Microsoft Agent Framework is a multi-language framework for building, coordinating, and running AI agents and workflows in Python and .NET. Teams use it for agent systems that need orchestration, collaboration, durability, observability, governance, or human involvement beyond a single prompt or chat loop. Catalogue add-ons provide skills and instructions for working with the framework.
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.
npx skills add microsoft/agent-framework --skill agent-framework-builder-pythongit clone --depth 1 https://github.com/microsoft/agent-frameworkWrote 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.
[](https://agentmods.dev/skills/microsoft/agent-framework/agent-framework-builder-python)<a href="https://agentmods.dev/skills/microsoft/agent-framework/agent-framework-builder-python"><img src="https://agentmods.dev/badge/skills/microsoft/agent-framework/agent-framework-builder-python/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.
<a href="https://agentmods.dev/skills/microsoft/agent-framework/agent-framework-builder-python"><img src="https://agentmods.dev/badge/skills/microsoft/agent-framework/agent-framework-builder-python.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00076 | $0.01460 |
| Opus 5.5 | $0.00030 | $0.00584 |
| Sonnet 5.5 | $0.00015 | $0.00292 |
| Haiku 4.5 | $0.00008 | $0.00146 |
Grade A, and why
agent-framework-builder-python 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Framework builder for Python
Use this skill as the entry point for Python Agent Framework application work. Choose the smallest framework pattern that preserves the required behavior, load only the relevant references, and validate against current APIs instead of relying on remembered preview-era syntax.
Workflow
- Inspect the existing project, Python version, dependency manager, and installed Agent Framework packages.
- Choose the simplest matching path from the table below.
- Resolve design questions only when they materially change the implementation.
- Read only the linked reference for the selected path.
- Implement the smallest coherent change and run the narrowest validation that exercises it.
Core abstractions
- A chat client implements the model-facing
SupportsChatGetResponseprotocol. It sends messages and options to a model provider and returns chat responses or streaming updates. - An agent implements the
SupportsAgentRunprotocol. The standardAgentimplementation combines a chat client with instructions, tools, middleware, context providers, and session handling behind onerun(...)interface. - A harness agent is a regular
Agentassembled bycreate_harness_agent. It adds an opinionated set of context providers and middleware; it does not introduce a separate agent abstraction. - A workflow coordinates explicit execution paths. Graph workflows and most orchestration builders can use multiple
SupportsAgentRunimplementations or executors.HandoffBuilderis the exception: its participants must be concreteAgentinstances.
User interface options
- DevUI is a local development, testing, and debugging tool for interacting with agents and workflows. Never run or deploy DevUI as a production application host.
- AG-UI is the application-facing protocol integration for connecting an agent or workflow to an AG-UI-compatible
frontend. Use the
agent-framework-ag-uipackage when the product needs streaming UI events, tool interactions, shared state, interrupts, or resume behavior.
What ships with it
9 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.
- references/agent-builder.md 6.9 KB
- references/declarative.md 2.3 KB
- references/evaluation.md 1.9 KB
- references/extensibility.md 7.4 KB
- references/harness-agent-builder.md 2.9 KB
- references/hosting-and-deployment.md 3.4 KB
- references/integrations.md 2.7 KB
- references/observability.md 1.4 KB
- references/workflow-builder.md 2.9 KB
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.
- today First seen · 107 lines · 76 tokens per session scan A 25ea81bf217a
agent-framework-builder-python is a skill published in the GitHub repository microsoft/agent-framework (14,281 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 1,460 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-23.
Other skills, from other repositories
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
goga-cell-python
Python rules for implementing CODEMANIFEST contracts.
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
vigilante-issue-implementation-on-python
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Python repository with idiomatic tooling and security guidance.
goga-lang-disp
Detects the project language and dispatches execution to the matching language-specific skill. Apply this specification within the calling skill's context. Do not restate the contents — use them for decision-making.
python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).