What is msaf-architect?

A C# architecture guide for Microsoft Agent Framework, a .NET toolkit for building workflows where multiple AI agents or components collaborate.

Use it to resolve the project’s installed package version and design or debug executors, workflow connections, checkpoints, and human approval steps with matching APIs.

The framework’s APIs vary by package version, and examples for the wrong version may not work.

msaf-architect — Skill for Claude Code by hiadamhere

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.

Any agent

npx skills add hiadamhere/skills --skill msaf-architect

Clone the repo

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

Made for: Claude Code.

Or install agent-skills, the plugin that ships this one along with the rest of its 6 skills.

Its marketplace also offers this one on its own, as the plugin msaf-architect — /plugin install msaf-architect after adding the marketplace above.

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/skills/hiadamhere/skills/msaf-architect/github.svg)](https://agentmods.dev/skills/hiadamhere/skills/msaf-architect)

Your own site

<a href="https://agentmods.dev/skills/hiadamhere/skills/msaf-architect"><img src="https://agentmods.dev/badge/skills/hiadamhere/skills/msaf-architect/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hiadamhere/skills/msaf-architect"><img src="https://agentmods.dev/badge/skills/hiadamhere/skills/msaf-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,927 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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	$0.00155	$0.01927
Opus 5	$0.00077	$0.00963
Sonnet 5	$0.00031	$0.00385
Haiku 4.5	$0.00015	$0.00193

Measured 4d ago against content hash 9f20060b30bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

msaf-architect 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 4d 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.

skills/msaf-architect/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🏛️ Microsoft Agent Framework (MAF) C# Architect Skill

This skill embeds the architectural guidelines, design principles, and API mappings for building multi-agent systems using the Microsoft Agent Framework (MAF).

🧭 Getting Started: Version Resolution

The Workflows layer was API-stable across v1.10–v1.14, adds members in v1.15, v1.16 and v1.19, and is unchanged in v1.17, v1.18 and v1.20; the agent layer (Microsoft.Agents.AI) changes between the earlier releases, adds again in v1.18 and v1.19, and adds a single property in v1.20 — and stale tutorials/model memory describe APIs that were never shipped (e.g. WorkflowSuspendedException). Resolve the version, then trust only the matching reference page and the version map.

Resolve the version. Read the project's .csproj or dependency files for the installed Microsoft.Agents.AI.Workflows / Microsoft.Agents.AI version.
- Note: a project referencing Microsoft.Agents.Builder or Microsoft.Agents.Hosting.AspNetCore (v1.6.x) belongs to the separate Microsoft 365 Agents SDK — this skill does not apply to it.
Check feature availability in the Version Compatibility Matrix: which versions have the feature, and which cells are MAAI001-gated.
Read the one page your task needs, from the folder matching the resolved version.

Your task	Page
Build an agent: `ChatClientAgent` construction, sessions, workflow binding, modes	`agent-layer-core.md`
Wrap an agent: approval middleware, concurrent invocation, per-session routing	`agent-middleware.md` (v1.19+)
Background agents: releasing a session, the wait-tool timeout	`background-agents.md` (v1.20+)
Autonomous iteration: `LoopAgent` and loop evaluators	`agent-loops.md`
Agent skills, tool approval, file stores	`agent-skills.md`
Keep a long conversation inside the window	`context-compaction.md`
Write an executor: message handlers, protocol configuration	`declarative-executors.md`
Human-in-the-loop, request ports, Magentic manager-led planning	`hitl-and-routing.md`
Choose an orchestration: sequential, concurrent, group chat, handoff	`orchestration-patterns.md`
Ship it: streaming, observability, error handling, cancellation	`production-readiness.md`
Workflow state, scopes, checkpoint stores	`state-and-persistence.md`
Host a workflow as an agent: `AsAIAgent`, checkpoint redirection, run recovery	`workflow-hosting.md` (v1.19+)
Observe a run: the event taxonomy and typed output	`workflow-events.md`

Read the full file on GitHub · 73 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.

4d ago Changed 9f20060b30bf
5d ago Changed · +18 lines · +15 tokens per session 2ca9f2bfd8d1
9d ago First seen · 55 lines · 140 tokens per session scan A 4c804ec84309

Subscribe to this mod's changes

msaf-architect is a skill published in the GitHub repository hiadamhere/skills (2 stars, last pushed 4d ago), licensed MIT. It adds 155 tokens to every session and 1,927 once invoked, about $0.0008 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.

Building agents C# and .NET Languages

build-and-test

How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.

microsoft/agent-framework · 26 tokens

dotnet-reverse

A guide for analyzing compiled .NET and C# programs, including managed Windows executables and libraries. Reverse engineering means studying compiled software to understand how it works, and decompiling turns it back into readable approximate source code.

zhaoxuya520/reverse-skill · 144 tokens

agui-dotnet-streaming-chat

Get started with the AG-UI .NET SDK: bootstrap and run your first streaming-chat app (client + server) with the AG-UI .NET NuGet packages (AGUI.Client, AGUI.Server, AGUI.Formatting, AGUI.Abstractions). USE FOR: which packages to install and how to wire them; constructing an AGUIChatClient against an endpoint and…

ag-ui-protocol/ag-ui · 223 tokens

azure-mgmt-apicenter-dotnet

Azure API Center SDK for .NET. Centralized API inventory management with governance, versioning, and discovery. Use for creating API services, workspaces, APIs, versions, definitions, environments, deployments, and metadata schemas. Triggers: "API Center", "ApiCenterService", "ApiCenterWorkspace", "ApiCenterApi", "API…

microsoft/skills · 97 tokens

migrate-xunit-to-xunit-v3

Migrate .NET test projects from xUnit.net v2 to xunit.v3 and fix v3 breaks. Use for package/CPM conversion, OutputType=Exe, preserving the VSTest or MTP runner (including projects currently using YTest.MTP.XUnit2), incompatible TFMs, async void tests, string-to-Type attributes, custom Fact/Theory/BeforeAfterTest…

dotnet/skills · 149 tokens

platform-detection

Identify a .NET project's test platform, framework, command mode, and SDK-style vs classic project system. Use only for "which test platform/framework?", "VSTest or MTP?", or "what runner does this project use?", including bridge settings, UseVSTest opt-outs, and incompatible or conflicting VSTest/MTP configuration.…

dotnet/skills · 146 tokens