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 agents/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/agents/sbroenne/mcp-windows/copilot-instructions)<a href="https://agentmods.dev/agents/sbroenne/mcp-windows/copilot-instructions"><img src="https://agentmods.dev/badge/agents/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 | $0.00000 | $0.01201 |
| Opus 5 | $0.00000 | $0.00600 |
| Sonnet 5 | $0.00000 | $0.00240 |
| Haiku 4.5 | $0.00000 | $0.00120 |
Grade A, and why
copilot-instructions 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 3d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-windows Development Guidelines
Auto-generated from all feature plans. Last updated: 2025-12-07
Active Technologies
- C# 12+ (.NET 8.0 LTS) + Microsoft.Extensions.Logging, Serilog, MCP SDK, System.CommandLine (002-keyboard-control)
- N/A (stateless operations, held keys tracked in memory only) (002-keyboard-control)
- C# 12+ / .NET 8.0 LTS + MCP C# SDK, Microsoft.Extensions.Logging, Serilog (003-window-management)
- N/A (stateless window queries) (003-window-management)
- TypeScript 5.9+ (extension), C# 12+ (.NET 8.0 for bundled server) + VS Code Extension API 1.106.0+, .NET Install Tool extension (006-vscode-extension)
- C# 12+ (.NET 8.0 LTS) + Microsoft.Extensions.Logging, System.Drawing, existing MCP tools (mouse_control, keyboard_control, window_management, screenshot_control) (007-llm-integration-testing)
- File-based (PNG images, JSON metadata, Markdown scenarios) (007-llm-integration-testing)
- C# 12+ / .NET 8.0 LTS + Windows GDI+ (System.Drawing), existing ScreenshotService infrastructure (008-all-monitors-screenshot)
- N/A (returns base64-encoded PNG via MCP) (008-all-monitors-screenshot)
- C# 12 / .NET 8.0 + MCP C# SDK (latest), Microsoft.Extensions.*, System.Text.Json (010-code-quality)
- N/A (stateless tool server) (010-code-quality)
- C# 12+ / .NET 8.0 + System.Drawing (GDI+ for encoding/scaling), existing
Sbroenne.WindowsMcp.Capturenamespace (011-screenshot-llm-optimization) - File output to
System.IO.Path.GetTempPath()with unique naming (011-screenshot-llm-optimization) - File output to
System.IO.Path.GetTempPath()with timestamp naming (011-screenshot-llm-optimization) - N/A (stateless operations) (013-ui-automation-ocr)
- C# 12+ / .NET 8.0 + System.Windows.Automation (UIAutomationClient.dll), Windows.Media.Ocr, Microsoft.Windows.AI.Imaging (optional NPU) (013-ui-automation-ocr)
- C# 12 / .NET 10.0 + MCP C# SDK, Microsoft.Extensions.Compliance.Redaction, Microsoft.Extensions.Hosting (015-session-control)
- In-memory (ConcurrentDictionary), no persistence (015-session-control)
- Python (pytest-aitest test format) + pytest-aitest, GPT-5.5, Filesystem MCP Server (015-llm-tool-coverage)
- Timestamped output folders under
tests/Sbroenne.WindowsMcp.LLM.Tests/output/(gitignored) (015-llm-tool-coverage)
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.
- 3d ago First seen · 92 lines · 0 tokens per session scan A 47116215b559
copilot-instructions is an agent published in the GitHub repository sbroenne/mcp-windows (87 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,201 tokens. 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 agents, from other repositories
API Tester Specialist
Specialist in creating and executing API tests. Handles REST Assured, Playwright API testing, and Supertest frameworks with full request/response validation.
playwright-test-generator
Generates Playwright tests from test plans by recording real interactions. Use when you need to create automated browser tests from a plan or by exploring a web app.
Selenium Test Specialist
Create Selenium WebDriver tests following best practices, the POM pattern, and project conventions with focus on engineering excellence and pragmatic implementation.
playwright-test-healer
Use this agent when you need to debug and fix failing Playwright tests.
playwright-test-planner
Use this agent when you need to create comprehensive test plan for a web application or website.
qa
QA engineer who implements Playwright end-to-end tests following project conventions. Writes tests, runs them, and collaborates with teammates to ensure comprehensive coverage.