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/dotnet-presentations/ai-workshop/copilot-instructionsgit clone --depth 1 https://github.com/dotnet-presentations/ai-workshopWhat 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 | $0.01712 | $0.01712 |
| Opus 5 | $0.00856 | $0.00856 |
| Sonnet 5 | $0.00342 | $0.00342 |
| Haiku 4.5 | $0.00171 | $0.00171 |
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.
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 |
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.
- 2d ago First seen · 68 lines · 1,712 tokens per session scan A 4dd0d36d649d
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.
Other instructions, from other repositories
mcp-for-beginners AGENTS.md
Instructions for microsoft/mcp-for-beginners, covering agents.md, project overview, key technologies, architecture and setup commands.
quarkus-workshop-langchain4j AGENTS.md
Instructions for quarkusio/quarkus-workshop-langchain4j, covering agents.md, project overview, technology stack, project structure and building and running.
Foundry-Local-Lab AGENTS.md
Instructions for microsoft-foundry/Foundry-Local-Lab, covering coding agent instructions, project overview, repository structure, language & framework details and python.
n8n-skills CLAUDE.md
Instructions for czlonkowski/n8n-skills, covering claude.md, project overview, repository structure, the 14 skills and 1. n8n expression syntax.
Tutorial_AwesomeModernCPP AGENTS.md
Instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
Fluence.Wpf AGENTS.md
AGENTS.md instructions for sintaxasn/Fluence.Wpf, covering fluence.wpf - developer handbook, 1. project overview, solution layout, clr namespaces and 2. coding standards.