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.
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 skills/vstorm-co/pydantic-deepagents/refactornpx skills add vstorm-co/pydantic-deepagents --skill refactorgit clone --depth 1 https://github.com/vstorm-co/pydantic-deepagentsWrote 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.
[](https://agentmods.dev/skills/vstorm-co/pydantic-deepagents/refactor)<a href="https://agentmods.dev/skills/vstorm-co/pydantic-deepagents/refactor"><img src="https://agentmods.dev/badge/skills/vstorm-co/pydantic-deepagents/refactor.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00012 | $0.00251 |
| Opus 5 | $0.00006 | $0.00125 |
| Sonnet 5 | $0.00002 | $0.00050 |
| Haiku 4.5 | $0.00001 | $0.00025 |
Grade A, and why
refactor 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 5d 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.
What it actually says
Refactor
Improve code structure without changing external behavior.
Process
- Understand — Read all related code, run existing tests
- Plan — Identify what to change and why
- Execute — Make changes incrementally
- Verify — Run tests after each change
Common Refactoring Patterns
Extract
- Long function → smaller focused functions
- Repeated code → shared helper
- Magic numbers → named constants
Simplify
- Deep nesting → early returns / guard clauses
- Complex conditionals → descriptive functions
- Large classes → smaller focused classes
Rename
- Unclear names → descriptive names
- Inconsistent naming → consistent conventions
Reorganize
- Related functions scattered → grouped in modules
- Circular dependencies → dependency inversion
Rules
- Never change behavior — tests must pass before and after
- One refactoring type per commit
- If tests don't exist, write them first
- Don't refactor and add features in the same change
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.
- 5d ago First seen · 45 lines · 12 tokens per session scan A 6838d73006df
refactor is a skill published in the GitHub repository vstorm-co/pydantic-deepagents (1,058 stars, last pushed 13d ago), licensed MIT. It adds 12 tokens to every session and 251 once invoked, about $0.0001 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 skills, from other repositories
add-new-model
Add support for a newly-released LLM model in pydantic-ai (e.g. openai:gpt-5.6, anthropic:claude-sonnet-5). Use when a provider ships a new model id and you need to wire literals, profile flags, and tests to recognize it. Handles SDK-lag, gateway list conventions, and capability probing.
building-pydantic-ai-agents
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
testing-skill
Record, rewrite, and debug VCR cassettes for HTTP recordings. Use when running tests with --record-mode, verifying cassette playback, or inspecting request/response bodies in YAML cassettes.
pre-push-review
Run a high-judgment local review of the current branch before pushing, both before a PR exists and between PR iterations.
adding-a-provider-api-feature
Add a new provider API capability (prompt caching, strict/structured tool calling, thinking/reasoning effort, service tier, safety settings, logprobs, etc.) to Pydantic AI. Use when wiring a provider feature through the library — it enforces reasoning from the existing cross-provider abstraction before designing…