agentmods.dev

eShopLite: Instructions file for GitHub Copilot

.github/copilot-instructions.md

eShopLite copilot-instructions.md is an instructions file for GitHub Copilot from Azure-Samples/eShopLite. It costs 1,022 tokens per session, scanned A, original, MIT.

Project instructions for eShopLite, a modular .NET Aspire reference online store. Each scenario is a separate runnable example that may include services such as APIs, databases, search, AI, or agent integrations.

In plain words
What is it for?
Use them when building or running a scenario, wiring services through the app host, adding search or AI features, or working with MCP and agent examples.
Why use it?
They explain how the scenarios are organized and how their services are connected, making it easier to run or extend the correct example.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is Azure-Samples/eShopLite's own configuration. It tells GitHub Copilot how to work on eShopLite itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything eShopLite configures →

not rated 169repo changed 9d ago A scan 1,022 tokens original MIT
View source ↗ Azure-Samples/eShopLite aka.ms
Reuse

Borrowing it

Nothing to install: this file belongs to Azure-Samples/eShopLite. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Azure-Samples/eShopLite/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/Azure-Samples/eShopLite

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for eShopLite copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/azure-samples/eshoplite/copilot-instructions/github.svg)](https://agentmods.dev/instructions/azure-samples/eshoplite/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/azure-samples/eshoplite/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/azure-samples/eshoplite/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.

agentmods 80×15 button for eShopLite copilot-instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/azure-samples/eshoplite/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/azure-samples/eshoplite/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,022 This file is loaded in full into every session.
When invoked 1,022 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01022 $0.01022
Opus 5.5 $0.00409 $0.00409
Sonnet 5.5 $0.00204 $0.00204
Haiku 4.5 $0.00102 $0.00102

Measured 9d ago against content hash ec7212576969, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

eShopLite 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.

.github/copilot-instructions.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

eShopLite Copilot Instructions

Project Overview

eShopLite is a modular Aspire-based reference eCommerce platform demonstrating advanced AI, search, and orchestration patterns. Each scenario in scenarios/ is a self-contained solution, often integrating Azure, OpenAI, vector DBs, and/or agent protocols.

Architecture & Patterns

  • Scenario-driven: Each folder in scenarios/ is a complete, runnable solution (see its README for details). Common patterns include:
    • AppHost Orchestration: All services (APIs, DBs, agents) are composed in eShopAppHost using Aspire's builder API.
    • Service Boundaries: Projects like Products, Store, and VectorEntities are reused across scenarios.
    • AI Integration: Semantic search, embeddings, and chat use Azure OpenAI, DeepSeek, or Chroma DB, configured via user-secrets or Aspire resource bindings.
    • Agent/MCP Patterns: Some scenarios (e.g., 06-mcp, 07-AgentsConcurrent) use Model Context Protocol or Semantic Kernel for tool/function calling and agent orchestration.

Critical Workflows

  • Build/Run:
    • Always run from the scenario's src/eShopAppHost using dotnet run (or the provided VS Code task).
    • For Azure deployment, use azd up from the scenario root after azd auth login.
    • Local dev often requires Docker/Podman for containerized DBs (e.g., Chroma, SQL 2025).
  • Configuration:
    • Azure/OpenAI endpoints and keys are injected via user-secrets (see scenario README for exact keys).
    • Aspire auto-wires service URLs and credentials for local and cloud.
  • Testing:
    • Unit/integration tests are in Products.Tests, Store.Tests, etc. Run with dotnet test from the scenario's src.
  • Telemetry:
    • Aspire Dashboard and Azure Application Insights are integrated for all scenarios. Access dashboard URLs from console output after launch.

Project-Specific Conventions

  • Aspire: All orchestration is done in eShopAppHost/Program.cs using the Aspire builder API. Services are referenced by logical names (e.g., products, store, sql).
  • User Secrets: For local dev, always set connection strings using dotnet user-secrets in the relevant project directory.
  • Azure Integration:
    • Use CredentialSource: AzureCli for local Azure auth.
    • Resource provisioning is handled by Aspire or Bicep files in infra/.
  • AI/Vector DBs:
    • Embedding and search clients are registered in code with AddAzureOpenAIClient, AddAzureSearchClient, or Chroma DB client.
    • For custom models (DeepSeek, GPT-4o, etc.), update connection strings and model names as shown in scenario READMEs.
  • Agent/MCP:
    • MCP tools are registered via attributes and exposed to LLMs for function calling.
    • Agent orchestration (e.g., concurrent analysis) is implemented using Semantic Kernel or MCP SDK.

Read the full file on GitHub · 62 lines

Changes

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.

  1. 9d ago Changed · -5 tokens per session ec7212576969
  2. 2mo ago First seen · 62 lines · 1,027 tokens per session scan A fc519c89c611

Subscribe to this mod's changes

eShopLite copilot-instructions.md is an instructions file published in the GitHub repository Azure-Samples/eShopLite (169 stars, last pushed 6d ago), licensed MIT. It adds 1,022 tokens to every session, about $0.0041 per session on Opus 5.5. 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.

E-commerceaspireazdazd-templatesazure-openaichromadbdeepseek-r1
Related

eShopLite copilot-instructions.md compared with instructions from other repositories

eShopLite copilot-instructions.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
eShopLite copilot-instructions.mdAzure-Samples/eShopLiteInstructions file1696d agoMITA1,022GitHub Copilot
vibetags com-example-service-OrderService.instructions.mdPIsberg/vibetagsInstructions file25todayMITA553GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot