A structured review of uncommitted or staged code changes, covering security, code quality, project rules, and consistency between repositories or shared API types.

Use it to review current Git changes in applications and services, especially projects using React, Node.js, or APIs shared across repositories.

It catches defects, unsafe changes, missing tests, rule violations, and mismatched contracts before the changes are committed or merged.

code-review — Command for Claude Code by multiplex-ai/muggle-ai-teams

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.

Clone the repo

git clone --depth 1 https://github.com/multiplex-ai/muggle-ai-teams

Made for: Claude Code.

Or install muggle-ai-teams, the plugin that ships this one along with the rest of its 166 skills, 55 commands, 30 agents, 4 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/multiplex-ai/muggle-ai-teams/code-review/github.svg)](https://agentmods.dev/commands/multiplex-ai/muggle-ai-teams/code-review)

Your own site

<a href="https://agentmods.dev/commands/multiplex-ai/muggle-ai-teams/code-review"><img src="https://agentmods.dev/badge/commands/multiplex-ai/muggle-ai-teams/code-review/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/multiplex-ai/muggle-ai-teams/code-review"><img src="https://agentmods.dev/badge/commands/multiplex-ai/muggle-ai-teams/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 583 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00043	$0.00583
Opus 5.5	$0.00017	$0.00233
Sonnet 5.5	$0.00009	$0.00117
Haiku 4.5	$0.00004	$0.00058

Measured 1mo ago against content hash 1b455cd1b5c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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.

commands/code-review.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

Run a structured 3-pass review on uncommitted or staged changes.

Process

Gather changes: git diff --staged and git diff to see all modifications. If no diff, check recent commits with git log --oneline -5.
Read surrounding code: Don't review changes in isolation. Read the full file and understand imports, dependencies, and call sites.
Run three passes:

Pass 1: Code Quality

Security (CRITICAL — always flag):

Hardcoded credentials, API keys, tokens
SQL/NoSQL injection, XSS vulnerabilities
Missing input validation, path traversal
Authentication bypasses, CSRF gaps
Insecure dependencies, exposed secrets in logs

Code Quality (HIGH):

Bugs, logic errors, off-by-one errors
Functions >50 lines, files >800 lines, nesting >4 levels
Missing error handling, console.log statements
Missing tests for new code paths, dead code

React/Node.js Patterns (HIGH):

Missing useEffect dependency arrays, stale closures
N+1 queries, unbounded queries, missing rate limiting
Unvalidated request input, error message leakage

Performance (MEDIUM):

O(n²) algorithms, missing caching, large bundle imports

Pass 2: Compliance

CLAUDE.md rules for each repo touched (naming, structure, patterns)
TypeScript strictness (no any, explicit types)
Code style (longform property syntax, ~200 line files)
Test coverage for changed behavior

Pass 3: Contract Consistency (skip if single-repo)

Frontend/backend API type alignment
Endpoint path consistency
Error format consistency ({ code, message, details })

Confidence-Based Filtering

Only report issues with >80% confidence
Consolidate similar issues
Skip stylistic preferences unless they violate project conventions

Output Format

## MUST FIX
- [file:line] [description] — [why critical]

## SHOULD FIX
- [file:line] [description] — [why improves quality]

## NITPICK
- [file:line] [description]

## Summary
| Severity | Count |
|----------|-------|
| MUST FIX | N |
| SHOULD FIX | N |
| NITPICK | N |

Verdict: APPROVE / REQUEST CHANGES / BLOCK

Read the full file on GitHub · 79 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.

1mo ago First seen · 79 lines · 43 tokens per session scan A 1b455cd1b5c2

Subscribe to this mod's changes

code-review is a command published in the GitHub repository multiplex-ai/muggle-ai-teams (2 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 583 once invoked, about $0.0002 per session on Opus 5.5. 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.

Code review ai-agent-orchestration ai-agents ai-code-review ai-development ai-pair-programming ai-workflow

analyze-file

Deep analysis of a specific file using code-analyst sub-agent.

rubenCodeforges/codeforges-claude-plugin · 17 tokens

pi-plan

Multi-provider implementation planning — consult Codex and Gemini for architectural perspectives. Trigger: when the task involves architectural decisions, tech stack selection, evaluating multiple approaches, migration strategy, or complex implementation with multiple viable paths. Do NOT trigger for simple task…

tznthou/claude-prism · 78 tokens

code-review