Hosted_Agents_Workshop_dotNET AGENTS.md

Repository instructions for a beginner workshop about Microsoft Foundry hosted agents built with .NET 10. They cover documentation, code, testing, deployment, and user-interface exercises.

In plain words
What is it for?
They are for following the workshop's learning sequence, writing beginner-friendly documentation, implementing deterministic tools, building tests, and preparing Azure deployment work.
Why use it?
They give coding agents and contributors consistent rules for working in that repository.

Instructions file for CodexOpenCode

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/microsoft/hosted_agents_workshop_dotnet/agents-md
Clone the repo
git clone --depth 1 https://github.com/microsoft/Hosted_Agents_Workshop_dotNET

Made for: Codex, OpenCode.

Per session 474 This file is loaded in full into every session.
When invoked 474 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 $0.00474 $0.00474
Opus 5 $0.00237 $0.00237
Sonnet 5 $0.00095 $0.00095
Haiku 4.5 $0.00047 $0.00047

Measured 2d ago against content hash 98a32d113795, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Hosted_Agents_Workshop_dotNET AGENTS.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.

AGENTS.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file defines repository-level guidance for coding agents and contributors.

Repository Purpose

This repo is a beginner workshop for Microsoft Foundry hosted agents with .NET 10.

Primary learning flow:

  1. Local hosted agent setup and validation
  2. Copilot customization
  3. Deterministic tool implementation and tests
  4. CI validation
  5. Azure deployment flow
  6. UI integration and screenshot capture

General Rules

  • Keep instructions beginner-friendly and copy-paste ready.
  • Prefer placeholder values in docs over real subscription, tenant, endpoint, or registry identifiers.
  • Keep examples safe for public sharing.
  • Preserve the current lab sequence and avoid reordering labs without a clear reason.

Documentation Rules

  • Use short sections and simple language.
  • Include expected results for each lab step.
  • For any command that depends on user environment, show placeholders:
    • <account>
    • <project>
    • <your-acr-name>
  • If screenshots are referenced, ensure the files exist in labs/lab-5-ui/images.

Code and Build Rules

  • Target framework is .NET 10.
  • Keep deterministic business logic in src/WorkshopLab.Core.
  • Keep hosted agent host behavior in src/WorkshopLab.AgentHost.
  • Run tests when changing core logic:
dotnet test WorkshopLab.sln

UI Screenshot Workflow

When UI images need refresh for docs:

  1. Start the app:
dotnet run --project src/WorkshopLab.ChatUI --urls http://localhost:5075
  1. In another terminal, run screenshot capture:
npm run capture:screenshots

Expected outputs:

  • labs/lab-5-ui/images/01-chat-ui-landing.png
  • labs/lab-5-ui/images/02-chat-ui-prompt-entered.png
  • labs/lab-5-ui/images/03-chat-ui-response-hd.png

Public Sharing Checklist

Before publishing updates:

  • No hardcoded personal tenant IDs, subscription IDs, or project endpoints
  • No hardcoded personal ACR names
  • .gitignore includes local-only artifacts (for example node_modules/, local logs, debug outputs)
  • Beginner docs still read top-to-bottom without hidden assumptions

Read the full file on GitHub · 76 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 · 76 lines · 474 tokens per session scan A 98a32d113795

Subscribe to this mod's changes

Hosted_Agents_Workshop_dotNET AGENTS.md is an instructions file published in the GitHub repository microsoft/Hosted_Agents_Workshop_dotNET (23 stars, last pushed 7d ago), licensed MIT. It adds 474 tokens to every session, about $0.0024 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.