macbeth: Instructions file for Claude Code

CLAUDE.md

macbeth CLAUDE.md is an instructions file for Claude Code from wende/macbeth. It costs 4,226 tokens per session, scanned A, original, MIT.

Repository instructions for Macbeth, a tool that automates native macOS applications through the operating system’s Accessibility API. It includes a Swift background service, a TypeScript client, and an MCP server for AI agents.

In plain words
What is it for?
Use them when building or testing Macbeth, changing its Swift daemon or TypeScript client, or working with its JSON-RPC protocol and MCP tools.
Why use it?
They explain how the components communicate and provide the commands for building and testing them. This helps developers work on the daemon, client, protocol, or agent interface without guessing the project layout.

Instructions file for Claude Code

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

This is wende/macbeth's own configuration. It tells Claude Code how to work on macbeth 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 macbeth configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wende/macbeth. 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/wende/macbeth/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/wende/macbeth

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 macbeth CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/wende/macbeth/claude-md"><img src="https://agentmods.dev/badge/instructions/wende/macbeth/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,226 This file is loaded in full into every session.
When invoked 4,226 The same file — it is already loaded in full.
Security scan A 0 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 $0.04226 $0.04226
Opus 5.5 $0.01690 $0.01690
Sonnet 5.5 $0.00845 $0.00845
Haiku 4.5 $0.00423 $0.00423

Measured 1mo ago against content hash 9ac5e141872f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

macbeth 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 1mo 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 · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 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 is Macbeth

Playwright-style automation framework for native macOS apps via the Accessibility API. A Swift daemon (macbethd) talks to apps through AX APIs, a TypeScript client communicates with it over JSON-RPC 2.0 on a Unix socket, and an MCP server exposes tools for LLM agents.

Build & Test Commands

# Swift daemon (universal binary → client/bin/macbethd)
./scripts/build-daemon.sh

# TypeScript client
cd client && npm run build        # compile once
cd client && npm run dev          # watch mode

# Tests
cd client && npm test             # vitest (single run)
cd client && npx vitest run src/__tests__/locator.test.ts  # single test file
cd daemon && swift test           # Swift tests

Architecture

TypeScript Client ←→ macbethd (Swift) ←→ macOS Accessibility API
       ↑
  MCP Server (for LLM agents)

Communication: JSON-RPC 2.0 over Unix domain socket (/tmp/macbeth-<uid>.sock), newline-delimited JSON framing.

Protocol schema: protocol/schema.ts is the canonical source of truth for all RPC types. Swift implements these manually.

Client (client/src/)

  • client.ts — MacbethClient (daemon lifecycle, RPC) and AppHandle (per-app API surface)
  • elements.ts — Locator class: chainable, immutable, lazy (no RPC until a terminal method like .click() or .fill())
  • rpc.ts — JSON-RPC client over Unix socket
  • daemon.ts — Auto-spawns and manages the daemon subprocess
  • mcp.ts — MCP server: registers the shared tool catalog over stdio
  • tools.ts — Shared MCP/CLI tool catalog (schemas + handlers)
  • cli.ts / cli-args.ts — CLI dispatch and argv parsing for the same catalog
  • applescript.ts, native-bridge.ts, shell.ts, shortcuts.ts — Utilities used by skills

Daemon (daemon/Sources/macbethd/)

  • AX/HandleTable.swift — Opaque element handles (h_0, h_1, ...) with 5-min idle TTL (60 min when pinned)
  • AX/AppConnection.swift — App connection with fuzzy name matching
  • AX/TreeWalker.swift + TreeSerializer.swift — Recursive AX tree traversal and output
  • AX/ElementQuery.swift — Resolves locator query paths to AX elements
  • Methods/ — One file per RPC method (Click, Fill, WaitFor, Screenshot, etc.)
  • JSONRPC/Dispatcher.swift — Routes incoming calls to method handlers
  • Transport/SocketServer.swift — Unix socket server
  • Logging/RequestLogger.swift — Per-RPC audit log (NDJSON, rotated) written to ~/Library/Caches/macbeth/logs/

Read the full file on GitHub · 300 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. 1mo ago Changed · +3 lines · +83 tokens per session 9ac5e141872f
  2. 2mo ago First seen · 297 lines · 4,143 tokens per session scan A 7703e3aca427

Subscribe to this mod's changes

macbeth CLAUDE.md is an instructions file published in the GitHub repository wende/macbeth (4 stars, last pushed 1mo ago), licensed MIT. It adds 4,226 tokens to every session, about $0.0169 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 2026-08-31.

Related

macbeth CLAUDE.md compared with instructions from other repositories

macbeth CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
macbeth CLAUDE.mdwende/macbethInstructions file41mo agoMITA4,226Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode