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/sharpninja/mcpserver/copilot-instructionsgit clone --depth 1 https://github.com/sharpninja/McpServerWhat 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 | $0.01091 | $0.01091 |
| Opus 5 | $0.00545 | $0.00545 |
| Sonnet 5 | $0.00218 | $0.00218 |
| Haiku 4.5 | $0.00109 | $0.00109 |
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.
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 invokepowershell.exe(Windows PowerShell 5.1) for scripts, examples, or tooling.
Session Logging Requirements
- Follow
AGENTS-README-FIRST.yamlfor 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
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.
- yesterday First seen · 82 lines · 1,091 tokens per session scan A 16afd5baaecd
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.
Other instructions, from other repositories
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.
com-example-config-AsyncTestConfig
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.
pupila CLAUDE.md
Instructions for FranRom/pupila, covering claude.md, where things live, stack, run locally and repo layout.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.
UsageAtlas AGENTS.md
Instructions for SRX9/UsageAtlas, covering repository guidelines and coding approach.