Use them when editing the hosted agent, AG-UI and invocation routes, Docker configuration, CopilotKit bridge, React frontend, or Azure deployment setup.

They keep the agent, browser bridge, hosting endpoints, container port, and deployment setup aligned with the architecture that the sample expects.

generative-ui-foundry-hosted-agents copilot-instructions.md — Instructions file for GitHub Copilot by leestott: Project instructions for a f

Q: What is generative-ui-foundry-hosted-agents copilot-instructions.md?

Project instructions for a full-stack sample where a .NET AI agent sends interface updates to a React browser application through Azure services.

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/leestott/generative-ui-foundry-hosted-agents/copilot-instructions

Clone the repo

git clone --depth 1 https://github.com/leestott/generative-ui-foundry-hosted-agents

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/leestott/generative-ui-foundry-hosted-agents/copilot-instructions.svg)](https://agentmods.dev/instructions/leestott/generative-ui-foundry-hosted-agents/copilot-instructions)

Your own site

<a href="https://agentmods.dev/instructions/leestott/generative-ui-foundry-hosted-agents/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/leestott/generative-ui-foundry-hosted-agents/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>

Per session 916 This file is loaded in full into every session.

When invoked 916 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.

Model	Per session	Once invoked
Fable 5.1	$0.00916	$0.00916
Opus 5	$0.00458	$0.00458
Sonnet 5	$0.00183	$0.00183
Haiku 4.5	$0.00092	$0.00092

Measured 5d ago against content hash 190bdcc439ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

generative-ui-foundry-hosted-agents 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 5d 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 · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot instructions — Generative UI on Foundry Hosted Agents

These instructions apply repo-wide. They encode the validated architecture and the conventions that keep this solution working. See AGENTS.md for the full reference and docs/ for deep-dive playbooks.

What this repo is

A full-stack generative UI sample: a Microsoft Agent Framework (.NET 10) agent hosted as a Foundry Hosted Agent speaking AG-UI over the invocations protocol, bridged to the browser by a CopilotKit Node runtime on Azure App Service, with a React + CopilotKit frontend on Azure Static Web Apps.

Non-negotiable conventions

Agent hosting: use Microsoft.Agents.AI.Hosting.AGUI.AspNetCore (AddAGUI() + MapAGUI()). Build the agent with chatClient.AsIChatClient().AsAIAgent(instructions, name, tools). Never reintroduce the community AGUI.Server, a raw IChatClient loop, or a custom Azure.AI.AgentServer.Invocations handler.
.AsAIAgent is an extension on IChatClient — call .AsIChatClient() first.
Container: listen on :8088 (ASPNETCORE_URLS=http://+:8088 in the Dockerfile) and expose GET /readiness. Map AG-UI at both /invocations and /.
Invocations endpoint MUST include ?api-version=v1. Older api-versions 400.
Runtime route: mount the CopilotKit handler at the Express root and gate on req.path === "/api/copilotkit". A path-prefixed app.use(...) strips the prefix and CopilotKit's Hono basePath returns 404.
Auth: managed identity + DefaultAzureCredential everywhere. No API keys, connection strings, or tokens in code, config, or the browser.
CopilotKit v2 protocol: requests are method envelopes — {"method":"info"} and {"method":"agent/run","params":{"agentId":"analytics-agent"},"body":{<RunAgentInput>}}.

When editing code

agent/ — .NET 10, Microsoft.NET.Sdk.Web. Keep server tools registered via AIFunctionFactory.Create(...). Preserve Data/sales.csv as Content. Pinned package versions are intentional; bump deliberately, not incidentally.
runtime/ — TypeScript compiled with tsc to dist/. Run npm run build before deploy. Keep the lazy 503 when FOUNDRY_AGENT_ENDPOINT is unset and the /health endpoint.
frontend/ — Vite + React. Treat agent-supplied component props as untrusted; validate before rendering. runtimeUrl="/api/copilotkit".
infra/ — Bicep via azd. Managed identity, ACR (AcrPull), App Service, Static Web App, Foundry account + model, App Insights.

Read the full file on GitHub · 67 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.

5d ago First seen · 67 lines · 916 tokens per session scan A 190bdcc439ca

Subscribe to this mod's changes

generative-ui-foundry-hosted-agents copilot-instructions.md is an instructions file published in the GitHub repository leestott/generative-ui-foundry-hosted-agents (5 stars, last pushed 1mo ago), licensed MIT. It adds 916 tokens to every session, about $0.0046 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 2026-08-31.

ag-ui ai-agents asp-net-core azd azure-developer-cli azure-openai

eShopLite copilot-instructions.md

Instructions for Azure-Samples/eShopLite, covering eshoplite copilot instructions, project overview, architecture & patterns, critical workflows and project-specific conventions.

Azure-Samples/eShopLite · 1,027 tokens

eShopLite AGENTS.md

Instructions for Azure-Samples/eShopLite, covering agents.md, project overview, setup commands, prerequisites installation and install .net 10 sdk.

Azure-Samples/eShopLite · 3,633 tokens

aspnetcore-realworld-example-app AGENTS.md

AGENTS.md instructions for realworld-apps/aspnetcore-realworld-example-app, covering repository guidance, toolchain, validation and development practices.

realworld-apps/aspnetcore-realworld-example-app · 553 tokens

SSW.VerticalSliceArchitecture CLAUDE.md

Instructions for SSWConsulting/SSW.VerticalSliceArchitecture, covering ssw vertical slice architecture — agent instructions, project overview, technology stack, rules and skills.

SSWConsulting/SSW.VerticalSliceArchitecture · 1,020 tokens

chat-with-your-data-solution-accelerator copilot-instructions.md

Copilot instructions for Azure-Samples/chat-with-your-data-solution-accelerator, covering chat with your data (cwyd) — repository instructions, repository layout (truth), mandatory references — consult before editing, external pattern sources — read-only and hard rules.

Azure-Samples/chat-with-your-data-solution-accelerator · 8,430 tokens

ebi-agent-chat-relay CLAUDE.md

Claude Code instructions for ebibibi/ebi-agent-chat-relay, covering claude-code-discord-bridge (ccdb), framework vs instance, zero-config principle (critical), architecture and key design decisions.

ebibibi/ebi-agent-chat-relay · 6,623 tokens