Use them when implementing external triggers, scheduled or agent-initiated messages, conversation continuation, proactive HTTP endpoints, storage, or error handling.

They clarify which conversation data must be stored, which endpoint or method to call, and why a single message has less processing context than a continued conversation.

Agents-for-net proactive-messaging.instructions.md

Q: What is Agents-for-net proactive-messaging.instructions.md?

Instructions for proactive messaging in Microsoft Agents for .NET, where an agent sends a message outside the user's current request. They describe saved conversation references, HTTP triggers, in-code calls, and the different turn pipelines used to send or continue a conversation.

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/agents-for-net/proactive-messaging

Clone the repo

git clone --depth 1 https://github.com/microsoft/Agents-for-net

Made for: GitHub Copilot.

Per session 769 This file is loaded in full into every session.

When invoked 769 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	$0.00769	$0.00769
Opus 5	$0.00385	$0.00385
Sonnet 5	$0.00154	$0.00154
Haiku 4.5	$0.00077	$0.00077

Measured 2d ago against content hash 53fb1646fde7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Agents-for-net proactive-messaging.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.

.github/instructions/proactive-messaging.instructions.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Proactive Messaging Context

When working on proactive messaging, conversation continuation, or proactive HTTP endpoints, read docs/proactive-sequence-diagram.md for the full mermaid sequence diagrams covering all flows.

Key Design Points

Conversation storage is required for HTTP-triggered proactive flows. Proactive.StoreConversationAsync persists Conversation (Claims + ConversationReference) to IStorage under key proactive/conversations/{conversationId}.
Two invocation styles: HTTP endpoints (via MapAgentProactiveEndpoints) for external triggers, and in-code Proactive.ContinueConversationAsync / Proactive.SendActivityAsync for agent-initiated scenarios.
SendActivity is fire-and-send — it creates a minimal turn to deliver a single activity. ContinueConversation creates a full turn with TurnState, middleware, and optional token handling.
ProcessProactiveAsync on the adapter creates the full turn pipeline (state, middleware). This differs from the simpler ContinueConversationAsync on the adapter which only provides a raw TurnContext callback.
Exception handling — Exceptions inside proactive callbacks are captured via ExceptionDispatchInfo and re-thrown after the adapter call completes. Without this, exceptions in the background pipeline would be silently lost.
Token handling — [ContinueConversation(autoSignInHandlers: "me")] attribute triggers automatic token acquisition during proactive turns. If ProactiveOptions.FailOnUnsignedInConnections is true (default), UserNotSignedIn is thrown when tokens cannot be acquired.
HTTP query parameters are passed through as Activity.Value (dictionary) with ValueType = "application/vnd.microsoft.activity.continueconversation+json" on the continuation Event activity.
CreateConversation creates a new conversation on the channel (e.g., 1:1 in Teams) and optionally stores it and/or continues into it.

Endpoint Mapping

MapAgentProactiveEndpoints<TAgent>() discovers [ContinueConversation] attributes on the agent and maps:

/proactive/sendactivity/{conversationId} — send to stored conversation
/proactive/sendactivity — send with full Conversation in body
/proactive/continue[/{key}]/{conversationId} — continue stored conversation
/proactive/continue[/{key}] — continue with Conversation in body
/proactive/create[/{key}] — create new conversation

Read the full file on GitHub · 47 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.

2d ago First seen · 47 lines · 769 tokens per session scan A 53fb1646fde7

Subscribe to this mod's changes

Agents-for-net proactive-messaging.instructions.md is an instructions file published in the GitHub repository microsoft/Agents-for-net (177 stars, last pushed 4d ago), licensed MIT. It adds 769 tokens to every session, about $0.0038 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.

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens