Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vibeeval/vibecosystemnpx agentmods add agents/vibeeval/vibecosystem/e2e-runnerWrote 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/agents/vibeeval/vibecosystem/e2e-runner)<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/e2e-runner"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/e2e-runner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/e2e-runner"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/e2e-runner.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00069 | $0.05608 |
| Opus 5.5 | $0.00028 | $0.02243 |
| Sonnet 5.5 | $0.00014 | $0.01122 |
| Haiku 4.5 | $0.00007 | $0.00561 |
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 1mo 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' Copies of this mod
2 near-identical copies found in the catalogue:
- e2e-runner — 95% identical, 6 lines differ
- e2e-runner — 92% identical, 54 lines differ
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]"')
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.
- 1mo ago First seen · 804 lines · 69 tokens per session scan A a7b21d756149
e2e-runner is an agent published in the GitHub repository vibeeval/vibecosystem (538 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 5,608 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other agents, from other repositories
gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
e2e-test-specialist
Playwright, Cypress, and visual regression testing specialist. Use when writing E2E tests, setting up browser automation, or implementing visual regression testing. Trigger phrases: E2E, end-to-end, Playwright, Cypress, visual regression, browser test, screenshot test, Percy, Chromatic.
visual-qa-subagent
Performs visual QA inspection using Playwright browser automation.
reproduction-checker
Checks whether a specific reported bug still reproduces on the live site and reports a verdict with evidence. Use during a Bug Shepherd triage run.
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…
orc-qa-validator
Executor role — drives a real browser via the agent-browser CLI (vercel-labs/agent-browser) to QA a running web application — golden path + edge cases — and writes an evidence packet (criterion-anchored annotated screenshots, a WebM recording, accessibility snapshots, browser console, network HAR, narrated steps…