macos-mail-mcp: Instructions file for Claude Code

CLAUDE.md

macos-mail-mcp CLAUDE.md is an instructions file for Claude Code from marius-cetanas/macos-mail-mcp. It costs 4,971 tokens per session, scanned A, original, MIT.

Project instructions for a tool that connects Claude to macOS Mail.app, Apple's built-in email application, through AppleScript.

In plain words
What is it for?
Use them when working on the macos-mail-mcp project, which manages email accounts and messages in Mail.app, including reading, searching, composing, moving, deleting, flags, and attachments.
Why use it?
They give the coding agent the project's overview, architecture, technology choices, and operating rules, so changes follow the repository's conventions.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PROJECT_DIR} variable. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is marius-cetanas/macos-mail-mcp's own configuration. It tells Claude Code how to work on macos-mail-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 macos-mail-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to marius-cetanas/macos-mail-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/marius-cetanas/macos-mail-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/marius-cetanas/macos-mail-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 macos-mail-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/marius-cetanas/macos-mail-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/marius-cetanas/macos-mail-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,971 This file is loaded in full into every session.
When invoked 4,971 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 $0.04971 $0.04971
Opus 5 $0.02485 $0.02485
Sonnet 5 $0.00994 $0.00994
Haiku 4.5 $0.00497 $0.00497

Measured 9d ago against content hash 3cc8f9e24caa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

macos-mail-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 9d 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 · 334 lines

How it starts

The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — macos-mail-mcp

Project Overview

MCP (Model Context Protocol) server that connects Claude to macOS Mail.app via AppleScript. Provides 20 tools across 4 domains for full email management: reading, searching, composing, flagging, moving, deleting, and attachment handling.

Works with any email account configured in Mail.app — iCloud, Gmail, Outlook/Exchange, Yahoo, Fastmail, custom IMAP/POP, etc. No code changes needed when adding new accounts; just configure them in Mail.app.

Operating layer

This repository governs itself: .portulan/ is a kind: repository Portulan workspace, which the boot skill finds automatically because it searches ${CLAUDE_PROJECT_DIR}/.portulan/. It is not part of the Sleepy Panda portfolio workspace.

  • .portulan/identity.md — what this repository is, the stack, the three-layer shape, and the glossary. Start here.
  • .portulan/gate-map.md — which actions are Auto, Propose, Gated, Prohibited. Merge, publishing a release, pushing a tag, and npm publish by hand are Gated: they need explicit approval, per action. No action is Prohibited.
  • .portulan/dod.md — when a change is done here, including the 100% coverage bar and the rule that a verdict must post-date the head it judges.
  • .portulan/principles.md — five principles, each naming the incident that produced it.
  • .portulan/handoffs/ — the session record, dated YYYY-MM-DD-{slug}.md. Every session ends with one; read the most recent before starting.

It declares tree: "../", so doctor lints the gate map's claims against this repository — it checks that the required status check verify is one a workflow here actually reports. Nothing in .portulan/ ships to npm; files: ["build"] governs the tarball.

Tech Stack

  • Runtime: Node.js 20+ (engines floor; CI builds and tests on 20, 22 and 24)
  • Language: TypeScript (ES2022, Node16 module resolution)
  • MCP SDK: @modelcontextprotocol/sdk v1.x (stdio transport)
  • Mail integration: AppleScript via osascript (execFile, not exec — prevents shell injection)
  • Validation: Zod schemas on all tool inputs
  • Testing: Vitest, mocked bridge — no real Mail.app needed. Coverage of src/ is gated at 100% (statements, branches, functions, lines) in vitest.config.ts, and CI runs test:coverage. The gate is the invariant; the raw test count is not tracked here because it goes stale on every change and nothing checks it.
  • The .applescript files are the exception, and it is a real one. That 100% covers src/**/*.ts only. Because the bridge is mocked, the AppleScript templates are text handed to a mock rather than code that runs — which is how a handler that threw on any emoji subject shipped unexercised, found by an outside contributor (#33) rather than by the suite. tests/bridge/escape-for-json.applescript.test.ts executes the escaping handler through osascript for real. It runs only on macOS and is skipped everywhere else, including CI, so those assertions run on a maintainer's machine and never in the merge gate. Run npm run test:coverage locally before touching anything under src/**/*.applescript; the runner cannot do it for you.

Read the full file on GitHub · 334 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. 9d ago First seen · 334 lines · 4,971 tokens per session scan A 3cc8f9e24caa

Subscribe to this mod's changes

macos-mail-mcp CLAUDE.md is an instructions file published in the GitHub repository marius-cetanas/macos-mail-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 4,971 tokens to every session, about $0.0249 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.

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