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/azure-samples/mcp-container-ts/copilot-instructionsgit clone --depth 1 https://github.com/Azure-Samples/mcp-container-tsWrote 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/azure-samples/mcp-container-ts/copilot-instructions)<a href="https://agentmods.dev/instructions/azure-samples/mcp-container-ts/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/azure-samples/mcp-container-ts/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 | $0.00718 | $0.00718 |
| Opus 5 | $0.00359 | $0.00359 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
mcp-container-ts 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 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.
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions for MCP Container TS
Project Overview
- This project implements a Model Context Protocol (MCP) server using Node.js and TypeScript, designed to run locally or on Azure Container Apps.
- The MCP server acts as a bridge for AI models and tools, enabling communication and orchestration of tasks via HTTP endpoints.
- Key components: MCP HTTP server (
src/server.ts), tool definitions (src/tools.ts), SQLite database integration (src/db.ts), and infrastructure as code (infra/).
Architecture & Data Flow
- The server exposes endpoints for tool execution (add, list, complete, delete TODOs) and streams results using HTTP or SSE.
- Tools interact with an in-memory SQLite DB for state management.
- Configuration for local and remote servers is managed via
.vscode/mcp.json. - Deployment to Azure is automated using Bicep files and the Azure Developer CLI (
azd).
Developer Workflows
- Local Development:
- Install dependencies:
npm install - Start server:
npm run dev(default port: 3000) - Database is ephemeral (in-memory SQLite).
- Install dependencies:
- Azure Deployment:
- Provision and deploy:
azd up - Clean up:
azd down --purge --force
- Provision and deploy:
- Testing:
- Use MCP Inspector (
npm run inspect) or VS Code MCP client integration via.vscode/mcp.json. - Authentication uses a demo token (
abc).
- Use MCP Inspector (
Project-Specific Conventions
- Tool outputs are always structured as
{ content: string[] }for consistency. - All tool logic is centralized in
src/tools.tsand follows a simple input/output schema. - Server configuration (local/remote, tokens) is managed in
.vscode/mcp.json. - Infrastructure is defined in Bicep (
infra/), with parameters inmain.parameters.json. - No persistent database; all state is lost on server restart unless customized.
Integration Points
- External communication via HTTP/SSE endpoints (
/mcp,/sse). - Azure Container Apps for cloud deployment; local Docker support via
Dockerfileanddocker-compose.yml. - MCP Inspector and VS Code MCP client for tool invocation and inspection.
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 · 74 lines · 718 tokens per session scan A 7a35c49bfad9
mcp-container-ts copilot-instructions.md is an instructions file published in the GitHub repository Azure-Samples/mcp-container-ts (49 stars, last pushed 9d ago), licensed MIT. It adds 718 tokens to every session, about $0.0036 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 2026-08-30.
Other instructions, from other repositories
PlatformPlatform AGENTS.md
Instructions for platformplatform/PlatformPlatform, covering behavioral guidelines, build, test, and format, product management tool, auto memory and source of truth.
azure-lean-stack-skills CLAUDE.md
Claude Code instructions for alexpizarro/azure-lean-stack-skills, covering claude.md — azure lean stack (v2.2.0), plugin structure, how it works, composition with microsoft's azure-skills and contributing.
Azure-MCP-Server-Accelerator python.instructions.md
Python coding conventions and guidelines.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, working with the user and development principles.
GPT-RAG release.instructions.md
Instructions for Azure/GPT-RAG, a project described as: Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.
selfhost-ai CLAUDE.md
Claude Code instructions for kossakovsky/selfhost-ai, covering claude.md, project overview, core architecture, key files and installation flow.