monty: Skill for Claude Code

.agents/skills/review-usability/SKILL.md

review-usability is a skill for Claude Code, Codex from pydantic/monty. It costs 52 tokens per session (379 once invoked), scanned A, original, MIT.

A testing procedure for checking whether common Python code works the same way in Monty and CPython, the standard Python interpreter. It focuses on code an AI assistant is likely to write.

In plain words
What is it for?
Use it to write playground tests, compare outputs, and document differences or unsupported Python idioms.
Why use it?
It finds cases where the two interpreters return different results or where ordinary Python patterns fail unexpectedly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is pydantic/monty's own configuration. It tells Claude Code and Codex how to work on monty 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 monty configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run playground/test_thing.py # CPython.

About the project

Monty is a minimal Python interpreter written in Rust that runs AI-generated code in a restricted environment without direct filesystem, environment-variable, or network access. It is for AI agents that need to execute Python and type-checking tasks while allowing developers to control which host functions and objects the code can use, and the catalogue entries integrate it into agent workflows.

pydantic/monty · 8,184 stars · on GitHub · pydantic.dev

Reuse

Borrowing it

Nothing to install: this file belongs to pydantic/monty. 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/pydantic/monty/main/.agents/skills/review-usability/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/pydantic/monty

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.

agentmods badge for review-usability

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/pydantic/monty/review-usability"><img src="https://agentmods.dev/badge/skills/pydantic/monty/review-usability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 379 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.00379
Opus 5 $0.00026 $0.00189
Sonnet 5 $0.00010 $0.00076
Haiku 4.5 $0.00005 $0.00038

Measured 4d ago against content hash b372cdb71ba4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-usability 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 4d 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.

.agents/skills/review-usability/SKILL.md · 43 lines

What it actually says

Usability review

Monty exists so LLMs can write Python that calls tools. Real usage is therefore the most common patterns, not exotic corners — and a divergence in a common pattern is the worst kind of bug, because the model has no way to know it must write something else.

Think hard on this one.

git diff origin/main...HEAD
  1. For each feature the branch touches, list the idioms a model reaches for first — the obvious method, argument form, combination with another builtin. Include ones the branch does not handle; that's where the gaps are.

  2. Write real test files in playground/ (see python-playground), named recognisably.

  3. Run each under both and diff:

    uv run playground/test_thing.py        # CPython
    cargo run -- playground/test_thing.py  # Monty
    
  4. Prioritise silent divergence — same code, different result — over a clean AttributeError. A missing feature that raises is recoverable; a wrong answer isn't.

An undocumented divergence is also a ./limitations/ finding.

Report

Per divergence: the code, CPython's output, Monty's output, how likely a model is to write it. Then unsupported-but-common idioms with the error the user sees, and briefly what worked — it bounds the review. Leave the playground files in place.

Report only, unless the user asks for fixes.

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. 4d ago Changed · +2 lines b372cdb71ba4
  2. 9d ago First seen · 41 lines · 52 tokens per session scan A 2700f9a4ef1d

Subscribe to this mod's changes

review-usability is a skill published in the GitHub repository pydantic/monty (8,184 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 379 once invoked, about $0.0003 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.