Microsoft 365 Agents SDK is a C# and .NET software development kit for building agents that interact with users across Microsoft 365, Teams, Copilot Studio, Webchat, and selected third-party services. Developers use it to handle conversations, coordinate requests, generate responses, and enable collaboration between agents. The catalogue entries provide coding-agent instructions and agents for working with this SDK.
Borrowing it
Nothing to install: this file belongs to microsoft/Agents-for-net. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/Agents-for-net/main/.github/instructions/streaming-response.instructions.mdgit clone --depth 1 https://github.com/microsoft/Agents-for-netWrote 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/microsoft/agents-for-net/streaming-response)<a href="https://agentmods.dev/instructions/microsoft/agents-for-net/streaming-response"><img src="https://agentmods.dev/badge/instructions/microsoft/agents-for-net/streaming-response/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/microsoft/agents-for-net/streaming-response"><img src="https://agentmods.dev/badge/instructions/microsoft/agents-for-net/streaming-response.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00623 | $0.00623 |
| Opus 5.5 | $0.00249 | $0.00249 |
| Sonnet 5.5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
Agents-for-net streaming-response.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 27d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
StreamingResponse Context
When working on streaming message delivery, read docs/streaming-response-sequence-diagram.md for the full mermaid sequence diagrams covering all scenarios (streaming channels, non-streaming fallback, error handling).
Key Design Points
StreamingResponseis an internal class exposed viaITurnContext.StreamingResponse(created per-turn inTurnContext).- It sends intermediate Typing activities on a timer interval, giving the UX of a streamed message. Each intermediate contains the full accumulated text (not a delta).
- A final Message activity is sent with
StreamInfo.StreamType = FinalwhenEndStreamAsync()is called. - The timer is one-shot, re-armed after each successful send — prevents overlapping sends if
SendActivityAsynctakes longer thanInterval. - Non-streaming channels buffer all text and send a single normal message on
EndStreamAsync()— no timer runs. - Teams requires using the
Activity.Idreturned from the first send as theStreamIdfor all subsequent messages. ResetAsync()allows reusing the stream for multiple streaming sequences in one turn.
Channel Intervals
| Channel | Interval | Stream Start |
|---|---|---|
| Teams | 1000ms | StreamId from first response |
| WebChat / DirectLine | 500ms | Pre-generated GUID |
| DeliveryMode.Stream (SSE transport) | 100ms | Pre-generated GUID |
| M365 Copilot with DeliveryMode.Stream | 100ms | Pre-generated GUID; includes keep-alive and timeout fallback |
| Other / ExpectReplies | N/A | Non-streaming fallback |
Error Scenarios
- ContentStreamNotAllowed → user canceled on client; returns
UserCancelled - BadArgument + "streaming api is not enabled" → disables streaming for this turn (does not cancel)
- Other errors → cancels stream; returns
Error - M365 Copilot → while the queue is empty, sends an inactivity notice after 35 seconds from stream start or the last informative update; at 1 minute 45 seconds it stops streaming and falls back to normal final delivery
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.
- 27d ago Changed · +2 lines · +75 tokens per session 658bca40d0f4
- 2mo ago First seen · 48 lines · 548 tokens per session scan A e558f060ce79
Agents-for-net streaming-response.instructions.md is an instructions file published in the GitHub repository microsoft/Agents-for-net (183 stars, last pushed today), licensed MIT. It adds 623 tokens to every session, about $0.0025 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.