refactor-with-ai

refactor-with-ai is a skill for Claude Code from latestaiagents/agent-skills. It costs 54 tokens per session (1,854 once invoked), scanned A, original, MIT.

A guide for changing code structure with AI while keeping its existing behavior. Refactoring means improving code without intentionally changing what it does.

In plain words
What is it for?
Use it to extract reusable functions, reduce complexity, modernize legacy code, apply design patterns, and verify changes with tests.
Why use it?
It reduces the risk of breaking working software while cleaning up complexity, old patterns, or technical debt.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the developer-toolkit plugin — 19 skills shipped together

Good fit Use it to extract reusable functions, reduce complexity, modernize legacy code, apply design patterns, and verify changes with tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/latestaiagents/agent-skills/refactor-with-ai
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 latestaiagents/agent-skills --skill refactor-with-ai
Clone the repo
git clone --depth 1 https://github.com/latestaiagents/agent-skills

Made for: Claude Code.

Or install developer-toolkit, the plugin that ships this one along with the rest of its 19 skills.

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 refactor-with-ai

README.md
[![agentmods](https://agentmods.dev/badge/skills/latestaiagents/agent-skills/refactor-with-ai/github.svg)](https://agentmods.dev/skills/latestaiagents/agent-skills/refactor-with-ai)
Your own site
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/refactor-with-ai"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/refactor-with-ai/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 refactor-with-ai

Your own site · 80×15
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/refactor-with-ai"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/refactor-with-ai.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 1,854 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 $0.01854
Opus 5 $0.00027 $0.00927
Sonnet 5 $0.00011 $0.00371
Haiku 4.5 $0.00005 $0.00185

Measured 10d ago against content hash 461e6913cf82, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

refactor-with-ai 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 10d 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/developer-toolkit/skills/code-intelligence/refactor-with-ai/SKILL.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactor with AI

Safely refactor code with AI assistance while preserving behavior.

When to Use

  • Cleaning up messy or complex code
  • Extracting reusable functions/components
  • Modernizing legacy patterns
  • Reducing cyclomatic complexity
  • Applying design patterns
  • Preparing code for new features

The Safe Refactoring Process

┌─────────────────────────────────────────┐
│ 1. CHARACTERIZE - Understand current    │
│    behavior with tests                  │
└─────────────────────────────────────────┘
                    ↓
┌─────────────────────────────────────────┐
│ 2. IDENTIFY - Find specific smells      │
│    and improvement opportunities        │
└─────────────────────────────────────────┘
                    ↓
┌─────────────────────────────────────────┐
│ 3. REFACTOR - Small, incremental        │
│    changes with AI assistance           │
└─────────────────────────────────────────┘
                    ↓
┌─────────────────────────────────────────┐
│ 4. VERIFY - Tests still pass,           │
│    behavior unchanged                   │
└─────────────────────────────────────────┘

Step 1: Characterize with Tests

Before ANY refactoring, ensure behavior is captured.

// If no tests exist, create characterization tests
describe('OrderProcessor (characterization)', () => {
  it('processes valid order', () => {
    const result = processor.process(validOrder);
    // Capture current behavior, even if not ideal
    expect(result).toMatchSnapshot();
  });

  it('handles edge cases', () => {
    expect(processor.process(null)).toBeNull();
    expect(processor.process(emptyOrder)).toEqual({ status: 'empty' });
  });
});

Step 2: Identify Code Smells

Common Smells to Look For

Smell Sign Refactoring
Long Method >20 lines Extract Method
Long Parameter List >3 params Introduce Parameter Object
Duplicate Code Copy-paste Extract and reuse
Nested Conditionals >3 levels deep Guard clauses, early return
Feature Envy Uses other class's data Move method
Data Clumps Same params together Create class/type
Primitive Obsession Strings for everything Value objects
Switch Statements Type checking Polymorphism

Read the full file on GitHub · 323 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. 10d ago First seen · 323 lines · 54 tokens per session scan A 461e6913cf82

Subscribe to this mod's changes

refactor-with-ai is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 1,854 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.