What is Agents-for-python CLAUDE.md?

Repository instructions for Microsoft's Python Agents SDK, a framework for building conversational agents for Microsoft 365, Teams, and related platforms. They describe the codebase, setup process, and editable installation of its libraries.

Use them when setting up the project, installing its Python libraries for development, or making changes to the Microsoft 365 Agents SDK.

They give Claude Code the project context and setup rules needed to work on the repository correctly.

How microsoft/Agents-for-python configures Claude Code

About the project

microsoft/Agents-for-python is a Python SDK for building full-stack, multichannel agents that handle conversations, coordinate requests, generate responses, and work with other agents. It is intended for developers creating agent experiences for Microsoft 365, Teams, Copilot Studio, Webchat, and listed third-party messaging platforms. The catalogue entry provides setup or usage guidance for the SDK.

microsoft/Agents-for-python · 216 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to microsoft/Agents-for-python. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/microsoft/Agents-for-python/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/microsoft/Agents-for-python

Made for: Claude Code.

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/instructions/microsoft/agents-for-python/claude-md/github.svg)](https://agentmods.dev/instructions/microsoft/agents-for-python/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/microsoft/agents-for-python/claude-md"><img src="https://agentmods.dev/badge/instructions/microsoft/agents-for-python/claude-md/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/instructions/microsoft/agents-for-python/claude-md"><img src="https://agentmods.dev/badge/instructions/microsoft/agents-for-python/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,895 This file is loaded in full into every session.

When invoked 2,895 The same file — it is already loaded in full.

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	$0.02895	$0.02895
Opus 5.5	$0.01158	$0.01158
Sonnet 5.5	$0.00579	$0.00579
Haiku 4.5	$0.00290	$0.00290

Measured 2mo ago against content hash c28d6e516f49, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Agents-for-python CLAUDE.md 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 2mo 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.

CLAUDE.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Repository Overview

This is the Microsoft 365 Agents SDK for Python, a framework for building enterprise-grade conversational agents for M365, Teams, Copilot Studio, and other platforms. The SDK replaces the legacy Bot Framework SDK (botbuilder packages) with a modern, modular architecture.

Important: Python imports use underscores (microsoft_agents), not dots (microsoft.agents).

Development Setup

Initial Setup

Quick setup (Linux/macOS):

. ./scripts/dev_setup.sh

Quick setup (Windows):

. ./scripts/dev_setup.ps1

Manual setup (from repository root):

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install all libraries in editable mode
pip install -e ./libraries/microsoft-agents-activity/ --config-settings editable_mode=compat
pip install -e ./libraries/microsoft-agents-hosting-core/ --config-settings editable_mode=compat
pip install -e ./libraries/microsoft-agents-authentication-msal/ --config-settings editable_mode=compat
pip install -e ./libraries/microsoft-agents-authentication-entra-auth-sidecar/ --config-settings editable_mode=compat
pip install -e ./libraries/microsoft-agents-copilotstudio-client/ --config-settings editable_mode=compat
pip install -e ./libraries/microsoft-agents-hosting-aiohttp/ --config-settings editable_mode=compat
pip install -e ./libraries/microsoft-agents-hosting-teams/ --config-settings editable_mode=compat
pip install -e ./libraries/microsoft-agents-storage-blob/ --config-settings editable_mode=compat
pip install -e ./libraries/microsoft-agents-storage-cosmos/ --config-settings editable_mode=compat
pip install -e ./libraries/microsoft-agents-hosting-fastapi/ --config-settings editable_mode=compat

# Install development dependencies
pip install -r dev_dependencies.txt

# Setup pre-commit hooks
pre-commit install

Python version: Requires Python 3.10+, supports 3.10-3.14. Recommended: Python 3.11+

Read the full file on GitHub · 365 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.

2mo ago First seen · 365 lines · 2,895 tokens per session scan A c28d6e516f49

Subscribe to this mod's changes

Agents-for-python CLAUDE.md is an instructions file published in the GitHub repository microsoft/Agents-for-python (216 stars, last pushed yesterday), licensed MIT. It adds 2,895 tokens to every session, about $0.0116 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 2026-08-30.

Agents-for-python CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Agents-for-python CLAUDE.mdmicrosoft/Agents-for-python	Instructions file	216	yesterday	MIT	A	2,895	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Agents-for-python: Instructions file for Claude Code