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.
npx agentmods add instructions/fastslack/mtw-e2e-runner/claude-mdgit clone --depth 1 https://github.com/fastslack/mtw-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/instructions/fastslack/mtw-e2e-runner/claude-md)<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>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 | $0.02828 | $0.02828 |
| Opus 5 | $0.01414 | $0.01414 |
| Sonnet 5 | $0.00566 | $0.00566 |
| Haiku 4.5 | $0.00283 | $0.00283 |
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.
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, genericcdp,lightpanda(Zig),obscura(Rust+V8), orsteel. Defaultautoprobes endpoints and picks per pool.pool startuses 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
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.
- 3d ago First seen · 153 lines · 2,828 tokens per session scan A 93550eebf878
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.
Other instructions, from other repositories
cloakbrowser-mcp AGENTS.md
Instructions for swimmwatch/cloakbrowser-mcp, covering agents.md, about the project, golden rules, project layout and daily commands.
HeadlessX AGENTS.md
AGENTS.md instructions for saifyxpro/HeadlessX, covering agents.md — headlessx monorepo guide, project overview, repository structure, app / package purposes and tech stack.
cloakbrowser-mcp copilot-instructions.md
Instructions for swimmwatch/cloakbrowser-mcp: Follow AGENTS.md for project-wide coding, testing, documentation, changelog, and commit rules.
browser-agent AGENTS.md
Instructions for uiuing/browser-agent, covering agents.md — guide for ai coding agents, setup & commands, tests — run these before claiming done, repository layout and architecture invariants (do not break these).
browsercontrol AGENTS.md
Instructions for adityasasidhar/browsercontrol, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing & tool changes.
ndb-core e2e-tests.instructions.md
Instructions for Aam-Digital/ndb-core, covering e2e testing patterns (playwright), imports, loading the app, test data generators and clock and dates.