refactoring-assistant

refactoring-assistant is a skill for Claude Code, Codex from mehdiozdemir/awesome-agent-skills. It costs 54 tokens per session (5,264 once invoked), scanned A, original, MIT.

A guide for restructuring existing code to make it easier to understand, change, and maintain. It uses ideas such as giving each component one responsibility, removing duplication, and keeping solutions simple.

In plain words
What is it for?
It helps clean up legacy code, reduce complexity, remove code smells, improve architecture, and apply reusable design patterns.
Why use it?
It addresses tangled structure, repeated code, excessive complexity, and other forms of maintenance work that make future changes harder.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps clean up legacy code, reduce complexity, remove code smells, improve architecture, and apply reusable design patterns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mehdiozdemir/awesome-agent-skills/refactoring-assistant
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.

Any agent
npx skills add mehdiozdemir/awesome-agent-skills --skill refactoring-assistant
Clone the repo
git clone --depth 1 https://github.com/mehdiozdemir/awesome-agent-skills

Made for: Claude Code, Codex.

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 refactoring-assistant

README.md
[![agentmods](https://agentmods.dev/badge/skills/mehdiozdemir/awesome-agent-skills/refactoring-assistant/github.svg)](https://agentmods.dev/skills/mehdiozdemir/awesome-agent-skills/refactoring-assistant)
Your own site
<a href="https://agentmods.dev/skills/mehdiozdemir/awesome-agent-skills/refactoring-assistant"><img src="https://agentmods.dev/badge/skills/mehdiozdemir/awesome-agent-skills/refactoring-assistant/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.

agentmods 80×15 button for refactoring-assistant

Your own site · 80×15
<a href="https://agentmods.dev/skills/mehdiozdemir/awesome-agent-skills/refactoring-assistant"><img src="https://agentmods.dev/badge/skills/mehdiozdemir/awesome-agent-skills/refactoring-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,264 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.05264
Opus 5 $0.00027 $0.02632
Sonnet 5 $0.00011 $0.01053
Haiku 4.5 $0.00005 $0.00526

Measured 11d ago against content hash 83249357efd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

refactoring-assistant 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 11d 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.

skills/refactoring-assistant/SKILL.md · 842 lines

How it starts

The opening of the file, as written. The whole thing — 842 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactoring Assistant Skill

This skill guides systematic code improvement through proven refactoring techniques. Use this whenever you need to clean up code, reduce technical debt, improve structure, or apply better design patterns.

Core Refactoring Principles

1. SOLID Principles

Principle Description Violation Signs
Single Responsibility One class = one reason to change Large classes, mixed concerns
Open/Closed Open for extension, closed for modification Frequent edits to existing code
Liskov Substitution Subtypes must be substitutable Broken inheritance, type checks
Interface Segregation Many specific interfaces > one general Fat interfaces, unused methods
Dependency Inversion Depend on abstractions, not concretions Hard-coded dependencies

2. DRY (Don't Repeat Yourself)

  • Eliminate duplicate code
  • Extract common logic into reusable components
  • Use configuration over hardcoding
  • Single source of truth for data

3. KISS (Keep It Simple, Stupid)

  • Prefer simple solutions over clever ones
  • Avoid premature optimization
  • Reduce unnecessary complexity
  • Write readable, self-documenting code

4. YAGNI (You Ain't Gonna Need It)

  • Don't add functionality until needed
  • Remove unused code
  • Avoid speculative generality
  • Build for today's requirements

Code Smells Catalog

Bloaters

Code that has grown excessively large:

Smell Description Refactoring
Long Method Method > 20-30 lines Extract Method
Large Class Class doing too much Extract Class
Primitive Obsession Overuse of primitives Replace with Value Object
Long Parameter List > 3-4 parameters Parameter Object, Builder
Data Clumps Groups of data appearing together Extract Class

Object-Orientation Abusers

Misuse of OOP principles:

Smell Description Refactoring
Switch Statements Complex conditionals Replace with Polymorphism
Temporary Field Fields only sometimes used Extract Class
Refused Bequest Subclass not using parent methods Replace Inheritance with Delegation
Alternative Classes Similar classes, different interfaces Rename, Merge Classes

Read the full file on GitHub · 842 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. 11d ago First seen · 842 lines · 54 tokens per session scan A 83249357efd7

Subscribe to this mod's changes

refactoring-assistant is a skill published in the GitHub repository mehdiozdemir/awesome-agent-skills (2 stars, last pushed 7mo ago), licensed MIT. It adds 54 tokens to every session and 5,264 once invoked, about $0.0003 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.