Borrowing it
Nothing to install: this file belongs to Azure-Samples/APIM-Unified-AI-Gateway-Sample. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Azure-Samples/APIM-Unified-AI-Gateway-Sample/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/Azure-Samples/APIM-Unified-AI-Gateway-SampleWrote 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/apim-unified-ai-gateway-sample/copilot-instructions)<a href="https://agentmods.dev/instructions/azure-samples/apim-unified-ai-gateway-sample/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/azure-samples/apim-unified-ai-gateway-sample/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/azure-samples/apim-unified-ai-gateway-sample/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/azure-samples/apim-unified-ai-gateway-sample/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01404 | $0.01404 |
| Opus 5 | $0.00702 | $0.00702 |
| Sonnet 5 | $0.00281 | $0.00281 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
APIM-Unified-AI-Gateway-Sample 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 9d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Instructions
This file provides guidance to GitHub Copilot when working on code changes in this repository.
Repository Context - SAMPLE/DEMO
This is a SAMPLE repository designed for learning and demonstration purposes.
- NOT a production application - Does not implement production-level security, scalability, or reliability patterns
- Fresh deployments only - Users deploy with
azd upto create new infrastructure from scratch - No existing state - There is no production data, no existing users, no live infrastructure to preserve
- No migration scenarios - Users tear down and redeploy; there is nothing to migrate from
- Breaking changes welcome - Each deployment is independent; no backward compatibility needed
- Simplified patterns - Prioritizes clarity and learning over enterprise complexity
When implementing changes:
- Focus on clean, understandable code that demonstrates concepts
- Do NOT add enterprise patterns (feature flags, gradual rollouts, A/B testing) unless specifically requested
- Do NOT plan migration phases or assume existing infrastructure
- Do NOT add production hardening unless it's core to the feature being demonstrated
Project Knowledge
Deployment Model
This sample uses Azure Developer CLI (azd) to provision infrastructure via Terraform:
main.tfvars.jsondefines variable values for azd- azd passes these values to Terraform via
variables.tf
CRITICAL: Variable names must match exactly (case-sensitive) between main.tfvars.json and variables.tf.
main.tfvars.json variables.tf
───────────────── ────────────────
"resourceGroup" → variable "resourceGroup"
"location" → variable "location"
Tech Stack
- Infrastructure as Code: Terraform >= 1.7.0, Azure Resource Manager (ARM)
- Cloud Platform: Microsoft Azure
- Azure API Management (APIM)
- Azure AI Foundry (AI Services API 2025-06-01)
- Azure OpenAI Service (GPT-4o, GPT-4o-mini)
- Azure Cognitive Services
- Azure Application Insights
- Azure Entra ID (formerly Azure AD)
- Terraform Providers: azurerm ~> 3.114, azuread ~> 2.49, azapi >= 2.7.0, random ~> 3.6, local ~> 2.5
- DevOps & Automation: Azure Developer CLI (azd), PowerShell 7+, REST Client
- AI Models & APIs:
- Azure OpenAI (GPT-4o, GPT-4o-mini)
- Azure AI Foundry (Phi-4 model v7)
- Google Gemini 2.0 Flash (external API)
- API Management: Circuit breakers, load balancing, JWT authentication, managed identities
- Policy Languages: APIM policy XML (C# 7 syntax compliant)
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.
- 9d ago First seen · 135 lines · 1,404 tokens per session scan A c88052932c6d
APIM-Unified-AI-Gateway-Sample copilot-instructions.md is an instructions file published in the GitHub repository Azure-Samples/APIM-Unified-AI-Gateway-Sample (14 stars, last pushed 5mo ago), licensed MIT. It adds 1,404 tokens to every session, about $0.0070 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.