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/leestott/generative-ui-foundry-hosted-agents/agents-mdgit clone --depth 1 https://github.com/leestott/generative-ui-foundry-hosted-agentsWrote 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.
[](https://agentmods.dev/instructions/leestott/generative-ui-foundry-hosted-agents/agents-md)<a href="https://agentmods.dev/instructions/leestott/generative-ui-foundry-hosted-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/leestott/generative-ui-foundry-hosted-agents/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.03510 | $0.03510 |
| Opus 5 | $0.01755 | $0.01755 |
| Sonnet 5 | $0.00702 | $0.00702 |
| Haiku 4.5 | $0.00351 | $0.00351 |
Grade A, and why
generative-ui-foundry-hosted-agents AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **CopilotKit v2 request envelope** (what the frontend sends and how to curl it): How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents (and humans) working in this repository. This documents the validated, working architecture and the conventions that keep it working. It reflects the state of a solution that has been deployed and verified end-to-end on Azure.
TL;DR: A Microsoft Agent Framework agent is hosted as a Foundry Hosted Agent speaking AG-UI over the
invocationsprotocol. A CopilotKit Node runtime on Azure App Service bridges the browser to the agent, and a React + CopilotKit frontend on Azure Static Web Apps renders the generative UI. Managed identity everywhere; no keys in code.
1. Architecture (the mental model)
Browser (React + CopilotKit) Azure Static Web Apps
│ POST /api/copilotkit (CopilotKit v2 method envelope)
▼
CopilotKit runtime (Node/Express) Azure App Service ← holds endpoint + token
│ AG-UI RunAgentInput (SSE back)
▼
Foundry Hosted Agent POST /invocations?api-version=v1 ← Microsoft Agent Framework
│ reason + call server tools, stream AG-UI events
▼
Azure OpenAI model deployment (Model Router)
Three deployable units, one open protocol (AG-UI) between each hop:
| Unit | Tech | Azure host | Talks |
|---|---|---|---|
agent/ |
.NET 10, Microsoft Agent Framework, AG-UI ASP.NET hosting | Foundry Hosted Agent (container) | receives AG-UI RunAgentInput, streams AG-UI SSE |
runtime/ |
Node/TypeScript, @copilotkit/runtime + @ag-ui/client |
Azure App Service (Linux, Node 20) | CopilotKit v2 ↔ AG-UI over Foundry invocations |
frontend/ |
Vite + React + CopilotKit | Azure Static Web Apps | CopilotKit v2 to /api/copilotkit (SWA-proxied) |
Why AG-UI over invocations: Foundry Hosted Agents pass the invocation body
through byte-for-byte and stream the response back, so a synchronous
POST /invocations → text/event-stream satisfies the contract. This lets the
Microsoft Agent Framework AG-UI host serve the platform directly — no custom
invocation handler required.
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 · 265 lines · 3,510 tokens per session scan A bdbea4d9fc1a
generative-ui-foundry-hosted-agents AGENTS.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 3,510 tokens to every session, about $0.0175 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
eShopLite copilot-instructions.md
Instructions for Azure-Samples/eShopLite, covering eshoplite copilot instructions, project overview, architecture & patterns, critical workflows and project-specific conventions.
eShopLite AGENTS.md
Instructions for Azure-Samples/eShopLite, covering agents.md, project overview, setup commands, prerequisites installation and install .net 10 sdk.
aspnetcore-realworld-example-app AGENTS.md
AGENTS.md instructions for realworld-apps/aspnetcore-realworld-example-app, covering repository guidance, toolchain, validation and development practices.
SSW.VerticalSliceArchitecture CLAUDE.md
Instructions for SSWConsulting/SSW.VerticalSliceArchitecture, covering ssw vertical slice architecture — agent instructions, project overview, technology stack, rules and skills.
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.
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.