MCP-OsAutomation: Instructions file for Claude Code

CLAUDE.md

MCP-OsAutomation CLAUDE.md is an instructions file for Claude Code from thearpankumar/MCP-OsAutomation. It costs 1,308 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for an AI coding agent that controls desktop applications through screen analysis, mouse clicks, typing, and keyboard shortcuts.

In plain words
What is it for?
Automating actions in applications such as a web browser, code editor, or terminal, including switching programs, reading screen text, clicking controls, entering text, and stopping automation.
Why use it?
It gives the agent a fixed process for finding programs, checking the screen, and carrying out tasks through a terminal-based desktop setup.

Instructions file for Claude Code

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

This is thearpankumar/MCP-OsAutomation's own configuration. It tells Claude Code how to work on MCP-OsAutomation 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 MCP-OsAutomation configures →

Reuse

Borrowing it

Nothing to install: this file belongs to thearpankumar/MCP-OsAutomation. 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/thearpankumar/MCP-OsAutomation/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/thearpankumar/MCP-OsAutomation

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 MCP-OsAutomation CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thearpankumar/mcp-osautomation/claude-md.svg)](https://agentmods.dev/instructions/thearpankumar/mcp-osautomation/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/thearpankumar/mcp-osautomation/claude-md"><img src="https://agentmods.dev/badge/instructions/thearpankumar/mcp-osautomation/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,308 This file is loaded in full into every session.
When invoked 1,308 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 $0.01308 $0.01308
Opus 5 $0.00654 $0.00654
Sonnet 5 $0.00262 $0.00262
Haiku 4.5 $0.00131 $0.00131

Measured 7d ago against content hash db5fa7230de2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

MCP-OsAutomation 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 7d 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 · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP WebAutomation - Claude Code Instructions

Environment Setup

  • System: Single monitor setup with terminal-based workflow
  • Primary Interface: Terminal/CLI applications preferred
  • Display: One screen with multiple applications via Alt+Tab switching

Tools Available

Tool Purpose
analyze_screen() DUAL MODE: Get coordinates OR extract text
click_element() Click by coordinates or text
type_text() Type text with options
press_key() Keyboard shortcuts
emergency_stop() Stop all automation

Workflow Protocol

1. Task Analysis & Program Discovery

Before performing any task:

# Step 1: Switch to see available programs
mcp.call_tool("press_key", {"key": "tab", "modifiers": ["alt"]})

# Step 2: Analyze current screen to understand what's available
screen = mcp.call_tool("analyze_screen", {"include_ocr": False})

# Step 3: Check if required programs are running via bash
result = mcp.call_tool("bash_command", {"command": "pgrep -l firefox|chrome|code|terminal"})

2. Program Navigation Strategy

# Navigate through applications using Alt+Tab until target found
def find_target_program(target_program):
    max_attempts = 10
    for attempt in range(max_attempts):
        screen = mcp.call_tool("analyze_screen", {"include_ocr": False})

        if target_program.lower() in screen["screen_description"].lower():
            return True

        # Switch to next program
        mcp.call_tool("press_key", {"key": "tab", "modifiers": ["alt"]})

    return False

3. Task Execution Priority

  1. PREFER BASH: If task can be done via terminal commands
  2. GUI FALLBACK: Use desktop automation only when necessary
  3. HYBRID APPROACH: Combine bash + GUI for optimal efficiency

4. Complete Task Workflow

def execute_user_task(user_request):
    # Step 1: Analyze what user wants
    # Step 2: Check if bash can handle it
    if can_use_bash(user_request):
        return execute_bash_solution(user_request)

    # Step 3: Find required GUI program
    target_program = determine_required_program(user_request)

    # Step 4: Navigate to program
    if find_target_program(target_program):
        return execute_gui_task(user_request)
    else:
        # Step 5: Launch program if not running
        launch_program(target_program)
        return execute_gui_task(user_request)

Read the full file on GitHub · 160 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. 7d ago First seen · 160 lines · 1,308 tokens per session scan A db5fa7230de2

Subscribe to this mod's changes

MCP-OsAutomation CLAUDE.md is an instructions file published in the GitHub repository thearpankumar/MCP-OsAutomation (1 stars, last pushed 11mo ago), licensed Apache-2.0. It adds 1,308 tokens to every session, about $0.0065 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

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