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/sbroenne/mcp-windows/copilot-instructionsgit clone --depth 1 https://github.com/sbroenne/mcp-windowsWrote 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/sbroenne/mcp-windows/copilot-instructions)<a href="https://agentmods.dev/instructions/sbroenne/mcp-windows/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/sbroenne/mcp-windows/copilot-instructions.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 | $0.01131 | $0.01131 |
| Opus 5 | $0.00566 | $0.00566 |
| Sonnet 5 | $0.00226 | $0.00226 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
mcp-windows copilot-instructions.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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions for mcp-windows
Sister Projects
mcp-windows is one of a family of Windows-only MCP-server repos maintained by the same author
(sbroenne). The family also includes:
mcp-server-excel(sbroenne/mcp-server-excel) — Excel COM automation. This is the authoritative architectural template for the family's general server-side patterns: layered architecture (Core → Service → CLI/MCP Server), the "two equal entry points" (MCP Server + CLI) principle, Unified Service Architecture (shared daemon/session registry), and its support/audit scripts (scripts/*.ps1) and CI Gate workflow.mcp-windowsis UI-automation-focused (FlaUI/ pywinauto patterns) rather than COM/Office-interop-focused, so not every Excel pattern applies directly — but when solving a cross-cutting problem (session lifecycle, CLI/MCP parity, daemon process management, pre-commit audit tooling), check how Excel solved it first.mcp-server-powerpoint(sbroenne/mcp-server-powerpoint) — PowerPoint COM automation, structurally mirrorsmcp-server-excel.
If you fix a real bug or process/tooling gap here that likely also exists in the other repos, flag it so the same fix can be considered there.
Core Principles
The project follows these NON-NEGOTIABLE principles:
- Test-First Development - Write tests before implementation
- MCP Protocol Compliance - Follow MCP specification strictly
- Augmentation, Not Duplication - Tools are "dumb actuators", no complex logic in tools
- Microsoft Libraries First - Prefer official Microsoft libraries over third-party alternatives
- Security Best Practices - No secrets in code, validate inputs, follow security guidelines
- Modern .NET & C# - Use current .NET and C# language features
- xUnit Testing - All .NET tests use xUnit framework
- LLM Integration Testing - Use pytest-skill-engineering with GitHub Copilot SDK
- Token Optimization - Optimize MCP responses for LLM token efficiency
- UI Automation First - Semantic UI automation is the primary approach
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 · 90 lines · 1,131 tokens per session scan A 1bea59c2fe83
mcp-windows copilot-instructions.md is an instructions file published in the GitHub repository sbroenne/mcp-windows (88 stars, last pushed yesterday), licensed MIT. It adds 1,131 tokens to every session, about $0.0057 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
maui uitests.instructions.md
Instructions for dotnet/maui, covering ui testing guidelines for .net maui, ui test structure, two-project requirement, base class and infrastructure and naming conventions.
maui ci-copilot-pipeline-security.instructions.md
Security rules for the Copilot PR-review pipeline. Read before editing.
maui performance-hotpaths.instructions.md
Instructions for dotnet/maui, covering performance-critical path rules, hot paths in maui, allocation avoidance, caching and invalidation and collection iteration.
maui collectionview-windows.instructions.md
Instructions for dotnet/maui, covering collectionview — windows (items/ handler), winui listview/itemsrepeater patterns, data source and change notifications, layout configuration and cross-platform consistency.
codex-provider-sync AGENTS.md
Instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.
Grace AGENTS.md
AGENTS.md instructions for ScottArbeit/Grace, covering agent instructions, agent quickstart (local), issue tracking, development process and markdown guidelines.