Borrowing it
Nothing to install: this file belongs to HabaAndrei/custom-chrome-dev-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.
curl -O https://raw.githubusercontent.com/HabaAndrei/custom-chrome-dev-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/HabaAndrei/custom-chrome-dev-mcpWrote 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/habaandrei/custom-chrome-dev-mcp/claude-md)<a href="https://agentmods.dev/instructions/habaandrei/custom-chrome-dev-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/habaandrei/custom-chrome-dev-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.
<a href="https://agentmods.dev/instructions/habaandrei/custom-chrome-dev-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/habaandrei/custom-chrome-dev-mcp/claude-md.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 | $0.01511 | $0.01511 |
| Opus 5.5 | $0.00604 | $0.00604 |
| Sonnet 5 | $0.00302 | $0.00302 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
custom-chrome-dev-mcp 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 today.
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 — 49 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.
What this is
A local-only MCP server (custom-chrome-dev-mcp) that drives the user's real Chrome browser via a companion MV3 extension, exposing 60 tools across navigation, tabs, perception, interaction, trusted input, observability, capture, and storage. Its entire premise is behaving like a human using the browser (trusted CDP input, real focus, real keystrokes) rather than firing synthetic DOM events — see README.md for the full rationale and tool reference.
Commands
npm test # offline lane only — the CI gate, no browser needed, <1s
npm run test:browser # browser lane — drives real Chrome
npm run test:all # both lanes
npm run test:list # list every suite/test without running
node test/run.mjs --grep=fill # filter by suite/test name substring
Running the browser lane requires freeing port 9876 first (pkill -f src/hub.js) and disconnecting any live MCP client, otherwise the client respawns the hub and the suite dies with EADDRINUSE. Then reload the extension in chrome://extensions so it connects to the test bridge instead of the real hub.
There is no separate lint/build step — npm test (the offline lane) is the fast correctness gate and should pass before any change is considered done.
Architecture
Transport chain: MCP client <-stdio-> bin/custom-chrome-dev-mcp.js <-> src/hub.js (ws://127.0.0.1:9876) <-> Chrome extension <-> active tab. The hub is a separate long-lived process (not inside the server) because multiple MCP sessions may each want the one browser socket; the first session spawns it detached, later sessions find it already listening. Each session connects as role:"mcp", the extension as role:"extension"; the hub multiplexes and re-tags message ids since they can collide across sessions.
The server and the extension are mirrored 1:1 by tool group. Every file in src/tools/ (schema + docs, registered via src/tools/index.js) has a same-named handler file in extension/src/handlers/ (implementation, dispatched via extension/src/handlers/index.js). Adding or changing a tool means touching exactly that pair — groups: navigation, tabs, perception, interaction, trustedInput (file: trusted-input.js), observability, capture, storage. The offline test suite asserts the two sides stay in lockstep (every schema has a handler and vice versa, no tool name claimed by two groups, every tool exercised by at least one test).
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.
- today Changed · +2 tokens per session 36cbc44e70e7
- yesterday First seen · 49 lines · 1,509 tokens per session scan A 378642501f5c
custom-chrome-dev-mcp CLAUDE.md is an instructions file published in the GitHub repository HabaAndrei/custom-chrome-dev-mcp (0 stars, last pushed today), licensed MIT. It adds 1,511 tokens to every session, about $0.0060 per session on Opus 5.5. 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 2026-09-27.
Other instructions, from other repositories
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).
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.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
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.