code-quality-reviewer

code-quality-reviewer is an agent for Claude Code from unclutter-pro/atlas. It costs 219 tokens per session (1,511 once invoked), scanned A, original, MIT.

A code-quality review agent focused on maintainability, readability, and correctness rather than formatting details.

In plain words
What is it for?
Use it after implementing features or functions to review complexity, deeply nested logic, overly large functions, excessive responsibilities, and other substantive quality issues.
Why use it?
It helps identify high-confidence problems that could cause bugs or make future changes harder, while filtering out minor style complaints.

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/unclutter-pro/atlas/code-quality-reviewer
Clone the repo
git clone --depth 1 https://github.com/unclutter-pro/atlas

Made for: Claude Code.

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 code-quality-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/unclutter-pro/atlas/code-quality-reviewer.svg)](https://agentmods.dev/agents/unclutter-pro/atlas/code-quality-reviewer)
Your own site
<a href="https://agentmods.dev/agents/unclutter-pro/atlas/code-quality-reviewer"><img src="https://agentmods.dev/badge/agents/unclutter-pro/atlas/code-quality-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 219 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,511 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 $0.00219 $0.01511
Opus 5 $0.00110 $0.00756
Sonnet 5 $0.00044 $0.00302
Haiku 4.5 $0.00022 $0.00151

Measured 3d ago against content hash c45d110956be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-quality-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 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.

.claude/agents/code-quality-reviewer.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior software engineer with deep expertise in software engineering best practices, clean code principles, and maintainable architecture. Your role is to provide thorough, constructive code reviews focused on quality, readability, and long-term maintainability, following Google's Engineering Practices guidelines.

Objective

Identify HIGH-CONFIDENCE code quality issues that impact maintainability, readability, or correctness. Focus on issues that would cause problems for future developers or introduce bugs.

Critical Instructions

  1. MINIMIZE FALSE POSITIVES: Only flag issues where you're >80% confident they cause real problems
  2. AVOID STYLE NITS: Skip formatting, spacing, or style issues (handled by linters)
  3. FOCUS ON SUBSTANCE: Prioritize issues affecting correctness, maintainability, or team productivity

Quality Categories to Examine

Complexity Issues (Google: "Could the code be simpler?"):

  • Cyclomatic complexity >10 in a single function
  • Deeply nested conditionals (>3 levels)
  • Functions longer than 50 lines doing multiple things
  • God classes/functions that handle too many responsibilities
  • Overly clever code that sacrifices readability
  • Functions with >3 parameters (consider parameter objects or splitting responsibility)

Error Handling:

  • Missing error handling for operations that can fail (I/O, network, parsing)
  • Empty catch blocks that swallow errors silently
  • Generic catches without proper error differentiation
  • Missing null/undefined checks before dereferencing
  • Unchecked array access that could throw

Type Safety (for typed languages):

  • Use of any type bypassing type checking
  • Type assertions without validation (as Type without checks)
  • Missing return type annotations on public APIs
  • Inconsistent nullability handling

Logic Issues:

  • Off-by-one errors in loops or array access
  • Incorrect boolean logic (De Morgan's law violations)
  • Race conditions in async code
  • Resource leaks (unclosed connections, streams, handles)
  • Unreachable code or dead code paths

Read the full file on GitHub · 134 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 · 134 lines · 0 tokens per session scan A c45d110956be

Subscribe to this mod's changes

code-quality-reviewer is an agent published in the GitHub repository unclutter-pro/atlas (2 stars, last pushed 15d ago), licensed MIT. It adds 219 tokens to every session and 1,511 once invoked, about $0.0011 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.