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/remote-mcp-functions-typescript/copilot-instructionsgit clone --depth 1 https://github.com/Azure-Samples/remote-mcp-functions-typescriptWrote 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/remote-mcp-functions-typescript/copilot-instructions)<a href="https://agentmods.dev/instructions/azure-samples/remote-mcp-functions-typescript/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/azure-samples/remote-mcp-functions-typescript/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 | $0.00272 | $0.00272 |
| Opus 5 | $0.00136 | $0.00136 |
| Sonnet 5 | $0.00054 | $0.00054 |
| Haiku 4.5 | $0.00027 | $0.00027 |
Grade A, and why
remote-mcp-functions-typescript 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- mcp copilot-instructions.md — 100% identical, 0 lines differ
What it actually says
You are an ai assistant tasked assisting the developer to build and deploy MCP Servers successfully using Azure Functions. Our ultimate goal is for the user to be able to complete this quickstart guide, where the app is deployed and healthy in azure, and the MCP client tools are calling this MCP server.
Here are some specific requirements and pieces of context:
- This must build a working Azure Function project complete with code, Readme changes, and AZD bicep. The original repo is already in this state, so your job is to preserve it.
- AZD and the func (aka Azure Functions Core Tools) commandline tools are the main tools to be used for deployment, provisioning and running locally. As soon as the user has done the
azd uporazd provisionstep at least once, you can learn all values of their azure application like resource group and function app name using the environment variables stored in the .azure folder. Please proactively use these and be helpful to suggest running commands for the developer, replacing placeholder values when possible with these environment variables. - This particular project is TypeScript (Node.js) Azure Function using the v4 programming model
- We prefer using Azure Functions bindings if they can work versus the Azure SDKs, but Azure SDKs are ok if there is no substitute.
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 · 9 lines · 272 tokens per session scan A 7bb939f53c32
remote-mcp-functions-typescript copilot-instructions.md is an instructions file published in the GitHub repository Azure-Samples/remote-mcp-functions-typescript (59 stars, last pushed 1mo ago), licensed MIT. It adds 272 tokens to every session, about $0.0014 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
AppClaw CLAUDE.md
Claude Code instructions for appclawhq/AppClaw, covering claude.md, what is appclaw?, build & run commands, architecture and entry point & cli modes (src/index.ts).
awsmux AGENTS.md
Instructions for 0hardik1/awsmux, covering agents.md, what awsmux is, build, test, verify, layout and the safety model — invariants you must not weaken.
google-connector AGENTS.md
Instructions for kevinbkt10/google-connector, covering agents.md — google connector, objetivo do usuário, regras, fluxo em um pedido (“um clique” com a ia) and instalação (comandos).
awesome-ai-native-cloudflare-app CLAUDE.md
Instructions for vibegui/awesome-ai-native-cloudflare-app, covering operating manual: this is a self-improving app, setup (once per machine), the team, the loop — run it every session and rules.
EpesiCRM CLAUDE.md
Claude Code instructions for jtylek/EpesiCRM, covering claude.md, project, environment quirks (this machine), commands and architecture.
cron-mcp CLAUDE.md
Claude Code instructions for Shreyas-Profile/cron-mcp, covering deploying cron-mcp to hetzner + regiq.in, server (shared with the rest of the globalion mcp fleet), deploy a new version, first-time subdomain wiring (cron.regiq.in) and env vars.