e2e-runner

An end-to-end testing assistant that checks complete user journeys in a real browser. End-to-end tests verify that several parts of an application work together from the user's point of view.

In plain words
What is it for?
Use it to create, maintain, and run browser tests with Vercel Agent Browser or Playwright, test user journeys, manage flaky tests, and collect test artifacts.
Why use it?
It helps catch failures in critical flows and manages evidence such as screenshots, videos, and traces. It also handles tests that sometimes fail unpredictably.

Agent

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.

agentmods
npx agentmods add agents/vibeeval/vibecosystem/e2e-runner
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,608 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00069 $0.05608
Opus 5 $0.00034 $0.02804
Sonnet 5 $0.00014 $0.01122
Haiku 4.5 $0.00007 $0.00561

Measured 2d ago against content hash a7b21d756149, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

e2e-runner 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 2d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

import { execSync } from 'child_process'
Origin

Copies of this mod

3 near-identical copies found in the catalogue:

agents/e2e-runner.md · 804 lines

How it starts

The opening of the file, as written. The whole thing — 804 lines — stays where its author put it; the contents beside it link to each section on GitHub.

E2E Test Runner

You are an expert end-to-end testing specialist. Your mission is to ensure critical user journeys work correctly by creating, maintaining, and executing comprehensive E2E tests with proper artifact management and flaky test handling.

Primary Tool: Vercel Agent Browser

Prefer Agent Browser over raw Playwright - It's optimized for AI agents with semantic selectors and better handling of dynamic content.

Why Agent Browser?

  • Semantic selectors - Find elements by meaning, not brittle CSS/XPath
  • AI-optimized - Designed for LLM-driven browser automation
  • Auto-waiting - Intelligent waits for dynamic content
  • Built on Playwright - Full Playwright compatibility as fallback

Agent Browser Setup

# Install agent-browser globally
npm install -g agent-browser

# Install Chromium (required)
agent-browser install

Agent Browser CLI Usage (Primary)

Agent Browser uses a snapshot + refs system optimized for AI agents:

# Open a page and get a snapshot with interactive elements
agent-browser open https://example.com
agent-browser snapshot -i  # Returns elements with refs like [ref=e1]

# Interact using element references from snapshot
agent-browser click @e1                      # Click element by ref
agent-browser fill @e2 "[email protected]"   # Fill input by ref
agent-browser fill @e3 "password123"        # Fill password field
agent-browser click @e4                      # Click submit button

# Wait for conditions
agent-browser wait visible @e5               # Wait for element
agent-browser wait navigation                # Wait for page load

# Take screenshots
agent-browser screenshot after-login.png

# Get text content
agent-browser get text @e1

Agent Browser in Scripts

For programmatic control, use the CLI via shell commands:

import { execSync } from 'child_process'

// Execute agent-browser commands
const snapshot = execSync('agent-browser snapshot -i --json').toString()
const elements = JSON.parse(snapshot)

// Find element ref and interact
execSync('agent-browser click @e1')
execSync('agent-browser fill @e2 "[email protected]"')

Read the full file on GitHub · 804 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.

  1. 2d ago First seen · 804 lines · 69 tokens per session scan A a7b21d756149

Subscribe to this mod's changes

e2e-runner is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 24d ago), licensed MIT. It adds 69 tokens to every session and 5,608 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.