-browser wait --load networkidle && agent-browser screenshot desktop-dashboard.png
Mobile viewport (375x812):
agent-browser set viewport 375 812
agent-browser open http://localhost:<PORT> && agent-browser wait --load networkidle && agent-browser screenshot mobile-dashboard.png
Key routes to test
Adjust based on what the user asks. Common routes:
| Route | Description |
|---|---|
/ |
Dashboard — project list |
/chat/<workspaceId> |
Workspace chat view |
/tasks |
Tasks page |
/cronjobs |
Cronjobs page |
To find valid workspace IDs for the chat route, first snapshot the dashboard and look for project links.
3. Interactive testing
If the user asks to test interactions (clicking, filling forms), use the standard agent-browser workflow:
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.
- 4d ago First seen · 112 lines · 77 tokens per session scan A 1cbb811a2e24
web-test is a skill published in the GitHub repository band-app/band (5 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 882 once invoked, about $0.0004 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 skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…
web-browser
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.