monty: Skill for Claude Code

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

review-general is a skill for Claude Code, Codex from pydantic/monty. It costs 55 tokens per session (466 once invoked), scanned A, original, MIT.

A checklist and process for reviewing a code branch before it is merged. It checks for bugs, behavior differences from CPython, sandbox and resource-limit escapes, performance problems, excessive comments, and missing documentation.

In plain words
What is it for?
Reviewing branches or pull requests against their merge base, especially in projects that implement or sandbox Python behavior.
Why use it?
It helps catch correctness, security, compatibility, and documentation problems before changes enter the main codebase.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions subagents; 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 →

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 · 8,188 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-general/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-general

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/pydantic/monty/review-general"><img src="https://agentmods.dev/badge/skills/pydantic/monty/review-general.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 466 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 $0.00055 $0.00466
Opus 5 $0.00028 $0.00233
Sonnet 5 $0.00011 $0.00093
Haiku 4.5 $0.00006 $0.00047

Measured 4d ago against content hash 42746d0ceb56, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-general 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-general/SKILL.md · 40 lines

What it actually says

General branch review

git diff --stat origin/main...HEAD   # scope first
git diff origin/main...HEAD

Read the changed files in full — a hunk is rarely enough to judge correctness. Look for:

  • Bugs — logic errors, DropWithContext values not released on every exit path (the fix is defer_drop!/DropGuard, not more drop_with calls), borrow/aliasing mistakes, unhandled error paths.
  • CPython divergence — different results, exception types or messages, missing attributes. Check anything you're unsure of with python-playground.
  • Sandbox escapes — sandboxed code reaching the host filesystem, environment, network or subprocesses.
  • Resource-limit escapes — allocations not charged to the tracker (an unbounded or amplifying String build without StringBuilder), unbounded loops, recursion without a depth guard.
  • Performance — regressions the branch introduces, and improvements you spot.
  • Verbose comments — docstrings and comments should be concise as per CLAUDE.md.
  • Cleanups — duplication, misplaced logic, functions grown too complex.
  • ./limitations/ — a new divergence with no entry is a finding.
  • Docs parity — a user-visible change reflected in only one of README.md, docs/, limitations/ and the crate READMEs is a finding. CLAUDE.md "Documentation surfaces that must stay in sync" has the obligation table. For a full pass, delegate to the docs-parity-reviewer subagent.

Report

Concise, most severe first. Per finding: file:line, what's wrong, the concrete failure it causes. Don't pad with what the branch got right.

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 42746d0ceb56
  2. 10d ago First seen · 40 lines · 55 tokens per session scan A d0110abe3713

Subscribe to this mod's changes

review-general is a skill published in the GitHub repository pydantic/monty (8,188 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 466 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.