app_control

app_control is a skill for Claude Code, Codex from frontier-ai-next/mgarlbot. It costs 13 tokens per session (535 once invoked), scanned A, original, MIT.

A set of instructions for opening, closing, and controlling applications on macOS, Apple's desktop operating system.

In plain words
What is it for?
Use it to launch apps, open files or folders, bring apps to the front, type text, press shortcuts, check whether an app is running, and quit it.
Why use it?
It removes the need to remember shell commands or AppleScript for routine app actions.

Skill for Claude CodeCodex

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

Good fit Use it to launch apps, open files or folders, bring apps to the front, type text, press shortcuts, check whether an app is running, and quit it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/frontier-ai-next/mgarlbot/app_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 frontier-ai-next/mgarlbot --skill app_control
Clone the repo
git clone --depth 1 https://github.com/frontier-ai-next/mgarlbot

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 app_control

README.md
[![agentmods](https://agentmods.dev/badge/skills/frontier-ai-next/mgarlbot/app_control.svg)](https://agentmods.dev/skills/frontier-ai-next/mgarlbot/app_control)
Your own site
<a href="https://agentmods.dev/skills/frontier-ai-next/mgarlbot/app_control"><img src="https://agentmods.dev/badge/skills/frontier-ai-next/mgarlbot/app_control.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 535 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 $0.00013 $0.00535
Opus 5 $0.00006 $0.00267
Sonnet 5 $0.00003 $0.00107
Haiku 4.5 $0.00001 $0.00053

Measured 8d ago against content hash 8fdf745a69db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

app_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 8d 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/app_control/SKILL.md · 105 lines

What it actually says

Application control (macOS)

Use shell and AppleScript to launch and control apps.

Open by app name

open -a "TextEdit"
open -a "Safari"
open -a "Calculator"
open -a "Cursor"
open -a "Terminal"
open -a "Finder"
open -a "Notes"

Open a file

Default app:

open /path/to/file.txt

Specific app:

open -a "TextEdit" /path/to/file.txt

URL:

open "https://example.com"

Editor with content

echo "content here" > /tmp/tempfile.txt && open -a "TextEdit" /tmp/tempfile.txt

Projects / folders

Open folder in Cursor:

open -a "Cursor" /path/to/project

Open in Finder:

open /path/to/folder

Quit

osascript -e 'quit app "TextEdit"'

Is it running?

pgrep -x "TextEdit" && echo "Running" || echo "Not running"

AppleScript (advanced)

Type into frontmost app:

osascript -e 'tell application "System Events" to keystroke "Hello World"'

Shortcut:

osascript -e 'tell application "System Events" to keystroke "s" using command down'

Bring to front:

osascript -e 'tell application "TextEdit" to activate'

Rules

  1. On macOS, “notepad” → TextEdit unless the user names another app.
  2. After open, confirm success when practical (e.g. pgrep).
  3. Prefer write a temp file and open it over long keystroke typing.
  4. Use osascript only when needed; it is fragile under focus changes.
  5. After launching an app, a short sleep 1 before UI automation can help.
  6. For “open notepad and write X”: write X to a file, open in TextEdit.
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. 8d ago First seen · 105 lines · 13 tokens per session scan A 8fdf745a69db

Subscribe to this mod's changes

app_control is a skill published in the GitHub repository frontier-ai-next/mgarlbot (17 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 535 once invoked, about $0.0001 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 2026-08-30.