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/mcprunner/mssqlmcp/copilot-instructionsgit clone --depth 1 https://github.com/MCPRUNNER/mssqlMCPWrote 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/mcprunner/mssqlmcp/copilot-instructions)<a href="https://agentmods.dev/instructions/mcprunner/mssqlmcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/mcprunner/mssqlmcp/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 | $0.00303 | $0.00303 |
| Opus 5 | $0.00151 | $0.00151 |
| Sonnet 5 | $0.00061 | $0.00061 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade C, and why
mssqlMCP copilot-instructions.md scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Use this file to provide workspace-specific custom instructions to Copilot. For more details, visit https://code.visualstudio.com/docs/copilot/copilot-customization#_use-a-githubcopilotinstructionsmd-file --> What it actually says
mssqlMCP Copilot Instructions
This is a Model Context Protocol (MCP) Server project that connects to SQL Server databases, and is designed to be used by vscode as a Copilot Agent.
You can find more info and examples at
This project:
- Implements the Model Context Protocol for SQL Server database connectivity
- uses stdio for communication
- Allows VS Code and Copilot to connect to SQL databases via MCP
- Supports fetching metadata
- Uses C# for the implementation
- To be used as a Copilot Agent MCP
Additional Instructions
- Use current vscode workspace
- Use Microsoft.Data.SqlClient instead of System.Data.SqlClient
- Use ModelContextProtocol
- Use async/await for all database calls
- Use a logging framework for logging
- Use a configuration file for connection strings
- Add all changes to current workspace
- Use a .gitignore file to ignore build files
- Create example mcp.json for running with Copilot Agent in VS Code
- Make sure to include an initialize endpoint.
- Use best practices
- when prompting for terminal commands, use a semicolon to separate commands
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 · 35 lines · 303 tokens per session scan C b1c88f06655c
mssqlMCP copilot-instructions.md is an instructions file published in the GitHub repository MCPRUNNER/mssqlMCP (10 stars, last pushed 3mo ago), licensed MIT. It adds 303 tokens to every session, about $0.0015 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
MCP-PostgreSQL-Ops copilot-instructions.md
Instructions for call518/MCP-PostgreSQL-Ops, covering architecture overview, core components, key patterns, in functions.py and development workflows.
mcp AGENTS.md
AGENTS.md instructions for Teamwork/mcp, covering agents.md, this repository is public, project overview, setup commands and build and run.
raindrop-mcp GEMINI.md
Instructions for adeze/raindrop-mcp, covering raindrop mcp server - project context, project overview, core technologies, architecture and key commands.
raindrop-mcp copilot-instructions.md
Instructions for adeze/raindrop-mcp: The canonical project instructions are in AGENTS.md. Follow them for architecture, MCP safety constraints, tooling, validation, and release policy.
raindrop-mcp CLAUDE.md
Instructions for adeze/raindrop-mcp: Project instructions moved to AGENTS.md, the canonical Codex operating guide.
counterpoise-ledger CLAUDE.md
Instructions for jeffjjohnston/counterpoise-ledger, covering claude.md, project overview, development commands, essential commands and testing.