agentmods.dev

pydantic-deepagents: Instructions file for Claude Code

CLAUDE.md

pydantic-deepagents CLAUDE.md is an instructions file for Claude Code from vstorm-co/pydantic-deepagents. It costs 4,506 tokens per session, scanned A, original, MIT.

Repository guidance for working on pydantic-deepagents, a Python project for building AI agents. It lists its commands, tests, documentation workflow, and feature-based code layout.

In plain words
What is it for?
Installing dependencies, running all checks or one pytest test, building documentation, and locating code for a particular feature.
Why use it?
It gives a coding agent the project rules and commands it needs, reducing guesswork about how to change and check the code.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is vstorm-co/pydantic-deepagents's own configuration. It tells Claude Code how to work on pydantic-deepagents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pydantic-deepagents configures →

not rated 1.1krepo +5 changed 1mo ago A scan 4,506 tokens original MIT
View source ↗ vstorm-co/pydantic-deepagents vstorm-co.github.io
About the project

Pydantic Deep Agents is a self-hosted terminal AI assistant and Python framework for building coding, research, and other AI agents. It gives agents tools such as file access, shell commands, planning, memory, sub-agents, sandboxed execution, and MCP connections, and supports different models.

vstorm-co/pydantic-deepagents · 1,115 stars · on GitHub · vstorm-co.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to vstorm-co/pydantic-deepagents. 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/vstorm-co/pydantic-deepagents/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/vstorm-co/pydantic-deepagents

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-deepagents CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vstorm-co/pydantic-deepagents/claude-md/github.svg)](https://agentmods.dev/instructions/vstorm-co/pydantic-deepagents/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vstorm-co/pydantic-deepagents/claude-md"><img src="https://agentmods.dev/badge/instructions/vstorm-co/pydantic-deepagents/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.

agentmods 80×15 button for pydantic-deepagents CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/vstorm-co/pydantic-deepagents/claude-md"><img src="https://agentmods.dev/badge/instructions/vstorm-co/pydantic-deepagents/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,506 This file is loaded in full into every session.
When invoked 4,506 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04506 $0.04506
Opus 5.5 $0.01802 $0.01802
Sonnet 5.5 $0.00901 $0.00901
Haiku 4.5 $0.00451 $0.00451

Measured 1mo ago against content hash b722c3a9abc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pydantic-deepagents 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 1mo 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 · 373 lines

How it starts

The opening of the file, as written. The whole thing — 373 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.

Development Commands

Core Development Tasks

  • Install dependencies: make install (requires uv and pre-commit)
  • Run all checks: make all or pre-commit run --all-files
  • Run tests: make test
  • Build docs: make docs or make docs-serve (local development)

Single Test Commands

  • Run specific test: uv run pytest tests/test_agent.py::test_function_name -v
  • Run test file: uv run pytest tests/test_agent.py -v
  • Run with debug: uv run pytest tests/test_agent.py -v -s

Project Architecture

Repository Layout

  • pydantic_deep/ — Core library (agent, deps, models, instructions, types)
  • pydantic_deep/features/<name>/ — One vertical-slice package per feature (capability.py + toolset.py + service.py/types.py). Organize by feature, not by kind — features/ is the only import location; the old toolsets/, capabilities/, processors/ and improve/ shims were removed in 0.3.39.
  • apps/cli/ — CLI + TUI application (Textual-based terminal AI assistant)
  • apps/deepresearch/ — Full-featured research reference app
  • tests/ — Unit tests
  • docs/ — Documentation source (MkDocs)

Core Components

Agent Factory (pydantic_deep/agent.py)

  • create_deep_agent(): Main factory function for creating configured agents
  • create_default_deps(): Helper for creating DeepAgentDeps with sensible defaults
  • Built on top of pydantic-ai's Agent class
  • Requires pydantic-ai>=2.52.0 (workspaces)
  • workspace=: the capability that supplies each run's workspace; default StateWorkspace() (in-memory, no commands), False leaves it to agent.run(workspace=...)

Dependencies (pydantic_deep/deps.py)

  • DeepAgentDeps: Dataclass holding agent dependencies (todos, subagents, uploads, checkpoint store, message queue)
  • Passed to agent.run() for runtime configuration
  • Holds no files: those live in the run's workspace, ctx.workspace. upload_file() queues bytes that write_pending_uploads() writes when the run starts

Read the full file on GitHub · 373 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. 1mo ago Changed · +59 tokens per session b722c3a9abc2
  2. 1mo ago Changed · -3 lines · +188 tokens per session 4a000759843a
  3. 2mo ago First seen · 376 lines · 4,259 tokens per session scan A e4d570b63e27

Subscribe to this mod's changes

pydantic-deepagents CLAUDE.md is an instructions file published in the GitHub repository vstorm-co/pydantic-deepagents (1,115 stars, last pushed 7d ago), licensed MIT. It adds 4,506 tokens to every session, about $0.0180 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 agentsPythonagent-frameworkanthropicllmspydanticpydantic-ai
Related

pydantic-deepagents CLAUDE.md compared with instructions from other repositories

pydantic-deepagents CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pydantic-deepagents CLAUDE.mdvstorm-co/pydantic-deepagentsInstructions file1.1k7d agoMITA4,506Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode