What is relay-inspect CLAUDE.md?

A CLAUDE.md instruction file for Relay Inspect, a bridge between AI coding agents and Chrome developer tools. It explains the project's architecture, technologies, files, and commands.

Understanding Relay Inspect, installing its dependencies, building and testing its TypeScript code, and maintaining its browser-inspection connection.

It gives the agent the repository context needed to make changes and follow the project's development workflow.

How samsolomon/relay-inspect configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to samsolomon/relay-inspect. 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/samsolomon/relay-inspect/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/samsolomon/relay-inspect

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/samsolomon/relay-inspect/claude-md/github.svg)](https://agentmods.dev/instructions/samsolomon/relay-inspect/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/samsolomon/relay-inspect/claude-md"><img src="https://agentmods.dev/badge/instructions/samsolomon/relay-inspect/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/samsolomon/relay-inspect/claude-md"><img src="https://agentmods.dev/badge/instructions/samsolomon/relay-inspect/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,042 This file is loaded in full into every session.

When invoked 1,042 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01042	$0.01042
Opus 5	$0.00521	$0.00521
Sonnet 5	$0.00208	$0.00208
Haiku 4.5	$0.00104	$0.00104

Measured 8d ago against content hash 93f552d7f37d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

relay-inspect CLAUDE.md 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

If `check_connection` returns `ECONNREFUSED`, Chrome's debugging port didn't bind. Common cause: Chrome was already running without `--remote-debugging-port`, so the flag was silently ignored. Verify with `curl -s http:/

CLAUDE.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Relay Inspect

An MCP server that bridges AI coding agents and Chrome DevTools Protocol, giving agents real-time visibility into console logs, network requests, DOM elements, and the ability to execute JavaScript in the browser.

Architecture

                                                    ┌─ Chrome (CDP over WebSocket)
AI Coding Agent  ←→  Relay Inspect (MCP over stdio) ─┤
                                                    └─ Dev Servers (child processes)

MCP server built with @modelcontextprotocol/sdk, communicates with the AI coding agent over stdio
Connects to Chrome via chrome-remote-interface on localhost:9222
Buffers console and network events continuously once connected
Stateless tools — each tool call returns current buffer contents or live queries
Design goal: enable a tight edit → hot-reload → verify loop. Every decision should make this cycle faster and more reliable

Tech Stack

TypeScript in strict mode, built with tsup. See package.json for dependencies.

Project Structure

relay-inspect/
├── src/
│   ├── index.ts              # Entry point — MCP server setup, tool registration, exit handlers
│   ├── cdp-client.ts         # Chrome connection, event buffering, reconnection, auto-launch integration
│   ├── chrome-launcher.ts    # Chrome path discovery, auto-launch, CDP readiness polling
│   ├── server-manager.ts     # Dev server lifecycle management (start/stop/logs)
│   ├── *.test.ts             # Test files (cdp-target-selection, circular-buffer, server-manager)
├── package.json
├── tsconfig.json
├── CLAUDE.md
└── README.md

Commands

Build: npm run build
Test: npm test
Dev: npm run dev or npx tsx src/index.ts

Connection Management

Lazy connect, no background timers — Don't connect at startup. ensureConnected() connects on first tool call. On disconnect, null out the client and let the next call reconnect. No auto-reconnect timers
Never cache WebSocket URLs — Always discover Chrome targets via HTTP (CDP.List()). Chrome WebSocket URLs change on restart; caching them causes silent failures
Buffers drain on read — get_console_logs and get_network_requests clear the buffer by default so the agent sees only new entries

Read the full file on GitHub · 95 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.

8d ago First seen · 95 lines · 1,042 tokens per session scan A 93f552d7f37d

Subscribe to this mod's changes

relay-inspect CLAUDE.md is an instructions file published in the GitHub repository samsolomon/relay-inspect (2 stars, last pushed 5mo ago), licensed MIT. It adds 1,042 tokens to every session, about $0.0052 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Browser automation

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

relay-inspect: Instructions file for Claude Code