monty: Skill for Claude Code

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

review-verbosity is a skill for Claude Code, Codex from pydantic/monty. It costs 43 tokens per session (471 once invoked), scanned A, original, MIT.

A code-review helper that shortens new comments and documentation in a branch, removing wording that merely repeats the code.

In plain words
What is it for?
Use it after adding a feature to review changed comments and docstrings, including changes spread across multiple crates or groups of files.
Why use it?
It keeps comments useful and easier to scan, while preserving reasons, warnings, and other information developers need.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: 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 · 8,193 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-verbosity/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-verbosity

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/pydantic/monty/review-verbosity"><img src="https://agentmods.dev/badge/skills/pydantic/monty/review-verbosity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 471 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 $0.00043 $0.00471
Opus 5 $0.00022 $0.00235
Sonnet 5 $0.00009 $0.00094
Haiku 4.5 $0.00004 $0.00047

Measured 5d ago against content hash af95de78d95d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

review-verbosity 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.

.agents/skills/review-verbosity/SKILL.md · 44 lines

What it actually says

Verbosity review

New comments and docstrings are usually too verbose. Rewrite them concisely. This skill edits — it doesn't just report.

git diff --stat origin/main...HEAD   # which crates changed
git diff origin/main...HEAD

Dispatch one sub-agent per changed area — a crate, or any other group of changed files, so nothing outside crates/ is missed — then review their edits yourself. A single pass over a large diff won't be exhaustive. In every comment the branch touched:

  • Cut it down. Comments and field docstrings rarely over 3 lines, mostly 1; function and struct docstrings <= 5.
  • Delete tautology — restating what the code plainly says earns nothing.
  • Delete narration of the obvious, restated type signatures, how the code came to be, hedging.
  • Keep the motivation — why the code exists and its foot-guns are the valuable part. Don't cut real information to hit a line count.
  • Drop over-long examples. Public items only, <= 8 lines, and every one must run in tests — never ignore.
  • Fix what's out of date. A comment the branch made wrong gets corrected, not left.

Python docstrings are markdown: single backticks, never RST double-backticks.

Only touch what this branch added or changed, unless asked for a wider sweep. Don't change behaviour — if a comment is wrong because the code is wrong, say so rather than rewording it to match. Concision, not terseness: an unfollowable comment is worse than a long one.

make format-rs && make lint-rs
git diff --stat   # format-rs is `cargo +nightly fmt --all` — check it touched only your files

Then report what you cut, by file, in a couple of lines — not a full inventory.

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. 5d ago Changed af95de78d95d
  2. 11d ago First seen · 44 lines · 43 tokens per session scan A d07eb7df7a56

Subscribe to this mod's changes

review-verbosity is a skill published in the GitHub repository pydantic/monty (8,193 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 471 once invoked, about $0.0002 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.