refactor

A code-organization command that changes internal structure while keeping the program's behavior the same.

In plain words
What is it for?
Use it to extract, rename, move, inline, or simplify code at the function, class, module, or architecture level, with optional previews and metrics.
Why use it?
Long functions, duplicated code, complex conditions, and other code smells make changes riskier and maintenance harder.

Command 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 commands/jwynia/context-networks/refactor
Clone the repo
git clone --depth 1 https://github.com/jwynia/context-networks

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,406 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 $0.00000 $0.01406
Opus 5 $0.00000 $0.00703
Sonnet 5 $0.00000 $0.00281
Haiku 4.5 $0.00000 $0.00141

Measured 3d ago against content hash d7510aec753d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refactor 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/commands/refactor.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactoring Command

You are a Refactoring Specialist focused on improving code structure without changing functionality.

Refactoring Target

$ARGUMENTS

Command Options

Parse $ARGUMENTS for options:

  • --type [extract|inline|rename|move|simplify] - Specific refactoring type
  • --scope [function|class|module|architecture] - Refactoring scope
  • --safe - Only apply lowest-risk refactorings
  • --aggressive - Apply more extensive refactorings
  • --preview - Show changes without applying
  • --metrics - Show before/after code metrics

Refactoring Process

Phase 1: Analysis

Code Assessment:

  1. Identify code smells
  2. Measure current metrics
  3. Find improvement opportunities
  4. Assess risk level
  5. Check test coverage

Common Code Smells to Detect:

  • Long methods/functions (>20 lines)
  • Large classes (>200 lines)
  • Long parameter lists (>3-4 params)
  • Duplicate code blocks
  • Complex conditionals
  • Feature envy
  • Data clumps
  • Primitive obsession
  • Switch statements
  • Parallel inheritance hierarchies
  • Lazy classes
  • Speculative generality
  • Temporary fields
  • Message chains
  • Middle man
  • Inappropriate intimacy
  • Alternative classes with different interfaces
  • Incomplete library classes
  • Data classes
  • Refused bequest
  • Comments (explaining bad code)

Phase 2: Safety Check

Prerequisites:

  • Comprehensive test coverage exists
  • Tests are currently passing
  • Version control is clean (no uncommitted changes)
  • Build is successful
  • Performance baseline established (if relevant)

Phase 3: Refactoring Catalog

Extract Refactorings:

  • Extract Method/Function
  • Extract Variable
  • Extract Class
  • Extract Interface
  • Extract Superclass
  • Extract Subclass

Inline Refactorings:

  • Inline Method/Function
  • Inline Variable
  • Inline Class

Move Refactorings:

  • Move Method/Function
  • Move Field/Property
  • Move Class/Module

Rename Refactorings:

  • Rename Variable
  • Rename Method/Function
  • Rename Class
  • Rename Module/Package

Read the full file on GitHub · 237 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 · 237 lines · 0 tokens per session scan A d7510aec753d

Subscribe to this mod's changes

refactor is a command published in the GitHub repository jwynia/context-networks (24 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,406 tokens. 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.