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.
npx agentmods add instructions/sandraschi/windows-computer-use-mcp/agents-mdgit clone --depth 1 https://github.com/sandraschi/windows-computer-use-mcpWrote 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.
[](https://agentmods.dev/instructions/sandraschi/windows-computer-use-mcp/agents-md)<a href="https://agentmods.dev/instructions/sandraschi/windows-computer-use-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/windows-computer-use-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00283 | $0.00283 |
| Opus 5 | $0.00142 | $0.00142 |
| Sonnet 5 | $0.00057 | $0.00057 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
windows-computer-use-mcp AGENTS.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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- windows-computer-use-mcp AGENTS.md — 89% identical, 5 lines differ
What it actually says
windows-computer-use-mcp — Agent Guide
Quick Reference
18 portmanteau tools. All use operation enum. Responses are ToolResult {status, message, data, recovery_tip}.
Autonomous: automation_mission(run="open Notepad, type hello, save") — decomposes, executes, retries, verifies.
Smart: automation_smart(click="the Save button") — finds element by intent across all windows.
Macros: automation_macro(record=true) → run tools → stop() → replay().
Watchers: automation_watch(start, condition="window_appears", target="Update").
Telemetry: automation_system(telemetry) — query failure patterns per tool.
Workflows: automation_mission(workflow, actions=[...], app="notepad.exe").
Safety
- Read docs/SAFETY.md first
- Mutating actions require HITL approval (bypass with WINDOWS_COMPUTER_USE_MCP_BYPASS_HITL=1)
- Face and keylogger are opt-in (off by default)
Entry Point
uv run windows-computer-use-mcp → windows_computer_use_mcp.main:main
Fleet
- mcp-central-docs for fleet-wide standards
- Pair with virtualization-mcp for sandbox isolation
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.
- 4d ago First seen · 25 lines · 283 tokens per session scan A 139383416bbc
windows-computer-use-mcp AGENTS.md is an instructions file published in the GitHub repository sandraschi/windows-computer-use-mcp (35 stars, last pushed 4d ago), licensed MIT. It adds 283 tokens to every session, about $0.0014 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.
Other instructions, from other repositories
outline-apps AGENTS.md
AGENTS.md instructions for OutlineFoundation/outline-apps, covering welcome to the outline monorepo!, repository structure, the npm run action command, common actions and other useful commands.
Windows-MCP CLAUDE.md
Claude Code instructions for CursorTouch/Windows-MCP, covering claude.md, project overview, build & development commands, architecture and code style.
outline-apps CLAUDE.md
Claude Code instructions for OutlineFoundation/outline-apps: This project uses AGENTS.md instead of CLAUDE.md.
wispterm AGENTS.md
Instructions for xuzhougeng/wispterm, covering agents.md, architecture, ui presentation styles, cohesion and coupling and integration layer vs feature domains.
HuLa AGENTS.md
Instructions for HuLaSpark/HuLa, a project described as: 🍀 A cross-platform instant messaging desktop application with exceptional performance built on Rust + Vue3, compatible with Windows, macOS, Linux, Android, and iOS（一款基于Rust+Vue3极致性能的跨平台即时通讯桌面应用，兼容Windows、MacOS、Linux、Android、IOS）.
nuclear AGENTS.md
AGENTS.md instructions for nukeop/nuclear, covering agents.md, project overview, packages, commands and development.