custom-agents

A guide to creating an AI agent by extending the framework’s base agent class and implementing its required behavior. It also explains sessions, which store the state and message history for a conversation.

In plain words
What is it for?
Use it to build custom agents, manage conversation sessions in memory or externally, and connect the agent to more complex application logic or AI services.
Why use it?
It provides a starting structure for agents that need custom logic instead of only the framework’s built-in behavior.

Agent

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 agents/managedcode/dotnet-skills/custom-agents
Clone the repo
git clone --depth 1 https://github.com/managedcode/dotnet-skills
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,746 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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.03746
Opus 5 $0.00005 $0.01873
Sonnet 5 $0.00002 $0.00749
Haiku 4.5 $0.00001 $0.00375

Measured yesterday against content hash 8ad9e51d18fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

custom-agents 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/references/official-docs/concepts/agents/custom-agents.md · 470 lines

How it starts

The opening of the file, as written. The whole thing — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Custom Agents

::: zone pivot="programming-language-csharp"

Microsoft Agent Framework supports building custom agents by inheriting from the AIAgent class and implementing the required methods.

This article shows how to build a simple custom agent that parrots back user input in upper case. In most cases building your own agent will involve more complex logic and integration with an AI service.

Getting Started

Add the required NuGet packages to your project.

dotnet add package Microsoft.Agents.AI.Abstractions --prerelease

Create a Custom Agent

The Agent Session

To create a custom agent you also need a session, which is used to keep track of the state of a single conversation, including message history, and any other state the agent needs to maintain.

To make it easy to get started, you can inherit from various base classes that implement common session storage mechanisms.

  1. InMemoryAgentSession - stores the chat history in memory and can be serialized to JSON.
  2. ServiceIdAgentSession - doesn't store any chat history, but allows you to associate an ID with the session, under which the chat history can be stored externally.

For this example, you'll use the InMemoryAgentSession as the base class for the custom session.

internal sealed class CustomAgentSession : InMemoryAgentSession
{
    internal CustomAgentSession() : base() { }
    internal CustomAgentSession(JsonElement serializedSessionState, JsonSerializerOptions? jsonSerializerOptions = null)
        : base(serializedSessionState, jsonSerializerOptions) { }
}

The Agent class

Next, create the agent class itself by inheriting from the AIAgent class.

internal sealed class UpperCaseParrotAgent : AIAgent
{
}

Constructing sessions

Sessions are always created via two factory methods on the agent class. This allows for the agent to control how sessions are created and deserialized. Agents can therefore attach any additional state or behaviors needed to the session when constructed.

Read the full file on GitHub · 470 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.

  1. yesterday First seen · 470 lines · 11 tokens per session scan A 8ad9e51d18fd

Subscribe to this mod's changes

custom-agents is an agent published in the GitHub repository managedcode/dotnet-skills (477 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 3,746 once invoked, about $0.0001 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.