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/peterbud/nitro-mcp-server/copilot-instructionsgit clone --depth 1 https://github.com/peterbud/nitro-mcp-serverWrote 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/peterbud/nitro-mcp-server/copilot-instructions)<a href="https://agentmods.dev/instructions/peterbud/nitro-mcp-server/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/peterbud/nitro-mcp-server/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 | $0.02069 | $0.02069 |
| Opus 5 | $0.01035 | $0.01035 |
| Sonnet 5 | $0.00414 | $0.00414 |
| Haiku 4.5 | $0.00207 | $0.00207 |
Grade A, and why
nitro-mcp-server 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 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions for Nitro MCP Server
Project Overview
This is a Model Context Protocol (MCP) server implementation using Nitro framework with streamable HTTP transport. It demonstrates MCP server capabilities including tools, resources, prompts, and pluggable authentication providers.
Technology Stack
- Runtime: Nitro (v2.12.4+)
- MCP SDK: @modelcontextprotocol/sdk (v1.17.3+)
- Validation: Zod (v3.25.76+)
- Auth: JWT with jose library
- Logger: consola (v3.4.2+)
- Package Manager: pnpm (v10.7.1+)
- TypeScript: v5.9.2+
- ESLint: @antfu/eslint-config (v5.2.1+)
Code Style & Conventions
TypeScript
- Use TypeScript for all source files
- Prefer type imports:
import type { TypeName } from '...' - Use Zod schemas for runtime validation
- Define explicit return types for public functions
- Use
interfacefor object shapes,typefor unions/intersections
Formatting
- Use single quotes for strings
- 2-space indentation
- Follow @antfu/eslint-config rules
- No semicolons (per config)
- Use arrow functions for callbacks
- Prefer const over let
File Organization
- Group imports by: types, external libraries, internal modules, utilities
- Export reusable types from
~/types.ts - Keep route handlers in
routes/directory - Place business logic in
lib/directory - Utils in
utils/for reusable helpers - Plugins in
plugins/for Nitro plugins - Middleware in
middleware/for global handlers
Architecture Patterns
MCP Server Structure
The MCP server is initialized in plugins/mcp.ts.
- Server Initialization: Create McpServer instance with name, version, and capabilities
- Registration: Register tools, resources, and prompts from arrays
- Singleton Pattern: Export
getServer()andgetAuthProvider()for accessing instances
Tools (in lib/tools/)
Tools are MCP functions that can be invoked by clients.
Key Points:
- Always validate input with Zod schemas
- Use
structuredContentfor typed outputs when outputSchema is defined - Always provide fallback
contentarray - Access auth info from second parameter:
{ authInfo } - Use
loggerfor logging operations - Add tool to
toolsarray inplugins/mcp.ts
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 · 262 lines · 2,069 tokens per session scan A 03cfab1ced11
nitro-mcp-server copilot-instructions.md is an instructions file published in the GitHub repository peterbud/nitro-mcp-server (6 stars, last pushed 9mo ago), licensed MIT. It adds 2,069 tokens to every session, about $0.0103 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
excalidraw-mcp AGENTS.md
Instructions for cmd8/excalidraw-mcp, covering important and testing.
ida-pro-mcp CLAUDE.md
Instructions for mrexodia/ida-pro-mcp, covering claude.md, what this project is, core implementation rules, ida thread safety and api conventions.
tableau-mcp CLAUDE.md
Instructions for tableau/tableau-mcp, covering claude.md, build & development commands, building, running the server and testing.
anytype-mcp CLAUDE.md
Instructions for anyproto/anytype-mcp, covering claude.md, common commands, development, testing and code quality.
RivalSearchMCP AGENTS.md
Instructions for damionrashford/RivalSearchMCP, covering agents.md, project overview, development commands, setup & running and install dependencies.
RivalSearchMCP CLAUDE.md
Instructions for damionrashford/RivalSearchMCP, covering claude.md, project overview, development commands, setup & running and set up pre-commit hooks.