mtw-e2e-runner CLAUDE.md

mtw-e2e-runner CLAUDE.md is an instructions file for coding agents from fastslack/mtw-e2e-runner. It costs 2,828 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for an end-to-end browser test runner. End-to-end tests check a complete user flow in a real browser, and these tests are written as JSON action sequences rather than JavaScript files.

In plain words
What is it for?
Use it when adding the runner to another project, creating its e2e/ test folder, or managing its browser test setup.
Why use it?
It gives an agent the project’s setup details, commands, and rules so it can install the runner and prepare browser tests consistently.

Instructions file

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 instructions/fastslack/mtw-e2e-runner/claude-md
Clone the repo
git clone --depth 1 https://github.com/fastslack/mtw-e2e-runner

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 mtw-e2e-runner CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fastslack/mtw-e2e-runner/claude-md.svg)](https://agentmods.dev/instructions/fastslack/mtw-e2e-runner/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/fastslack/mtw-e2e-runner/claude-md"><img src="https://agentmods.dev/badge/instructions/fastslack/mtw-e2e-runner/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,828 This file is loaded in full into every session.
When invoked 2,828 The same file — it is already loaded in full.
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 $0.02828 $0.02828
Opus 5 $0.01414 $0.01414
Sonnet 5 $0.00566 $0.00566
Haiku 4.5 $0.00283 $0.00283

Measured 3d ago against content hash 93550eebf878, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mtw-e2e-runner CLAUDE.md 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 3d 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.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

@matware/e2e-runner is a JSON-driven E2E test runner that executes browser tests in parallel against a configurable browser pool via Puppeteer. Tests are defined as JSON files containing sequential action arrays — no JavaScript test files.

  • Runtime: Node.js >= 20, ESM ("type": "module")
  • Dependencies: puppeteer-core (connects to remote browser), @modelcontextprotocol/sdk (MCP server), better-sqlite3 (dashboard DB)
  • Infrastructure: Multi-driver pool — browserless, generic cdp, lightpanda (Zig), obscura (Rust+V8), or steel. Default auto probes endpoints and picks per pool. pool start uses Docker Compose for browserless/lightpanda; Obscura ships as a single binary the user runs locally.

Commands

# Install dependencies
npm install

# Scaffold e2e/ directory in a consuming project
npx e2e-runner init

# Manage Chrome pool (requires Docker) — CLI only, NOT available via MCP
npx e2e-runner pool start      # spins up browserless/chrome container
npx e2e-runner pool stop
npx e2e-runner pool status     # also available as e2e_pool_status MCP tool

# Run tests
npx e2e-runner run --all                  # all suites in e2e/tests/
npx e2e-runner run --suite <name>         # single suite (matches with or without numeric prefix)
npx e2e-runner run --tests <file.json>    # specific JSON file
npx e2e-runner run --inline '<json>'      # inline JSON array

# Force a driver for the whole run (overrides per-test `driver` fields)
npx e2e-runner run --all --driver obscura
npx e2e-runner run --all --driver obscura --fallback-driver cdp

# List available suites
npx e2e-runner list

# Capture a screenshot of any URL (no test required)
npx e2e-runner capture <url>
npx e2e-runner capture <url> --full-page --selector ".loaded" --delay 2000 --filename my-capture.png

# Web dashboard
npx e2e-runner dashboard [--port 8484]

# Issue-to-test
npx e2e-runner issue <url>                # fetch and display
npx e2e-runner issue <url> --generate     # generate test via Claude API
npx e2e-runner issue <url> --verify       # generate + run + report
npx e2e-runner issue <url> --prompt       # output AI prompt as JSON
npx e2e-runner issue <url> --test-type api  # generate API tests instead of UI tests

Read the full file on GitHub · 153 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. 3d ago First seen · 153 lines · 2,828 tokens per session scan A 93550eebf878

Subscribe to this mod's changes

mtw-e2e-runner CLAUDE.md is an instructions file published in the GitHub repository fastslack/mtw-e2e-runner (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 2,828 tokens to every session, about $0.0141 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 2026-08-31.

Related

Other instructions, from other repositories