background-agents

A way for one software agent to give separate tasks to named child agents that run at the same time. The main agent can later wait for, collect, continue, or clean up those tasks.

In plain words
What is it for?
Use it to split work such as code analysis, research, or other focused jobs into concurrent tasks, then retrieve their results for the main agent.
Why use it?
It removes the need to handle every independent task one after another in a single agent session. It also defines how delegated work is tracked and returned to the main agent.

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/background-agents
Clone the repo
git clone --depth 1 https://github.com/managedcode/dotnet-skills
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,880 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 $0.00021 $0.01880
Opus 5 $0.00010 $0.00940
Sonnet 5 $0.00004 $0.00376
Haiku 4.5 $0.00002 $0.00188

Measured 2d ago against content hash 8ca59ba2610a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

background-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 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.

catalog/Frameworks/Microsoft-Agent-Framework/skills/microsoft-agent-framework/references/official-docs/agents/background-agents.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Background agents

Background agents let a parent agent delegate independent tasks to named child agents. Each task runs concurrently in its own child-agent session, while the parent keeps a task ID that it can use to wait, retrieve results, continue work, or release the task.

[!IMPORTANT] Background agents are experimental.

Background agents are different from background responses. A background response represents one provider request that the application polls or resumes. A background-agent task invokes another Agent Framework agent and later feeds that agent's text result back to the parent.

Set up background agents manually

Each child agent must have a nonempty, case-insensitively unique name. Give child agents focused instructions and only the tools needed for their delegated role.

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

Import BackgroundAgentsProvider and add it to a regular agent through ChatClientAgentOptions.AIContextProviders:

using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;

var backgroundProvider = new BackgroundAgentsProvider(
    [webSearchAgent, codeAnalysisAgent]);

AIAgent parentAgent = chatClient.AsAIAgent(new ChatClientAgentOptions
{
    Name = "research-coordinator",
    AIContextProviders = [backgroundProvider],
});

AgentSession session = await parentAgent.CreateSessionAsync();

Read the full file on GitHub · 246 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. 2d ago First seen · 246 lines · 21 tokens per session scan A 8ca59ba2610a

Subscribe to this mod's changes

background-agents is an agent published in the GitHub repository managedcode/dotnet-skills (477 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 1,880 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.