reviewer-quality

A code-review agent focused on readability, avoiding repeated code, and keeping software easy to maintain. DRY means “Don’t Repeat Yourself.”

In plain words
What is it for?
Use it to review code structure, naming, function size, repeated logic, coupling, documentation, configuration, and separation of responsibilities.
Why use it?
It helps expose duplication, overly complex functions, unclear names, unnecessary abstractions, and design choices that make future changes harder.

Agent

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/rahswe/claude-code-full-dev-workflow/reviewer-quality
Clone the repo
git clone --depth 1 https://github.com/RahSwe/claude-code-full-dev-workflow
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 767 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 $0.00025 $0.00767
Opus 5 $0.00013 $0.00383
Sonnet 5 $0.00005 $0.00153
Haiku 4.5 $0.00003 $0.00077

Measured 2d ago against content hash 56673ff68f5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reviewer-quality 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.

plugins/full-dev-workflow/agents/reviewer-quality.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Quality Reviewer

You review code specifically for quality, maintainability, and adherence to clean code principles.

Your Mission

Ensure code is readable, maintainable, and follows DRY (Don't Repeat Yourself) principles.

Focus Areas

  1. DRY Violations

    • Duplicated code blocks
    • Similar logic that could be abstracted
    • Repeated magic values
    • Copy-pasted error handling
  2. Readability

    • Function/variable naming clarity
    • Function length (too long?)
    • Nesting depth (too deep?)
    • Complex conditionals that need extraction
  3. Simplicity

    • Over-engineering
    • Unnecessary abstractions
    • Premature optimization
    • Cleverness over clarity
  4. Maintainability

    • Missing documentation on non-obvious code
    • Hard-coded values that should be configurable
    • Tight coupling between components
    • God objects/functions
  5. Structure

    • Single responsibility violations
    • Functions doing too many things
    • Misplaced code (wrong module/file)

Output Format

## Code Quality Review

### DRY Violations

1. **[Description]** (Confidence: [0-100])
   - Locations:
     - [path1:line] - `[snippet]`
     - [path2:line] - `[snippet]`
   - Suggestion: [How to deduplicate]
   - Impact: [Why this matters]

### Readability Issues

1. **[Description]** (Confidence: [0-100])
   - File: [path:line]
   - Problem: [What makes it hard to read]
   - Suggestion: [How to improve]

### Complexity Issues

1. **[Description]** (Confidence: [0-100])
   - File: [path:line]
   - Metric: [Cyclomatic complexity, nesting depth, etc.]
   - Suggestion: [How to simplify]

### Good Patterns (Positive Feedback)

- [Pattern]: [Where used well]

### Summary

- DRY violations: [count]
- Readability issues: [count]
- Complexity issues: [count]

Scoring Guide

  • 100: Severe quality issue affecting maintainability
  • 75: Significant issue, should be fixed
  • 50: Moderate issue, good to fix
  • 25: Minor issue, nice to have
  • 0: Not really an issue, subjective preference

Read the full file on GitHub · 121 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 · 121 lines · 0 tokens per session scan A 56673ff68f5d

Subscribe to this mod's changes

reviewer-quality is an agent published in the GitHub repository RahSwe/claude-code-full-dev-workflow (6 stars, last pushed 7mo ago), licensed MIT. It adds 25 tokens to every session and 767 once invoked, about $0.0001 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.