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.
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.
curl -O https://raw.githubusercontent.com/pydantic/monty/main/.agents/skills/review-usability/SKILL.mdgit clone --depth 1 https://github.com/pydantic/montyWrote 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/pydantic/monty/review-usability)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.00379 |
| Opus 5 | $0.00026 | $0.00189 |
| Sonnet 5 | $0.00010 | $0.00076 |
| Haiku 4.5 | $0.00005 | $0.00038 |
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.
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
-
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.
-
Write real test files in
playground/(seepython-playground), named recognisably. -
Run each under both and diff:
uv run playground/test_thing.py # CPython cargo run -- playground/test_thing.py # Monty -
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.
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.
- 4d ago Changed · +2 lines b372cdb71ba4
- 9d ago First seen · 41 lines · 52 tokens per session scan A 2700f9a4ef1d
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.
Other skills, from other repositories
temporal-python-testing
Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.
python-testing
Guidelines for writing and running tests in the Agent Framework Python codebase. Use this when creating, modifying, or running tests.
adk-verify-snippets
Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail report with per-snippet coverage. Use when the user asks to verify, test, or validate the code samples in a README, a guide…
adk-setup
Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test run. Runs only when explicitly requested, never on its own. Use when asked to set up, bootstrap, or repair a development…
typescript
TypeScript strict mode with eslint and jest.
test-generator
Generate pytest test cases for Python functions and classes.