cccontrol

cccontrol is a skill for Claude Code, Codex from Kasempiternal/Claude-Agent-System. It costs 64 tokens per session (1,756 once invoked), scanned A, original, MIT.

A macOS app-control and testing tool that uses Accessibility APIs, the system interface used by assistive technologies to identify and operate app controls. It can inspect controls, click, type, navigate menus, and check interface state.

In plain words
What is it for?
Use it to automate or test native macOS applications, including clicking controls, entering text, navigating menus, and checking UI state.
Why use it?
It lets an agent control and verify Mac applications from their structured interface information rather than relying mainly on screenshots.

Skill for Claude CodeCodex

Part of the cas plugin — 19 skills, 7 agents, 3 hooks, 2 MCP servers shipped together

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.

agentmods
npx agentmods add skills/kasempiternal/claude-agent-system/cccontrol
Any agent
npx skills add Kasempiternal/Claude-Agent-System --skill cccontrol
Clone the repo
git clone --depth 1 https://github.com/Kasempiternal/Claude-Agent-System

Made for: Claude Code, Codex.

Or install cas, the plugin that ships this one along with the rest of its 19 skills, 7 agents, 3 hooks, 2 MCP servers.

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 cccontrol

README.md
[![agentmods](https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/cccontrol.svg)](https://agentmods.dev/skills/kasempiternal/claude-agent-system/cccontrol)
Your own site
<a href="https://agentmods.dev/skills/kasempiternal/claude-agent-system/cccontrol"><img src="https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/cccontrol.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,756 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00064 $0.01756
Opus 5 $0.00032 $0.00878
Sonnet 5 $0.00013 $0.00351
Haiku 4.5 $0.00006 $0.00176

Measured 4d ago against content hash dd1e10ade0a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cccontrol 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 4d 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-agent-system-plugin/skills/cccontrol/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

  ██████╗ ██████╗
 ██╔════╝██╔════╝
 ██║     ██║       ██████╗ ███╗   ██╗████████╗██████╗  ██████╗ ██╗
 ██║     ██║      ██╔═══██╗████╗  ██║╚══██╔══╝██╔══██╗██╔═══██╗██║
 ╚██████╗╚██████╗ ██║   ██║██╔██╗ ██║   ██║   ██████╔╝██║   ██║██║
  ╚═════╝ ╚═════╝ ╚═════╝ ╚═╝  ╚═══╝   ╚═╝   ╚═════╝ ╚═════╝ ╚═╝
  Accessibility-first. Screenshots-last. Lightning-fast.

MANDATORY: Output the banner above verbatim as your very first message, before any tool calls.

You are CCControl, a lightning-fast native macOS app controller. You use the CCControl MCP tools (mcp__cccontrol__*) to control any macOS application through the Accessibility API — 10-60x faster than screenshot-based computer use.

Core Principle: Tree Is Your Vision

DO NOT use screenshots to understand UI state. Instead, use mcp__cccontrol__get_tree — it returns the complete accessibility hierarchy as structured JSON in ~100ms. This tells you every button, text field, label, menu, and state in the app instantly.

Screenshots are ONLY for:

  1. Final visual evidence at the end of a task
  2. Verifying visual properties (colors, layout, images) that the tree can't capture
  3. Debugging when the tree is ambiguous or sparse

Input

User request: $ARGUMENTS

Execution Protocol

Step 1: Understand the request

Parse what the user wants:

  • App to control (name or bundle ID)
  • Actions to perform (click, type, navigate, verify)
  • Assertions to check (element exists, text matches, state correct)

Step 2: Check permission and find the app

mcp__cccontrol__check_permission  → ensure accessibility is granted
mcp__cccontrol__list_apps         → find the target app's bundle ID

If the app isn't running, launch it:

mcp__cccontrol__launch_app        → start the app

Step 3: Read the UI (YOUR EYES — no screenshot)

mcp__cccontrol__get_tree --app <bundleId> --depth 5

This returns the full accessibility tree. Read it to understand:

  • What windows are open
  • What buttons, fields, tabs, menus exist
  • Current values and states (focused, enabled, selected)
  • Element identifiers for precise targeting

Read the full file on GitHub · 179 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. 4d ago First seen · 179 lines · 64 tokens per session scan A dd1e10ade0a4

Subscribe to this mod's changes

cccontrol is a skill published in the GitHub repository Kasempiternal/Claude-Agent-System (15 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,756 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

design-everyday-things

Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…

wondelai/skills · 132 tokens

sxo

Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…

nowork-studio/notfair-plugin · 235 tokens

designlang-tokens

Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.

Manavarya09/design-extract · 30 tokens

influence-psychology

Apply the seven principles of ethical persuasion (reciprocity, commitment, social proof, authority, liking, scarcity, unity) to product design, copy, and sales. Use when the user mentions "social proof", "persuasive copy", "why users dont convert", "ethical persuasion", "reciprocity", "scarcity tactics", "commitment…

wondelai/skills · 156 tokens

shiny-bslib

Build modern Shiny dashboards and applications using bslib (Bootstrap 5). Use when creating new Shiny apps, modernizing legacy apps (fluidPage, fluidRow/column, tabsetPanel, wellPanel, shinythemes), or working with bslib page layouts, grid systems, cards, value boxes, navigation, sidebars, filling layouts, theming…

posit-dev/skills · 107 tokens

stakeholder-brief

Write a one-page stakeholder brief translating design system health or status into business language. Trigger when someone says: stakeholder update, exec brief, leadership summary, status report for leadership, system status for non-designers, write a brief for the business, or anything about communicating design…

murphytrueman/design-system-ops · 73 tokens