A Python framework for building AI agents—programs that use language models to perform tasks through instructions and tools. It supports structured results, different model providers, testing agent behavior, shared dependencies, and multi-step workflows.

Use it to build Python agents, connect models from providers such as OpenAI, Anthropic, or Gemini, define typed tools, run evaluations, and connect MCP servers.

It helps keep agent inputs, outputs, and tool calls clearly defined while giving developers ways to test and observe how agents behave.

pydantic-ai — Skill for Claude Code and Codex by itechmeat/llm-code

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.

Any agent

npx skills add itechmeat/llm-code --skill pydantic-ai

Clone the repo

git clone --depth 1 https://github.com/itechmeat/llm-code

Made for: Claude Code, Codex.

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/skills/itechmeat/llm-code/pydantic-ai/github.svg)](https://agentmods.dev/skills/itechmeat/llm-code/pydantic-ai)

Your own site

<a href="https://agentmods.dev/skills/itechmeat/llm-code/pydantic-ai"><img src="https://agentmods.dev/badge/skills/itechmeat/llm-code/pydantic-ai/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/skills/itechmeat/llm-code/pydantic-ai"><img src="https://agentmods.dev/badge/skills/itechmeat/llm-code/pydantic-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,203 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00080	$0.05203
Opus 5.5	$0.00032	$0.02081
Sonnet 5.5	$0.00016	$0.01041
Haiku 4.5	$0.00008	$0.00520

Measured 24d ago against content hash 33bca4d3c7c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pydantic-ai 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 24d 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.

skills/pydantic-ai/SKILL.md · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pydantic AI

Python agent framework for building production-grade GenAI applications with the "FastAPI feeling".

Topic	Reference
Agents	agents.md
Capabilities	agents.md
Tools	tools.md
Models	models.md
Embeddings	embeddings.md
Evals	evals.md
Integrations	integrations.md
Graphs	graphs.md
UI Streams	ui.md
Installation	installation.md

When to Use

Building AI agents with structured output
Need type-safe, IDE-friendly agent development
Require dependency injection for tools
Multi-model support (OpenAI, Anthropic, Gemini, etc.)
Production observability with Logfire
Complex workflows with graphs

Installation

See references/installation.md for full/slim install options and optional dependency groups. Requires Python 3.10+.

Release Highlights (2.40.0 -> 2.48.0)

Security (upgrade) (2.44.0, backported to 1.107.6): four fixes reached through web_fetch_tool or OTel instrumentation — IPv6 zone-identifier bypass of the private-IP blocklist when local URLs are opted in, superlinear web_fetch HTML/charset processing that could stall the event loop, domain blocklists compared without resolver normalization, and span content leaks with include_content=False (GHSA-vmxc-h2x2-jmf3, GHSA-fpf4-vwcp-v4hp, GHSA-22h6-qm39-v87j, GHSA-4x9p-g9wm-8q7f).
Realtime session control (2.40.0/2.46.0): handle_barge_in=True with interrupt(played_bytes=...), RealtimeSession.enqueue() for out-of-band prompts, respond= on send(), wait_for_playback(), and @agent.on_event listeners.
Image generation (2.41.0): direct ImageGenerator API alongside the built-in tool; fallback_model on ImageGeneration/XSearch deprecated in favor of fallback_subagent_model.
Providers and models (2.41.0/2.42.0/2.48.0): openai-codex provider for ChatGPT/Codex subscription auth, GitHubCopilotProvider; OpenAI gpt-6-sol/gpt-6-luna and Claude Opus 5.5 (claude-opus-5-5).
Pricing (2.40.0): pydantic_ai.prices.update_in_background() refreshes genai-prices data in the background.
Temporal (2.46.0): event_stream_topic on TemporalDurability streams agent events via Workflow Streams.

Read the full file on GitHub · 324 lines

Files

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.

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.

24d ago Changed · +9 lines 33bca4d3c7c1
1mo ago Changed · +12 lines d29492e3791a
1mo ago First seen · 303 lines · 80 tokens per session scan A 31394a21933f

Subscribe to this mod's changes

pydantic-ai is a skill published in the GitHub repository itechmeat/llm-code (24 stars, last pushed 24d ago), licensed MIT. It adds 80 tokens to every session and 5,203 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 2026-08-30.

Building agents Languages Python

matlab

Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 44 tokens

pennylane

Builds and differentiates PennyLane quantum circuits, hybrid PyTorch or JAX models, molecular VQE and QAOA workflows. Use for variational quantum algorithms, quantum machine learning, simulator validation, and moving validated circuits to provider plugins. For hardware-specific compilation use qiskit or cirq; for…

K-Dense-AI/scientific-agent-skills · 74 tokens

rocm-kernels

Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…

huggingface/kernels · 93 tokens

holoscan-install-wheel

Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.

NVIDIA/skills · 37 tokens

typing-exclusion-worker

Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt workers or when asked to remove modules from pyproject mypy exclusion overrides.

getsentry/skills · 57 tokens

python

Python development with ruff, mypy, pytest - TDD and type safety.

alinaqi/maggy · 18 tokens

pydantic-ai