ai-workshop copilot-instructions.md

Instructions for a .NET AI workshop repository: a one-day teaching project made of self-contained lessons and working code examples using .NET 10 and Microsoft Foundry, Microsoft's platform for building generative-AI applications.

In plain words
What is it for?
Use it when editing, building, or testing this specific .NET AI workshop and its lessons, examples, or deployment material.
Why use it?
It keeps lesson folders, code snapshots, naming, builds, and tests consistent across the workshop. That makes the teaching materials easier to follow and verify from setup through deployment.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/dotnet-presentations/ai-workshop/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/dotnet-presentations/ai-workshop

Made for: GitHub Copilot.

Per session 1,712 This file is loaded in full into every session.
When invoked 1,712 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01712 $0.01712
Opus 5 $0.00856 $0.00856
Sonnet 5 $0.00342 $0.00342
Haiku 4.5 $0.00171 $0.00171

Measured 2d ago against content hash 4dd0d36d649d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-workshop 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 2d 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 · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

.NET AI Workshop

Teaching repository for a one-day .NET AI workshop. Content is 11 self-contained parts, each a top-level Part NN - <Name>/ folder containing a README.md (the lab instructions) and, where applicable, a working code snapshot. Folder names are zero-padded so they sort correctly in the GitHub web UI; prose and headings use the unpadded "Part N" form.

Everything targets .NET 10 and uses Microsoft Foundry (Azure OpenAI) as the default provider.

Parts and code snapshots

Part Snapshot project Notes
01 - Setup README only
02 - Build Chat App ChatApp/ Console app built by hand (dotnet new console)
03 - Add RAG RagChatApp/ Continues from Part 2; checkpoints/ holds two alternate Program.cs paths (manual cosine similarity, and MEDI + SqliteVec). checkpoints/verify/ holds compile-only projects so CI type-checks both checkpoints — the snapshot itself is the Step 2 manual path
04 - AI Web Chat Template (shares Part 11 - Deployment/GenAiLab/) README only in this folder; scaffolds GenAiLab with dotnet new aichatweb. The completed code deliberately lives in Part 11 rather than being duplicated here — keep both READMEs saying so
05 - MCP Server Basics MyMcpServer/ dotnet new mcpserver (template from Microsoft.McpServer.ProjectTemplates); RandomNumberTools + WeatherTools
06 - Enhanced MCP Server ContosoOrdersMcpServer/ Optional/bonus. Exploration of an existing snapshot — the README does not ask the user to scaffold it
07 - MCP Publishing Optional/bonus, README only
08 - Agent Framework Basics AgentApp/ dotnet new console + Microsoft.Agents.AI
09 - Adding AI to an Existing App eShopLite-start/ and eShopLite/ (5-project Aspire solutions) Capstone. eShopLite-start/ is the AI-free starting point attendees work in; eShopLite/ is the finished answer key. The workshop adds semantic search, grounded discovery, and a local-model assistant. Added code lives in Products/Ai/ and Store/Ai/
10 - Choosing Providers and Services README only. Sits immediately before deployment because provider and service selection is a deployment prerequisite
11 - Deployment GenAiLab/ (3-project Aspire solution) Same app as Part 4 plus WithExternalHttpEndpoints() in AppHost.cs. This is also the answer key for Part 4, so changes here must stay consistent with the Part 4 README

Read the full file on GitHub · 68 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. 2d ago First seen · 68 lines · 1,712 tokens per session scan A 4dd0d36d649d

Subscribe to this mod's changes

ai-workshop copilot-instructions.md is an instructions file published in the GitHub repository dotnet-presentations/ai-workshop (54 stars, last pushed 7d ago), licensed MIT. It adds 1,712 tokens to every session, about $0.0086 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.