browser-verifier

browser-verifier is an agent for Claude Code from Houseofmvps/ultraship. It costs 29 tokens per session (316 once invoked), scanned A, original, MIT.

A browser-testing agent that uses Playwright, a tool for controlling a real web browser, to check whether a running application works. It loads pages, checks browser errors, and inspects the page content.

In plain words
What is it for?
Use it to test the main page and other discoverable routes, record browser errors, and return a pass, fail, or skipped result when no development server is running.
Why use it?
A successful build does not guarantee that pages load correctly in a browser. This check can reveal broken routes, loading failures, and console errors before release.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the ultraship plugin — 45 skills, 16 commands, 13 agents, 3 hooks, 2 MCP servers shipped together

Good fit Use it to test the main page and other discoverable routes, record browser errors, and return a pass, fail, or skipped result when no development server is running.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/houseofmvps/ultraship/browser-verifier
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.

Clone the repo
git clone --depth 1 https://github.com/Houseofmvps/ultraship

Made for: Claude Code.

Or install ultraship, the plugin that ships this one along with the rest of its 45 skills, 16 commands, 13 agents, 3 hooks, 2 MCP servers.

Wrote 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.

agentmods badge for browser-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/houseofmvps/ultraship/browser-verifier.svg)](https://agentmods.dev/agents/houseofmvps/ultraship/browser-verifier)
Your own site
<a href="https://agentmods.dev/agents/houseofmvps/ultraship/browser-verifier"><img src="https://agentmods.dev/badge/agents/houseofmvps/ultraship/browser-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 316 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00029 $0.00316
Opus 5 $0.00015 $0.00158
Sonnet 5 $0.00006 $0.00063
Haiku 4.5 $0.00003 $0.00032

Measured 8d ago against content hash 35bf3842c466, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

browser-verifier 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 8d 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/browser-verifier.md · 45 lines

What it actually says

You are the Browser Verifier agent for Ultraship. Verify the application works in a real browser using Playwright MCP.

Steps

  1. Detect the app URL (check common dev server ports: 3000, 5173, 4321, 8080)
  2. Use Playwright MCP tools to:
    • Navigate to the main page (browser_navigate)
    • Wait for page load (browser_wait_for)
    • Check for console errors (browser_console_messages)
    • Take a snapshot (browser_snapshot)
    • Navigate to 2-3 additional pages if routes are discoverable
  3. Report PASS/FAIL based on whether pages load without errors

Output Format

Return results as a JSON code block:

{
  "category": "browser",
  "result": "PASS",
  "pages_tested": 3,
  "console_errors": [],
  "message": "All pages loaded without errors"
}

If no dev server is running:

{
  "category": "browser",
  "result": "SKIP",
  "message": "No running dev server detected. Start your dev server and re-run /ship."
}
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. 8d ago First seen · 45 lines · 29 tokens per session scan A 35bf3842c466

Subscribe to this mod's changes

browser-verifier is an agent published in the GitHub repository Houseofmvps/ultraship (121 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 316 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories

qa-tester

The QA Tester of the aSPARK team. Use in the Review phase (/demo-day) to test the running application hands-on in a real browser: verify every acceptance criterion from the spec, explore beyond the happy path, check console and network, and file reproducible bugs. Requires a browser integration (Claude in Chrome…

a-lottes/aSPARK · 79 tokens

visual-qa

Read-only. Browser-based QA via whichever backend capability detection found -- the project's existing Playwright setup, or a connected browser-automation MCP server (Chrome DevTools MCP or a generic Playwright MCP server) when Playwright isn't available at the project level. Runs existing Playwright tests (or drives…

Surjal/dev-agent · 116 tokens

dev-agent-visual-qa

Read-only. Browser-based QA using the project's existing Playwright setup -- runs existing Playwright tests, inspects screenshots/console/network evidence, checks functional flows, visual layout, responsive breakpoints, UX states, and basic accessibility. Only invoked when Playwright is genuinely available in the…

Surjal/dev-agent · 72 tokens

browser-tester

A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.

andrewcigan/vibe-dev-plugin · 76 tokens

ui-tester

ON-DEMAND browser smoke testing using Playwright MCP. This agent is NOT part of the automatic upgrade pipeline. Use it manually when you want to visually verify the app works after an upgrade. Triggers: "test the ui", "browser test", "smoke test", "playwright test", "check if app works in browser", "visual check"…

Acheron-AI/angular-upgrade-kit · 80 tokens

ui-tester

E2E browser testing specialist - writes persistent test files using Playwright MCP tools.

akaszubski/autonomous-dev · 20 tokens