python-code-review

python-code-review is a skill for Claude Code, Codex from tasanakorn/cc-marketplace. It costs 59 tokens per session (2,995 once invoked), scanned A, original, MIT.

A review guide for Python code, a programming language often used for scripts, services, and data work. It checks style, type annotations, structure, documentation, anti-patterns, and tools such as ruff, mypy, and uv.

In plain words
What is it for?
Use it to review Python for PEP 8 style rules, type hints, modern Python 3.9+ practices, module organization, and maintainability.
Why use it?
It gives developers specific findings instead of relying only on a general code review. Severity-based recommendations help show which issues need attention first.

Skill for Claude CodeCodex

Part of the python-dev plugin — 2 skills, 1 command shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/tasanakorn/cc-marketplace/python-code-review
Any agent
npx skills add tasanakorn/cc-marketplace --skill python-code-review
Clone the repo
git clone --depth 1 https://github.com/tasanakorn/cc-marketplace

Made for: Claude Code, Codex.

Or install python-dev, the plugin that ships this one along with the rest of its 2 skills, 1 command.

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 python-code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/tasanakorn/cc-marketplace/python-code-review.svg)](https://agentmods.dev/skills/tasanakorn/cc-marketplace/python-code-review)
Your own site
<a href="https://agentmods.dev/skills/tasanakorn/cc-marketplace/python-code-review"><img src="https://agentmods.dev/badge/skills/tasanakorn/cc-marketplace/python-code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,995 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00059 $0.02995
Opus 5 $0.00030 $0.01497
Sonnet 5 $0.00012 $0.00599
Haiku 4.5 $0.00006 $0.00299

Measured 3d ago against content hash c91e1f06cd5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

python-code-review 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 3d 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.

plugins/python-dev/skills/python-code-review/SKILL.md · 466 lines

How it starts

The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Python Code Review Skill

A specialized skill for reviewing Python code with focus on PEP8 compliance, type hints, modern best practices, and code quality.

Overview

This skill enables Claude to autonomously review Python code for compliance with modern Python standards, including PEP8 style guidelines, type hint coverage, proper structure, and common anti-patterns. It promotes clean, maintainable, and type-safe Python code.

Capabilities

When activated, this skill provides:

  1. PEP8 Compliance Review

    • Check naming conventions (snake_case, PascalCase)
    • Verify line length (88 characters)
    • Review whitespace and indentation
    • Check import ordering and grouping
    • Validate docstring presence and format
  2. Type Hints Validation

    • Ensure all functions have type hints
    • Check for proper return type annotations
    • Validate use of modern type syntax (list[], dict[] over List[], Dict[])
    • Verify Optional[] vs None union types
    • Check for Any types (discourage overuse)
  3. Code Structure & Organization

    • Review module structure and imports
    • Check for proper __init__.py usage
    • Validate entry points (__main__.py)
    • Review function/class organization
    • Assess module coupling and cohesion
  4. Best Practices Enforcement

    • Check for use of context managers (with statements)
    • Validate exception handling
    • Review string formatting (f-strings preferred)
    • Check for proper constant definitions
    • Assess use of comprehensions vs loops
  5. Common Anti-Patterns Detection

    • Mutable default arguments
    • Bare except clauses
    • Using global keyword unnecessarily
    • Poor variable naming
    • Overly complex functions (high cyclomatic complexity)
  6. Documentation Quality

    • Check for docstrings on public functions/classes
    • Validate docstring format (Google/NumPy style)
    • Review parameter documentation
    • Check for return value documentation
    • Assess example usage in docstrings

Read the full file on GitHub · 466 lines

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. 3d ago First seen · 466 lines · 59 tokens per session scan A c91e1f06cd5a

Subscribe to this mod's changes

python-code-review is a skill published in the GitHub repository tasanakorn/cc-marketplace (2 stars, last pushed 5mo ago), licensed MIT. It adds 59 tokens to every session and 2,995 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 2026-08-31.