python-package-management

Instructions for managing Python packages in a monorepo, a single repository containing multiple related packages, for the Agent Framework. It covers dependencies, versions, new connector packages, and lazy loading, where code is loaded only when needed.

In plain words
What is it for?
Create or modify connector packages, manage dependencies and lockfiles with uv, set up development environments, and prepare package releases.
Why use it?
It gives package changes a consistent structure and reduces dependency, versioning, and installation mistakes across the repository.

Skill for Claude CodeCodex

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 skills/microsoft/agent-framework/python-package-management
Any agent
npx skills add microsoft/agent-framework --skill python-package-management
Clone the repo
git clone --depth 1 https://github.com/microsoft/agent-framework

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,057 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 $0.00043 $0.03057
Opus 5 $0.00022 $0.01528
Sonnet 5 $0.00009 $0.00611
Haiku 4.5 $0.00004 $0.00306

Measured yesterday against content hash 016c91212e5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

python-package-management 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.

python/.github/skills/python-package-management/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Python Package Management

Monorepo Structure

python/
├── pyproject.toml              # Root package (agent-framework)
├── packages/
│   ├── core/                   # agent-framework-core (main package)
│   ├── foundry/                # agent-framework-foundry
│   ├── anthropic/              # agent-framework-anthropic
│   └── ...                     # Other connector packages
  • agent-framework-core contains core abstractions and OpenAI/Azure OpenAI built-in
  • Provider packages extend core with specific integrations
  • Root agent-framework depends on agent-framework-core[all]

Dependency Management

Uses uv for dependency management and poethepoet for task automation.

# Full setup (venv + install + prek hooks)
uv run poe setup

# Install dependencies from lockfile (frozen resolution with prerelease policy)
uv run poe install

# Create venv with specific Python version
uv run poe venv --python 3.12

# Intentionally upgrade a specific dependency to reduce lockfile conflicts
uv lock --upgrade-package <dependency-name> && uv run poe install

# Refresh exact development dependency-group pins, lockfile, and validation in one run
uv run poe upgrade-dev-dependencies

# Release cuts: refresh uv.lock and probe changed packages at both bound extremes.
# The release probe has a shared five-minute deadline.
uv run poe validate-python-release --base-ref upstream/main

# Exhaustive test+typing matrix (slow; use for deliberate dependency-range work or CI)
uv run poe validate-dependency-bounds-test
# Defaults to --package "*"; scope locally whenever possible.
uv run poe validate-dependency-bounds-test --package core

# Then expand bounds for one dependency in the target package
uv run poe validate-dependency-bounds-project --mode both --package core --dependency "<dependency-name>"

# Repo-wide automation can reuse the same task
uv run poe validate-dependency-bounds-project --mode upper --package "*"

# Add a dependency to one project and run both validators for that project/dependency
uv run poe add-dependency-and-validate-bounds --package core --dependency "<dependency-spec>"

Read the full file on GitHub · 266 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 · 266 lines · 43 tokens per session scan A 016c91212e5a

Subscribe to this mod's changes

python-package-management is a skill published in the GitHub repository microsoft/agent-framework (13,222 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 3,057 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

swarmclaw

AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.

swarmclawai/swarmclaw · 67 tokens

agent-collaboration

Use this skill when coordinating multiple AI agents. Covers multi-agent patterns, handoffs, and orchestration strategies.

ApexIQ/skillsmith · 27 tokens

crewai-multi-agent

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…

davila7/claude-code-templates · 61 tokens

strands-review

Local preview of the strands-agents/devtools /strands review agent. Body is the upstream Task Reviewer SOP verbatim — do not paraphrase. Use when the user types /strands-review, asks for a "strands review" of a PR, or wants to anticipate what the remote /strands review GitHub Action will flag. Findings are close but…

strands-agents/harness-sdk · 125 tokens

docs-writer

Draft or rewrite Strands Agents documentation pages. Use when writing new doc pages, rewriting pages that failed audit, drafting sections for existing pages, or writing blog posts and release notes about Strands. Also triggers on "write a doc", "draft a page", "rewrite the quickstart", "add a tutorial for X"…

strands-agents/harness-sdk · 74 tokens

pr-writer

Generates pull request titles and descriptions. Use when the user asks to create, open, write, draft, or generate a PR, pull request, or merge request description.

strands-agents/harness-sdk · 39 tokens