macos-mcp: Instructions file for Claude Code

CLAUDE.md

macos-mcp CLAUDE.md is an instructions file for Claude Code from krmj22/macos-mcp. It costs 2,310 tokens per session, scanned A, original, MIT.

Instructions for a local bridge that lets Claude work with six macOS apps: Reminders, Calendar, Notes, Mail, Messages, and Contacts.

In plain words
What is it for?
Use it when developing, testing, releasing, or troubleshooting the macOS app bridge and its publishing workflow.
Why use it?
It documents how the project works and warns developers that certain changes merged into its main branch automatically publish a public package.

Instructions file for Claude Code

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

This is krmj22/macos-mcp's own configuration. It tells Claude Code how to work on macos-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-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to krmj22/macos-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/krmj22/macos-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/krmj22/macos-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-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/krmj22/macos-mcp/claude-md.svg)](https://agentmods.dev/instructions/krmj22/macos-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/krmj22/macos-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/krmj22/macos-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,310 This file is loaded in full into every session.
When invoked 2,310 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 $0.02310 $0.02310
Opus 5 $0.01155 $0.01155
Sonnet 5 $0.00462 $0.00462
Haiku 4.5 $0.00231 $0.00231

Measured 6d ago against content hash da5b1dc6d40a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

macos-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 6d 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 · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Local MCP server bridging Claude to six macOS apps (Reminders, Calendar, Notes, Mail, Messages, Contacts). The user's data is the truth: if Mail.app shows 7 messages, this server returns 7. Any discrepancy with the native app is a bug.

⛔ MERGING TO main PUBLISHES A PUBLIC NPM PACKAGE

This repo is publish-on-merge. .github/workflows/ci.yml runs semantic-release on every push to main, which publishes to npm as mcp-macos and cuts a GitHub release. That is a public, outward-facing act and it is not cleanly reversible — npm restricts unpublish after 72 hours.

So merging a PR here is not the same class of action as merging a PR in any other repo on this machine. It is a release.

  • fix: / feat: / perf: on main → a real npm publish.
  • docs: / chore: / style: / refactor: / test: on main → CI runs, nothing publishes.
  • ⚠️ Exception: a BREAKING CHANGE: footer publishes a MAJOR from any commit type, docs: included, and a revert: publishes a patch. Verified at source in the installed @semantic-release/[email protected] lib/default-release-rules.js — that file is the authority, not this list.
  • pnpm release:preview dry-runs it and prints the next version before you commit to anything.

Rules for any agent, and especially for an unattended one:

  1. Never merge a fix:/feat:/perf: PR here without Kyle saying so in that session. A general instruction to "get everything back on main" or "clean up the branches" is NOT that authorization — those sweeps are written for repos where a merge is recoverable, and here it is a publish.
  2. A PR held for release timing is left as a DRAFT on purpose. Do not mark it ready to clear a queue. A deliberate hold is marked on four surfaces — draft flag, a [HELD — DO NOT MERGE: ...] title prefix, a blockquoted notice as the first block of the body, and a do-not-merge:publishes-npm label. The title prefix matters most: a sweep's inventory pass reads titles, not bodies. Set all four when you park one.
  3. Doc-only changes are free — commit them normally.

Read the full file on GitHub · 163 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. 6d ago First seen · 163 lines · 2,310 tokens per session scan A da5b1dc6d40a

Subscribe to this mod's changes

macos-mcp CLAUDE.md is an instructions file published in the GitHub repository krmj22/macos-mcp (5 stars, last pushed 17d ago), licensed MIT. It adds 2,310 tokens to every session, about $0.0115 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 · 5,182 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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens