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 agentmods add instructions/microsoft/agent365-python/claude-mdgit clone --depth 1 https://github.com/microsoft/Agent365-pythonWhat 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 | $0.02689 | $0.02689 |
| Opus 5 | $0.01345 | $0.01345 |
| Sonnet 5 | $0.00538 | $0.00538 |
| Haiku 4.5 | $0.00269 | $0.00269 |
Grade A, and why
Agent365-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 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.
How it starts
The opening of the file, as written. The whole thing — 292 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.
Project Overview
Microsoft Agent 365 SDK for Python - Enterprise-grade extensions for building production-ready AI agents for M365, Teams, Copilot Studio, and Webchat. This is a multi-package monorepo organized as a uv workspace with 13 interdependent packages.
Python Version: 3.11+ (3.11 and 3.12 tested in CI)
For detailed architecture and design documentation, see docs/design.md, which includes:
- Complete package descriptions and usage examples
- Design patterns (Singleton, Context Manager, Builder, Result, Strategy)
- Data flow diagrams for agent invocation tracing and MCP tool discovery
- Configuration options and environment variables
- Per-package design documents in
libraries/<package-name>/docs/design.md
Development Commands
Setup
# Create and activate virtual environment
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
# Install dependencies (locks and syncs all workspace packages)
uv lock && uv sync --locked --all-extras --dev
Building
# Build all packages (requires version environment variable)
export AGENT365_PYTHON_SDK_PACKAGE_VERSION="0.1.0" # Windows: $env:AGENT365_PYTHON_SDK_PACKAGE_VERSION = "0.1.0"
uv build --all-packages --wheel
# Built wheels are output to dist/
Testing
# Run all unit tests (excludes integration tests)
uv run --frozen pytest tests/ -v --tb=short -m "not integration"
# Run specific test file
uv run --frozen pytest tests/runtime/test_environment_utils.py -v
# Run tests matching pattern
uv run --frozen pytest tests/ -k "environment" -v
# Run integration tests (requires secrets/environment variables)
uv run --frozen pytest -m integration -v --tb=short
# Run with coverage report
pytest tests/ --cov=libraries --cov-report=html -v
Test markers:
unit: Fast, mocked tests (default)integration: Slow tests requiring real services/API keys
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.
- yesterday First seen · 292 lines · 2,689 tokens per session scan A a72fbfefd1ea
Agent365-python CLAUDE.md is an instructions file published in the GitHub repository microsoft/Agent365-python (41 stars, last pushed 6d ago), licensed MIT. It adds 2,689 tokens to every session, about $0.0134 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.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.