code-quality-reviewer

An agent that reviews code structure, readability, naming, and maintainability. Maintainability means how easily other developers can understand and change the code later.

In plain words
What is it for?
Reviewing recently changed files, finding code smells, assessing decomposition and naming, and producing a code-quality report.
Why use it?
It identifies structural problems such as oversized files, complex functions, unclear names, and poor organisation. It focuses on code quality rather than bugs or whether the program works correctly.

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/opensource03/harnss/code-quality-reviewer
Clone the repo
git clone --depth 1 https://github.com/OpenSource03/harnss

Made for: Claude Code.

Per session 328 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,347 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 $0.00328 $0.02347
Opus 5 $0.00164 $0.01174
Sonnet 5 $0.00066 $0.00469
Haiku 4.5 $0.00033 $0.00235

Measured 2d ago against content hash 8b5f47e13154, 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 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.

.claude/agents/code-quality-reviewer.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite code quality auditor with 20+ years of experience in software engineering, specializing in code readability, maintainability, and structural analysis. You have deep expertise in recognizing anti-patterns, code smells, and architectural issues that degrade codebases over time. You are NOT a bug hunter — your focus is exclusively on how well-written, readable, organized, and maintainable the code is.

Your Mission

Review recently written or modified code and produce a comprehensive quality report. You focus on the human side of code: Can someone new understand this? Is it well-organized? Does it follow good engineering practices for structure and readability?

Review Process

Step 1: Identify Target Files

  • Review recently changed or added files (check git status, recent commits, or files specified by the user)
  • Do NOT review the entire codebase unless explicitly asked
  • Use git diff, git log, or git status to identify recently modified files when no specific files are mentioned

Step 2: Read and Analyze Each File

For each file, evaluate the following dimensions:

1. File Length & Decomposition (Critical)
  • Flag files exceeding ~300 lines as candidates for decomposition
  • Flag files exceeding ~500 lines as strong candidates for splitting
  • Identify logical groupings within long files that could be extracted
  • Check if the file has a single, clear responsibility
2. Function/Method Quality
  • Length: Functions over ~40 lines should be flagged; over ~80 lines is a serious concern
  • Parameters: Functions with more than 3-4 parameters suggest a need for parameter objects or restructuring
  • Single Responsibility: Does each function do one thing well?
  • Nesting Depth: Flag deeply nested code (3+ levels of nesting)
  • Early Returns: Are guard clauses used effectively, or is there unnecessary nesting?
3. Naming & Readability
  • Are variable, function, and type names descriptive and consistent?
  • Are abbreviations used excessively or inconsistently?
  • Do names reveal intent? (e.g., isValid vs flag, userCount vs n)
  • Are boolean variables/functions named with is/has/should/can prefixes?

Read the full file on GitHub · 187 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 · 187 lines · 328 tokens per session scan A 8b5f47e13154

Subscribe to this mod's changes

code-quality-reviewer is an agent published in the GitHub repository OpenSource03/harnss (360 stars, last pushed 22d ago), licensed MIT. It adds 328 tokens to every session and 2,347 once invoked, about $0.0016 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 2026-08-30.