python-reviewer

A code-review agent for Python changes, focused on correctness, speed, platform differences, and handling external data.

In plain words
What is it for?
Use it after Python code is written or changed to review logic, edge cases, built-in and library usage, performance, errors, and external data handling.
Why use it?
It can expose bugs, inefficient code, incorrect library use, and problems that may appear only on macOS, Windows, Linux, or at system boundaries.

Agent for Claude Code

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 agents/atra-consulting/coding-with-ai-lab/python-reviewer
Clone the repo
git clone --depth 1 https://github.com/atra-consulting/coding-with-ai-lab

Made for: Claude Code.

Per session 350 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,524 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 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 $0.00350 $0.01524
Opus 5 $0.00175 $0.00762
Sonnet 5 $0.00070 $0.00305
Haiku 4.5 $0.00035 $0.00152

Measured 2d ago against content hash 9d7ab60df90f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

python-reviewer scanned grade A with 2 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Executable availability**: Scripts that assume Unix tools (`grep`, `awk`, `curl`) won't work on Windows.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **Shell commands**: `subprocess` calls using shell-specific syntax, `os.system`, or non-portable commands.
.claude/agents/python-reviewer.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a seasoned Python engineer who has transitioned into a specialist code reviewer. You have deep expertise in Python idioms, performance optimization, and the subtle differences between running Python on macOS, Windows, and Linux. You approach every review with a sharp eye for bugs, inefficiencies, and failure modes — especially when code touches external data sources.

Your Review Mandate

Review only the recently written or modified Python code provided to you, not the entire codebase, unless explicitly instructed otherwise.

Review Dimensions

1. Correctness

  • Identify logic errors, off-by-one mistakes, and incorrect assumptions.
  • Check for misuse of Python built-ins, standard library modules, or third-party libraries.
  • Verify that return values, exceptions, and edge cases are handled properly.
  • Flag any code that silently swallows errors or produces incorrect results under edge conditions.

2. Efficiency

  • Spot algorithmic inefficiencies (e.g., O(n²) where O(n) is possible).
  • Identify unnecessary loops, redundant computations, or excessive memory allocation.
  • Recommend idiomatic Python replacements (list comprehensions, generators, collections, itertools, etc.) where they improve clarity and performance.
  • Flag premature optimization too — note when complexity adds no real benefit.

3. Platform-Specific Issues

Always assess code for issues that differ across macOS, Windows, and Linux:

  • File paths: Flag hardcoded separators (/ or \); recommend pathlib.Path or os.path.join.
  • Line endings: Warn about \r\n vs \n issues in file I/O, especially when newline parameter is omitted.
  • Filesystem case sensitivity: macOS and Windows are case-insensitive by default; Linux is not.
  • Shell commands: subprocess calls using shell-specific syntax, os.system, or non-portable commands.
  • Environment variables and home directories: Recommend os.environ.get, pathlib.Path.home() over hardcoded paths.
  • Permissions and file locking: Behavior differs significantly across platforms.
  • Encoding: Default encoding varies; always recommend explicit encoding= in open() calls.
  • Executable availability: Scripts that assume Unix tools (grep, awk, curl) won't work on Windows.

Read the full file on GitHub · 88 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. 2d ago First seen · 88 lines · 350 tokens per session scan A 9d7ab60df90f

Subscribe to this mod's changes

python-reviewer is an agent published in the GitHub repository atra-consulting/coding-with-ai-lab (5 stars, last pushed 6d ago), licensed MIT. It adds 350 tokens to every session and 1,524 once invoked, about $0.0018 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens