index

A reference for built-in Agent Framework capabilities, including handling images, returning structured data, retrieving application knowledge, and running long responses.

In plain words
What is it for?
Use it when choosing or implementing features such as multimodal input, schema-based output, retrieval-augmented generation (using retrieved information to ground answers), declarative agents, or background responses.
Why use it?
It helps developers identify which optional capabilities fit an agent without searching through unrelated framework documentation.

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/index
Clone the repo
git clone --depth 1 https://github.com/managedcode/dotnet-skills
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 653 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 $0.00023 $0.00653
Opus 5 $0.00012 $0.00327
Sonnet 5 $0.00005 $0.00131
Haiku 4.5 $0.00002 $0.00065

Measured yesterday against content hash 224c64ba157a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

index 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/agents/index.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent capabilities

Agent capabilities are opt-in features that extend what an agent can understand, produce, retrieve, execute, observe, or secure. For the runtime, type, conversation, and middleware foundations behind these features, see Agents.

Agent types and model connections

Looking for the agent-type and SDK-selection guidance previously hosted on this page?

  • Agent concepts explains application-owned chat-client agents, custom agents, and remote agent types.
  • Model providers compares inference providers, conversation-history support, and .NET SDK and endpoint options.
  • Agent services covers managed and protocol-backed remote agent runtimes.

Input and output

Capability Purpose
Multimodal Send images and other supported content to an agent.
Structured outputs Return values that conform to a schema or application type.
Background responses Continue, poll, and reconnect to long-running responses.

Context and knowledge

Capability Purpose
RAG Ground responses with retrieved application knowledge.
Declarative agents Define supported agents through YAML or JSON.
Agent Skills Discover and progressively load reusable instructions, resources, and scripts.

Execution and autonomy

Capability Purpose
Tools Let agents call functions and provider-hosted capabilities.
CodeAct Let the model write programs that coordinate tools through a managed execution provider.
Looping Re-run an agent until a bounded completion condition is met.
Background agents Delegate work to background agents and retrieve task results.
Planning and todos Track plans, operational todos, dependencies, and completion.

Read the full file on GitHub · 63 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 · 63 lines · 23 tokens per session scan A 224c64ba157a

Subscribe to this mod's changes

index is an agent published in the GitHub repository managedcode/dotnet-skills (477 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 653 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.