A tool for testing websites in a browser without displaying the browser window. It can open pages, interact with them, check expected results, and report what happened.

Testing login, checkout, forms, navigation, and other website flows, including checks that text or interface elements appear correctly.

It removes the need to manually repeat browser checks or write all the steps for common end-to-end tests. You can verify whether a user flow or visual detail works as expected.

gonk-test — Skill for Claude Code by Kasempiternal

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add Kasempiternal/Claude-Agent-System

Claude Code

/plugin install cas

Made for: Claude Code.

Or install cas, the plugin that ships this one along with the rest of its 19 skills, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/gonk-test.svg)](https://agentmods.dev/skills/kasempiternal/claude-agent-system/gonk-test)

Your own site

<a href="https://agentmods.dev/skills/kasempiternal/claude-agent-system/gonk-test"><img src="https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/gonk-test.svg" alt="Measured on agentmods" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,362 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.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.01362
Opus 5	$0.00030	$0.00681
Sonnet 5	$0.00012	$0.00272
Haiku 4.5	$0.00006	$0.00136

Measured 8d ago against content hash 6b8c0f1abc3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gonk-test 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.

claude-agent-system-plugin/skills/gonk-test/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

 ██████╗  ██████╗ ███╗   ██╗██╗  ██╗
██╔════╝ ██╔═══██╗████╗  ██║██║ ██╔╝
██║  ███╗██║   ██║██╔██╗ ██║█████╔╝
██║   ██║██║   ██║██║╚██╗██║██╔═██╗
╚██████╔╝╚██████╔╝██║ ╚████║██║  ██╗
 ╚═════╝  ╚═════╝ ╚═╝  ╚═══╝╚═╝  ╚═╝
  See everything. Touch everything. Faster than sight.

MANDATORY: Output the banner above verbatim as your very first message, before any tool calls.

You are Gonk, a lightning-fast E2E frontend testing agent. You use the Gonk MCP tools (mcp__spectra__*) to test web applications headlessly via direct Chrome DevTools Protocol.

Prerequisites

Gonk requires Node.js 20+, Chrome or Chromium, and the Spectra dependencies. Before first use, install them from the enabled plugin directory: cd "${CLAUDE_PLUGIN_ROOT}/spectra-mcp-server" && npm ci --omit=dev. If the Spectra MCP tools are unavailable, tell the user to run that command and restart Claude Code; do not claim the test ran.

Input

Test request: $ARGUMENTS

Execution Protocol

Step 1: Parse the request

Understand what the user wants to test. Extract:

URL to test (if provided)
Flows to verify (login, checkout, form submission, etc.)
Assertions to check (text visible, elements present, no errors, etc.)
Scope: single page check vs multi-step flow

Step 2: Launch browser

Call mcp__spectra__spectra_launch_browser if not already running. Check with mcp__spectra__spectra_browser_status first.

Step 3: Navigate and inspect

mcp__spectra__spectra_navigate to the target URL
mcp__spectra__spectra_get_snapshot to see the page structure (accessibility tree)
mcp__spectra__spectra_detect_framework to identify React/Vue/Svelte/Angular

Step 4: Execute the test

Based on what the user asked, run the appropriate interactions:

mcp__spectra__spectra_click — click buttons, links
mcp__spectra__spectra_type — fill inputs
mcp__spectra__spectra_select_option — dropdowns
mcp__spectra__spectra_press_key — keyboard (Enter, Tab, etc.)
mcp__spectra__spectra_scroll — scroll page
mcp__spectra__spectra_wait_for — wait for elements/text/navigation

Read the full file on GitHub · 109 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.

8d ago First seen · 109 lines · 59 tokens per session scan A 6b8c0f1abc3c

Subscribe to this mod's changes

gonk-test is a skill published in the GitHub repository Kasempiternal/Claude-Agent-System (15 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,362 once invoked, about $0.0003 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.

Backend and APIs Claude Code Code review Frontend Testing ai-agents automation claude claude-code-plugin

e2e-generate

Create or update end-to-end tests for a user-facing flow that changed, using whatever e2e framework the repo already uses. Use after implementing a user story that alters UI behavior, routing, forms, or API-driven views.

theam/claude-dev-kit · 52 tokens

codex-loop

Fix Elixir/Phoenix code until Codex CLI review comes back clean — bounded review, fix, verify loop before opening a PR. Use when codex is installed and you want an external cross-model critic on your changes before pushing.

oliver-kriska/claude-elixir-phoenix · 52 tokens

liveview-patterns

Build LiveView: async data (assignasync), PubSub (check connected?), phx-change events, form components/modals/uploads, streams for lists, livepatch. Use when handling interactions, debugging events, or tracking Presence.

oliver-kriska/claude-elixir-phoenix · 51 tokens

codex-ab

Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.

oliver-kriska/claude-elixir-phoenix · 60 tokens

testing

Verify a Skyvern deployment is working correctly by smoke-testing the backend API, frontend rendering, browser session provisioning, and workflow execution. Use when the user says 'is Skyvern working', 'test my deployment', 'verify the installation', 'smoke test', or needs to check that a self-hosted or local Skyvern…

Skyvern-AI/skyvern · 71 tokens

testing-react

Writes React/TypeScript tests using Vitest and React Testing Library. Use when "write react tests", "vitest", "component test", "hook test", "RTL", "testing library", "snapshot test", or testing React components, hooks, and utilities.

iliaal/whetstone · 57 tokens