agentmods.dev

pydantic-ai-harness

pydantic-ai-harness is a plugin for Claude Code from pydantic/skills. Its manifest loads nothing; the 2 skills it bundles cost 296 tokens per session together, scanned A, original, MIT.

A plugin that extends Pydantic AI agents with extra capabilities from pydantic-ai-harness. The provided description specifically identifies Code Mode, which combines many tool calls into one sandboxed Python execution.

In plain words
What is it for?
Use it when a Pydantic AI agent needs the described Code Mode for grouped tool execution in a sandboxed Python run.
Why use it?
It can reduce the overhead of coordinating multiple tool calls while keeping that execution inside a sandbox. No other capabilities are supported by the provided information.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: mentions subagents.

not rated 151repo +4 changed 22d ago A scan tokens not measured original MIT

Good fit Use it when a Pydantic AI agent needs the described Code Mode for grouped tool execution in a sandboxed Python run.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add pydantic/skills
/plugin install pydantic-ai-harness
View source ↗ pydantic/skills
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.

Clone the repo
git clone --depth 1 https://github.com/pydantic/skills

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.

agentmods badge for pydantic-ai-harness

README.md
[![agentmods](https://agentmods.dev/badge/plugins/pydantic/skills/pydantic-ai-harness/github.svg)](https://agentmods.dev/plugins/pydantic/skills/pydantic-ai-harness)
Your own site
<a href="https://agentmods.dev/plugins/pydantic/skills/pydantic-ai-harness"><img src="https://agentmods.dev/badge/plugins/pydantic/skills/pydantic-ai-harness/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.

agentmods 80×15 button for pydantic-ai-harness

Your own site · 80×15
<a href="https://agentmods.dev/plugins/pydantic/skills/pydantic-ai-harness"><img src="https://agentmods.dev/badge/plugins/pydantic/skills/pydantic-ai-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 2 skills cost 296 tokens a session between them.
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.
Security

Grade A, and why

pydantic-ai-harness 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 22d 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.

plugins/pydantic-ai-harness/.claude-plugin/plugin.json · 10 lines

What it actually says

{
  "name": "pydantic-ai-harness",
  "description": "Extend Pydantic AI agents with batteries-included capabilities from pydantic-ai-harness — coding agents and sandboxed workspaces, Code Mode, sub-agents and planning, memory, context management, and guardrails — and port LangChain Deep Agents applications over to the harness",
  "version": "0.1.0",
  "author": {
    "name": "Pydantic",
    "email": "[email protected]"
  }
}
Contents

What it installs

The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 296 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 22d ago Changed f7aa16de5479
  2. 2mo ago First seen · 10 lines scan A 0d8ffe964b42

Subscribe to this mod's changes

pydantic-ai-harness is a plugin published in the GitHub repository pydantic/skills (151 stars, last pushed 9d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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
Related

pydantic-ai-harness compared with plugins from other repositories

pydantic-ai-harness next to 6 plugins from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pydantic-ai-harnesspydantic/skillsPlugin1519d agoMITA—Claude Code
humanizerblader/humanizerPlugin65k9d agoMITA—Claude Code
claude-plugins-official marketplaceanthropics/claude-plugins-officialPlugin46kyesterdayApache-2.0A—Claude Code
nextjsvercel/next.jsPlugin143kyesterdayMITA—Claude Code
themes-examplegoogle-gemini/gemini-cliPlugin109kyesterdayApache-2.0A—Gemini CLI
knowledge-work-plugins marketplaceanthropics/knowledge-work-pluginsPlugin35k2d agoApache-2.0A—Claude Code
code-modernizationanthropics/claude-plugins-officialPlugin46kyesterdayApache-2.0A—Claude Code