What is microsoft-agent-framework?

A development guide for Microsoft's .NET framework for building AI agents and workflows. It covers agents, conversations, tools, hosting, multi-agent coordination, and enterprise controls.

Building or reviewing .NET applications that use Microsoft Agent Framework, including tools, MCP connections, workflows, hosted agents, background work, monitoring, and supported model providers.

It helps developers choose an appropriate agent design and avoid adding AI autonomy where ordinary code or a fixed workflow is enough.

microsoft-agent-framework — Skill by managedcode

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 skills/managedcode/dotnet-skills/microsoft-agent-framework

Any agent

npx skills add managedcode/dotnet-skills --skill microsoft-agent-framework

Clone the repo

git clone --depth 1 https://github.com/managedcode/dotnet-skills

Made for: Claude Code, Codex.

Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,377 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00138	$0.03377
Opus 5	$0.00069	$0.01688
Sonnet 5	$0.00028	$0.00675
Haiku 4.5	$0.00014	$0.00338

Measured yesterday against content hash 4159b1270021, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

microsoft-agent-framework 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 yesterday.

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.

catalog/Frameworks/Microsoft-Agent-Framework/skills/microsoft-agent-framework/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microsoft Agent Framework

Trigger On

building or reviewing .NET code that uses Microsoft.Agents.*, Microsoft.Extensions.AI, AIAgent, HarnessAgent, AgentSession, or Agent Framework hosting packages
choosing between ChatClientAgent, Responses agents, hosted agents, custom agents, Anthropic agents, workflows, or durable agents
adding the batteries-included Microsoft.Agents.AI.Harness surface for planning, todos, compaction, file memory/access, tool approvals, skills, shell execution, or background agents
authoring preview-era Microsoft.Agents.AI.Workflows.Declarative* packages or wrapping a workflow with workflow.AsAIAgent()
adding tools, MCP, A2A, OpenAI-compatible hosting, AG-UI, DevUI, background responses, or OpenTelemetry
migrating from Semantic Kernel agent APIs or aligning AutoGen-style multi-agent patterns to Agent Framework
using Anthropic Claude models (haiku, sonnet, opus) via AnthropicClient or through Azure Foundry with AnthropicFoundryClient

Workflow

Decide whether the problem should stay deterministic. If plain code or a typed workflow without LLM autonomy is enough, do that instead of adding an agent.
Choose the execution shape first: single AIAgent, batteries-included HarnessAgent, explicit programmatic Workflow, workflow-as-agent wrapper, declarative workflow when YAML portability is explicitly required, Azure Functions durable agent, ASP.NET Core hosted agent, AG-UI remote UI, or DevUI local debugging.
Choose the agent type and provider intentionally. Prefer the simplest agent that satisfies the threading, tooling, and hosting requirements.
Keep agents stateless and keep conversation or long-lived state in AgentSession. Treat the session as opaque provider-owned state, serialize it through the owning agent, and never accept a raw service conversation ID as an end-user authorization boundary.
Add only the tools and middleware that the scenario needs. Narrow the tool surface, require approval for side effects, and treat MCP, A2A, and third-party services as trust boundaries.
For workflows, model executors, edges, typed RequestPort boundaries, checkpoints, shared state, and human-in-the-loop explicitly rather than hiding control flow in prompts.
Prefer Responses-based protocols for new remote/OpenAI-compatible integrations unless you specifically need Chat Completions compatibility.
Use durable agents only when you truly need Azure Functions serverless hosting, durable thread storage, or deterministic long-running orchestrations.
Verify preview status, package maturity, docs recency, and provider-specific limitations before locking a production architecture.

Read the full file on GitHub · 146 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

yesterday First seen · 146 lines · 138 tokens per session scan A 4159b1270021

Subscribe to this mod's changes

microsoft-agent-framework is a skill published in the GitHub repository managedcode/dotnet-skills (477 stars, last pushed 2d ago), licensed MIT. It adds 138 tokens to every session and 3,377 once invoked, about $0.0007 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.

Data and AI claude-code codex copilot dotnet dotnet-skills skills

winui-ui-testing

Automated UI testing for Windows desktop apps — generate a batch test script with the winapp ui UI Automation harness, run all tests in one pass, read results. Covers element assertions, interactions, value checking (TextBox, ComboBox, ToggleSwitch), keyboard shortcuts and typing (send-keys), hover, drag-and-drop…

microsoft/win-dev-skills · 122 tokens

pr-review

Multi-dimensional review of a PR or feature branch in microsoft/win-dev-skills. Activate on "review my PR / changes / branch", "vet before pushing", "PR review", "is this ready to merge". Fans out parallel sub-agents over skill content, the skill-vs-tool boundary (solution hierarchy), tool correctness…

microsoft/win-dev-skills · 98 tokens

winui-design

Use when designing, reviewing, or fixing WinUI 3: sample and control discovery with winapp find-ui, layout planning, control choice, Fluent Design alignment, Light/Dark/High Contrast theming, typography, spacing, brushes, accessibility, and XAML data-binding design. Load before authoring new XAML, reviewing UI PRs…

microsoft/win-dev-skills · 119 tokens

winui-dev-workflow

Build and run workflow for WinUI 3 apps with WinApp CLI 0.6+ — project creation with winapp new, project-mode winapp run, BuildAndRun.ps1 analyzer integration, crash diagnosis, and prerequisites. Use when creating, building, running, or fixing build errors in a WinUI 3 project.

microsoft/win-dev-skills · 73 tokens

winui-packaging

MSIX packaging, code signing, and distribution for WinUI 3 apps — build for release, certificate generation (winapp cert generate), certificate trust, code signing (winapp sign), self-contained deployment, CI/CD with GitHub Actions, and Microsoft Store submission. Use when preparing for release, creating MSIX…

microsoft/win-dev-skills · 86 tokens

winui-session-report

Analyze the current or a recent agent session (GitHub Copilot CLI or Claude Code) and generate a diagnostic report. Use only when the user explicitly asks for session feedback, agent debugging, or a review of what happened during a build session. Do not inspect session data automatically.

microsoft/win-dev-skills · 61 tokens