mac-control

mac-control is a skill for Claude Code, Codex from anmolol117/applescript-automation-mcp. It costs 160 tokens per session (1,107 once invoked), scanned A, original, MIT.

A Mac automation skill that lets the agent carry out supported actions on the user's computer, such as opening apps, playing music, sending messages, and managing notes or reminders.

In plain words
What is it for?
Use it to control apps and system settings, open URLs, get directions, handle messages or email, take screenshots, and manage the clipboard or volume.
Why use it?
It turns requests for Mac actions into completed actions instead of leaving the user to follow instructions manually.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to control apps and system settings, open URLs, get directions…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anmolol117/applescript-automation-mcp/mac-control
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add anmolol117/applescript-automation-mcp --skill mac-control
Clone the repo
git clone --depth 1 https://github.com/anmolol117/applescript-automation-mcp

Made for: Claude Code, Codex.

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 mac-control

README.md
[![agentmods](https://agentmods.dev/badge/skills/anmolol117/applescript-automation-mcp/mac-control.svg)](https://agentmods.dev/skills/anmolol117/applescript-automation-mcp/mac-control)
Your own site
<a href="https://agentmods.dev/skills/anmolol117/applescript-automation-mcp/mac-control"><img src="https://agentmods.dev/badge/skills/anmolol117/applescript-automation-mcp/mac-control.svg" alt="Measured on agentmods" height="20"></a>
Per session 160 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,107 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00160 $0.01107
Opus 5 $0.00080 $0.00553
Sonnet 5 $0.00032 $0.00221
Haiku 4.5 $0.00016 $0.00111

Measured 6d ago against content hash 9b8b01bb0994, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mac-control 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.

skills/mac-control/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mac Control

The user built the applescript-automation MCP server so requests get executed on their Mac, not explained. This skill covers how to use it well.

The core rule

If a request can be satisfied by an action on the Mac, take the action. Do not return a link to tap, a list of steps, or a suggestion to do it manually.

Describe instead of acting only when:

  • the user explicitly asks how rather than asking for the thing,
  • no tool here can express the action, or
  • the action is destructive or sends something irreversibly (see Confirmation).

After acting, confirm in one short line. Don't narrate the AppleScript.

Lookup vs. execution

Other connectors find things. This server does things. A request that needs both is one task, not two — never stop after the lookup.

Need Lookup Execute
Play a specific song Spotify connector search → track URI run_applescript play
Directions somewhere Places search → coordinates open_url maps
Message a person lookup_contact → handle send_imessage

Handing over a Spotify link and stopping is an incomplete answer.

Caveat: consumer connectors like Spotify require the user to opt in before first use in a session. Offer it, wait for the choice, then complete the chain. Once they've chosen it, don't ask again — go straight through on later requests.

Prefer run_applescript

The specialized wrappers are thin and several have misbehaved on this machine. run_applescript is the reliable path for anything expressible in AppleScript. Use a wrapper only when it does something AppleScript can't reach directly (screenshot, battery_status, get_clipboard, list_shortcuts).

Known-good patterns

Music — always Spotify, never the Music app:

tell application "Spotify"
	activate
	play track "spotify:track:<id>"
end tell

Pause / resume / skip: tell application "Spotify" to pause (or play, next track, previous track). Current track: tell application "Spotify" to return artist of current track & " — " & name of current track

Read the full file on GitHub · 125 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 · 125 lines · 160 tokens per session scan A 9b8b01bb0994

Subscribe to this mod's changes

mac-control is a skill published in the GitHub repository anmolol117/applescript-automation-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 160 tokens to every session and 1,107 once invoked, about $0.0008 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens