McpServer copilot-instructions.md

A set of Copilot instructions for the McpServer project. It covers response formatting, terminal use, session logging, and build and test practices.

In plain words
What is it for?
It guides responses, terminal commands, session-log updates, and build or test work in the McpServer project.
Why use it?
It gives the coding agent project-specific rules, including how to identify itself in logs and how to preserve session records.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/sharpninja/mcpserver/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/sharpninja/McpServer

Made for: GitHub Copilot.

Per session 1,091 This file is loaded in full into every session.
When invoked 1,091 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01091 $0.01091
Opus 5 $0.00545 $0.00545
Sonnet 5 $0.00218 $0.00218
Haiku 4.5 $0.00109 $0.00109

Measured yesterday against content hash 16afd5baaecd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

McpServer 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 yesterday.

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.

.github/copilot-instructions.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions — McpServer

Agent Identity: When posting to the MCP session log, use the agent's actual identity in Pascal-Case for sourceType and the session ID prefix. Do not use inaccurate aliases, lowercase names, or legacy placeholders. Example: Codex. For specific operational instructions (session bootstrap, turn logging lifecycle, helper command order), follow AGENTS-README-FIRST.yaml.

Response Formatting

  • Do not use table-style output in responses.
  • Use concise bullets or short paragraphs instead.

Terminal Usage

  • Do NOT set focus to the terminal window.
  • Do NOT write multiline commands to the terminal; use temporary scripts instead.
  • Use only pwsh.exe (PowerShell 7+). Do not invoke powershell.exe (Windows PowerShell 5.1) for scripts, examples, or tooling.

Session Logging Requirements

  • Follow AGENTS-README-FIRST.yaml for workflow and helper command order.
  • Persist session log changes immediately after each meaningful update; do not batch unsaved turn changes.
  • For each turn, include as much detail as available: interpretation, response/status, actions (type/status/filePath), files modified, design decisions, requirements discovered, blockers, and context references.

Build, Test, Lint

# Build (via Nuke)
./build.ps1 Compile
# or: dotnet build src\McpServer.Support.Mcp -c Debug

# Run all unit tests (via Nuke)
./build.ps1 Test
# or individual projects:
# dotnet test tests\McpServer.Support.Mcp.Tests -c Debug
# dotnet test tests\McpServer.Client.Tests -c Debug
# dotnet test tests\Build.Tests -c Debug

# Run integration tests (uses CustomWebApplicationFactory, in-memory EF)
dotnet test tests\McpServer.Support.Mcp.IntegrationTests -c Debug

# Run a single test by fully-qualified name
dotnet test tests\McpServer.Support.Mcp.Tests -c Debug --filter "FullyQualifiedName~TodoServiceTests.QueryAsync_NoFilters_ReturnsAllItems"

# Run tests in a single class
dotnet test tests\McpServer.Support.Mcp.Tests -c Debug --filter "FullyQualifiedName~TodoServiceTests"

# Validate appsettings config (via Nuke)
./build.ps1 ValidateConfig
# or: pwsh.exe -NoLogo -NoProfile -NonInteractive -File ./scripts/Validate-McpConfig.ps1

# Validate requirements traceability
./build.ps1 ValidateTraceability

# Markdown lint (docs only)
# CI uses markdownlint-cli2 with .markdownlint-cli2.yaml

Read the full file on GitHub · 82 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. yesterday First seen · 82 lines · 1,091 tokens per session scan A 16afd5baaecd

Subscribe to this mod's changes

McpServer copilot-instructions.md is an instructions file published in the GitHub repository sharpninja/McpServer (2 stars, last pushed 11d ago), licensed Apache-2.0. It adds 1,091 tokens to every session, about $0.0055 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.