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-general/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-general)<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.
<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>- 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 | $0.00055 | $0.00466 |
| Opus 5 | $0.00028 | $0.00233 |
| Sonnet 5 | $0.00011 | $0.00093 |
| Haiku 4.5 | $0.00006 | $0.00047 |
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.
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,
DropWithContextvalues not released on every exit path (the fix isdefer_drop!/DropGuard, not moredrop_withcalls), 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
Stringbuild withoutStringBuilder), 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 thedocs-parity-reviewersubagent.
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.
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 42746d0ceb56
- 10d ago First seen · 40 lines · 55 tokens per session scan A d0110abe3713
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.
Other skills, from other repositories
polars
High-performance DataFrame library for Python ETL, analytics, and pandas migration. Use for expression-based data manipulation with lazy query optimization, parallel execution, streaming out-of-core processing, Arrow interoperability, and optional GPU execution.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
code-review
Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.
code-review
Code review assistance with linting, style checking, and best practices.
tuicr
Use tuicr's review CLI to read and add comments in active TUI review sessions, and launch tuicr in cmux, tmux, Zellij, or Herdr when a user needs an interactive review pane.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.