agentmods.dev

lightscout-mcp: Instructions file for Claude Code

CLAUDE.md

lightscout-mcp CLAUDE.md is an instructions file for Claude Code from bobbyrgoldsmith/lightscout-mcp. It costs 2,431 tokens per session, scanned C, original, MIT.

Project instructions for LightScout MCP, a tool that checks website speed and other Core Web Vitals, which are measures of loading performance and page stability.

In plain words
What is it for?
They help with building the project, running its command-line checks, analyzing or comparing websites, crawling pages, and checking results against performance thresholds.
Why use it?
They give an agent the project's commands, architecture, and key design decisions in one reference. This reduces guesswork when building, running, or changing the project.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is bobbyrgoldsmith/lightscout-mcp's own configuration. It tells Claude Code how to work on lightscout-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lightscout-mcp configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/bobbyg/Documents/test-scout/lightscout-mcp/dist/index.js.

not rated 0repo 6mo ago C scan 2,431 tokens original MIT
View source ↗ bobbyrgoldsmith/lightscout-mcp testscout.dev
Reuse

Borrowing it

Nothing to install: this file belongs to bobbyrgoldsmith/lightscout-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bobbyrgoldsmith/lightscout-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/bobbyrgoldsmith/lightscout-mcp

Made for: Claude Code.

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 lightscout-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bobbyrgoldsmith/lightscout-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/bobbyrgoldsmith/lightscout-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/bobbyrgoldsmith/lightscout-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bobbyrgoldsmith/lightscout-mcp/claude-md/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.

agentmods 80×15 button for lightscout-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bobbyrgoldsmith/lightscout-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bobbyrgoldsmith/lightscout-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,431 This file is loaded in full into every session.
When invoked 2,431 The same file — it is already loaded in full.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02431 $0.02431
Opus 5 $0.01215 $0.01215
Sonnet 5 $0.00486 $0.00486
Haiku 4.5 $0.00243 $0.00243

Measured 8d ago against content hash d64352e19b14, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

lightscout-mcp CLAUDE.md scanned grade C with 2 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 8d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

macOS Finder creates duplicate dirs with spaces (`lighthouse 2/`, `sdk 2/`) in `node_modules` when browsing. These break `rm -rf` and `yarn install`. Root cause: Finder folder duplication on drag/view. Prevention: don't

Runs shell commandslowCapability

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

Replaced in-process `require("lighthouse/core/index.cjs")` + `chrome-launcher.launch()` with `child_process.execFile` spawning the Lighthouse CLI as a subprocess. The CLI manages its own Chrome lifecycle in an isolated N
CLAUDE.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — LightScout MCP

Overview

Dual-mode Core Web Vitals analysis powered by Lighthouse. First tool in the TestScout MCP Suite. Published as npm package lightscout-mcp.

Two entry points, same core logic:

  • lightscout-mcp → MCP server (AI tools: Claude Code, Cursor, Windsurf, n8n)
  • lightscout → CLI (CI/CD, shell scripts, non-AI users)

Commands

yarn build       # Build via tsup → dist/index.js + dist/cli.js (ESM)
yarn dev         # Build with watch mode
yarn clean       # Nuke node_modules (handles Finder artifacts with spaces)
yarn verify      # Check critical deps exist

CLI Usage

lightscout analyze <url> [--device mobile|desktop] [--categories perf,a11y]
lightscout compare <urlA> [urlB] [--device mobile|desktop]
lightscout crawl <url> [--device mobile|desktop] [--max-pages 20]
lightscout check <url> [--perf 90] [--lcp 2500] [--cls 0.1] [--tbt 300]
lightscout --help | --version

Architecture

  • src/index.ts — MCP server entry, registers 4 tools via @modelcontextprotocol/sdk 1.12.1
  • src/cli.ts — CLI entry, 4 subcommands, lightweight arg parsing, JSON to stdout
  • src/tools/analyze.ts — analyze_performance (single URL)
  • src/tools/compare.ts — compare_performance (two URLs or mobile vs desktop)
  • src/tools/check.ts — check_threshold (CI pass/fail)
  • src/tools/crawl.ts — crawl_site (site-wide audit: discover pages + parallel Lighthouse)
  • src/lib/lighthouse.ts — Subprocess launcher: spawns Lighthouse CLI, parses JSON. Semaphore (3 concurrent) prevents resource contention.
  • src/lib/crawler.ts — URL discovery: tries sitemap.xml first, falls back to BFS link crawling. Returns { urls, method }. Max 20 pages.
  • src/lib/scoring.ts — CWV thresholds + getRating() (ported from LightScout Chrome extension)
  • src/lib/types.ts — Shared TypeScript interfaces

Key Decisions

  • SDK pinned to 1.12.1 — v1.27.1 imports zod/v4 which causes module-loading hang in Node 22 (CJS shim deadlock on 27+ submodules). 1.12.1 uses zod v3 + ajv v6, loads fast.
  • Zod v3 for tool schemas — SDK 1.12.1's .tool() expects ZodRawShape, not raw JSON Schema.
  • Subprocess model — Lighthouse runs as a child process (execFile → node lighthouse/cli/index.js), avoiding ESM loader deadlocks on Node 22. The CLI manages its own Chrome lifecycle. Desktop mode uses --preset=desktop (auto-updated UA). Lighthouse must remain as a dependency for CLI binary resolution.
  • SDK + zod bundled — tsup inlines SDK + zod (~244KB) so server works from any CWD. Lighthouse stays external (large, spawned as subprocess).

Read the full file on GitHub · 141 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. 8d ago First seen · 141 lines · 2,431 tokens per session scan C d64352e19b14

Subscribe to this mod's changes

lightscout-mcp CLAUDE.md is an instructions file published in the GitHub repository bobbyrgoldsmith/lightscout-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 2,431 tokens to every session, about $0.0122 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Analytics and metricsFrontend
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens