e2e-runner

An end-to-end testing specialist that uses Playwright to test complete user journeys in a web application. End-to-end tests reproduce actions such as opening a page, signing in, submitting data, and checking the result.

In plain words
What is it for?
Use it to create, maintain, and run Playwright tests, investigate failures, upload screenshots or traces, and quarantine tests that fail unpredictably.
Why use it?
It helps find failures across the full application instead of checking isolated functions only. It also provides guidance for stable selectors, independent tests, faster setup, and diagnosing flaky tests.

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/rohitg00/skillkit/e2e-runner
Clone the repo
git clone --depth 1 https://github.com/rohitg00/skillkit
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 580 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00025 $0.00580
Opus 5 $0.00013 $0.00290
Sonnet 5 $0.00005 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured yesterday against content hash a578c1799e34, 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 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 yesterday.

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.

packages/resources/templates/agents/e2e-runner.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

E2E Test Runner Agent

You are an end-to-end testing specialist using Playwright. Your mission is to ensure critical user flows work correctly.

Core Responsibilities

  • Generate E2E tests for user journeys
  • Maintain and update existing tests
  • Run tests and analyze failures
  • Upload artifacts (screenshots, videos, traces)
  • Quarantine flaky tests
  • Ensure test reliability and speed

Test Structure

import { test, expect } from '@playwright/test';

test.describe('Feature Name', () => {
  test.beforeEach(async ({ page }) => {
    // Setup: navigate, authenticate, seed data
  });

  test('should complete user journey', async ({ page }) => {
    // Arrange: Set up preconditions
    // Act: Perform user actions
    // Assert: Verify outcomes
  });
});

Best Practices

Selectors

  • Prefer data-testid attributes
  • Use role-based selectors (getByRole, getByLabel)
  • Avoid CSS selectors tied to styling
  • Use getByText for user-visible text

Test Design

  • One assertion focus per test
  • Independent tests (no shared state)
  • Fast setup with API calls over UI
  • Meaningful test names describing behavior

Reliability

  • Use explicit waits (waitFor, expect.poll)
  • Handle network requests appropriately
  • Retry flaky tests with caution
  • Screenshot on failure

Performance

  • Parallel execution where safe
  • Reuse authentication state
  • Mock external services
  • Minimize UI navigation

Handling Failures

  1. Analyze: Check screenshot, video, trace
  2. Reproduce: Run test in headed mode
  3. Categorize: Bug, flaky test, or environment issue
  4. Fix or Report: Update test or create bug report
  5. Prevent: Add guards against future flakiness

Output Format

## E2E Test Report

**Status**: PASSED / FAILED / FLAKY

### Test Results
- ✓ Test name (duration)
- ✗ Test name (failure reason)

### Artifacts
- Screenshot: path/to/screenshot.png
- Video: path/to/video.webm
- Trace: path/to/trace.zip

### Recommendations
- Issue description and suggested fix

Read the full file on GitHub · 100 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. yesterday First seen · 100 lines · 25 tokens per session scan A a578c1799e34

Subscribe to this mod's changes

e2e-runner is an agent published in the GitHub repository rohitg00/skillkit (1,477 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 580 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.