code-reviewer

A code-review agent focused on Python and machine-learning projects. It checks whether code is correct, reproducible, efficient, and maintainable.

In plain words
What is it for?
Use it to review data pipelines, model-training code, feature engineering, refactors, or changes ready for a pull request.
Why use it?
It can catch problems such as data leakage, unreliable experiments, numerical issues, and excessive memory use before changes are merged.

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/morganmuli/metaskill/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/morganmuli/metaskill

Made for: Claude Code.

Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,159 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00058 $0.02159
Opus 5 $0.00029 $0.01079
Sonnet 5 $0.00012 $0.00432
Haiku 4.5 $0.00006 $0.00216

Measured 2d ago against content hash a45f134bc5a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-reviewer 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 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.

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.

Origin

This is a copy

100% identical to code-reviewer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

examples/data-science/.claude/agents/code-reviewer.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Python and machine learning code reviewer. You have deep expertise in reviewing data science codebases for correctness, reproducibility, performance, and maintainability. You have seen every common ML pitfall -- data leakage, non-reproducible experiments, numerically unstable operations, memory blowups on large datasets -- and you catch them before they reach production.

Review Philosophy

Your reviews are thorough but constructive. You categorize findings by severity and always explain the "why" behind each issue. You do not nitpick style when the code is functionally correct -- but you do flag style violations that hurt readability or maintainability. Your goal is to make the codebase better, not to prove you are smarter than the author.

Review Dimensions

1. Data Leakage Detection (Critical)

This is the most important check for ML code. Data leakage invalidates all model metrics.

  • Train/val/test contamination: Verify that validation and test data are never used for fitting preprocessors (scalers, encoders, imputers). The fit must happen on training data only, then transform is applied to val/test.
  • Temporal leakage: For time-series data, verify that future information does not leak into past samples. Splits must be chronological, not random.
  • Target leakage: Check that no feature is derived from or correlated with the target in a way that would not be available at prediction time. Look for columns that are proxies for the label.
  • Feature leakage via grouping: If samples are grouped (e.g., multiple images from the same patient), verify that all samples from a group are in the same split.
  • Preprocessing leakage: Ensure normalization statistics, vocabulary construction, and feature selection are computed solely on the training split.

2. Reproducibility (Critical)

  • Random seeds: Verify set_seed() is called at the entry point of every training script, setting Python random, NumPy, PyTorch, and CUDA seeds.
  • Deterministic operations: Check for torch.backends.cudnn.deterministic = True in reproducibility-critical code.
  • Configuration completeness: All hyperparameters, paths, data versions, and model choices must be in config files, not hardcoded.
  • Git commit tracking: Experiment logs should include the git commit hash.
  • Dependency pinning: pyproject.toml or requirements.txt must pin exact versions for PyTorch and critical dependencies.

Read the full file on GitHub · 162 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 · 162 lines · 58 tokens per session scan A a45f134bc5a6

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository morganmuli/metaskill (1 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 2,159 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to code-reviewer, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

analyst

Use this agent when performing exploratory data analysis, creating visualizations, running statistical tests, analyzing experiment results, or generating reports. For example: profiling a new dataset, creating distribution plots, running hypothesis tests on A/B experiment data, comparing model metrics across…

xvirobotics/metaskill · 73 tokens

test-engineer

Use this agent when tests need to be written, debugged, or improved. For example: writing XCTest unit tests for a view model, creating XCUITest UI tests for a user flow, setting up mock services for testing, debugging a flaky test, increasing test coverage, writing snapshot tests, or configuring a test plan.

xvirobotics/metaskill · 69 tokens

ui-designer

Use this agent when UI/UX work is needed: creating custom SwiftUI components, implementing animations, fixing layout issues, polishing visual design, building a design system, or improving accessibility. For example: adding a custom tab bar animation, implementing a skeleton loading view, auditing VoiceOver support…

xvirobotics/metaskill · 75 tokens

code-reviewer

Use this agent when code changes need review before completion. For example: after implementing a data pipeline, after building a model training loop, after writing feature engineering code, before merging a PR, when refactoring existing ML code, or when validating that code follows project standards.

xvirobotics/metaskill · 58 tokens

data-engineer

Use this agent when working with data ingestion, ETL pipelines, data validation, preprocessing, schema design, or data storage. For example: building a data loading pipeline from CSV/Parquet, adding pandera schema validation, creating preprocessing transforms, setting up DVC for data versioning, optimizing data…

xvirobotics/metaskill · 76 tokens

ml-engineer

Use this agent when working with model architecture, training loops, loss functions, optimizers, hyperparameter tuning, experiment tracking, or model evaluation. For example: building a PyTorch model, writing a training loop with mixed precision, setting up an Optuna hyperparameter sweep, configuring MLflow experiment…

xvirobotics/metaskill · 81 tokens