refactor

refactor is a skill for Claude Code from kzytateishi/spikeee-plugins-marketplace. It costs 70 tokens per session (1,362 once invoked), scanned A, original, MIT.

A guide for repeatedly improving recently changed code. It reviews structure, readability, and alignment with the project’s coding conventions, checking the code between rounds.

In plain words
What is it for?
Use it after implementation and before review to refactor changed source and related test files, then produce a before-and-after report.
Why use it?
It helps remove duplication and awkward code while preserving working behaviour through tests and lint checks.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the dev-workflow plugin — 6 skills shipped together

Good fit Use it after implementation and before review to refactor changed source and related test files, then produce a before-and-after report.

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

Made for: Claude Code.

Or install dev-workflow, the plugin that ships this one along with the rest of its 6 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

README.md
[![agentmods](https://agentmods.dev/badge/skills/kzytateishi/spikeee-plugins-marketplace/refactor/github.svg)](https://agentmods.dev/skills/kzytateishi/spikeee-plugins-marketplace/refactor)
Your own site
<a href="https://agentmods.dev/skills/kzytateishi/spikeee-plugins-marketplace/refactor"><img src="https://agentmods.dev/badge/skills/kzytateishi/spikeee-plugins-marketplace/refactor/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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kzytateishi/spikeee-plugins-marketplace/refactor"><img src="https://agentmods.dev/badge/skills/kzytateishi/spikeee-plugins-marketplace/refactor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,362 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 $0.00070 $0.01362
Opus 5 $0.00035 $0.00681
Sonnet 5 $0.00014 $0.00272
Haiku 4.5 $0.00007 $0.00136

Measured 12d ago against content hash f9bd644c9b12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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/dev-workflow/skills/refactor/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactor

Run iterative refactoring on files changed in $ARGUMENTS (or the current branch if no arguments are provided).

Iterative Refactoring Principle

CRITICAL: Refactoring is NOT a one-pass process. You MUST execute at minimum 3 separate rounds. Do NOT combine rounds or skip ahead. After completing Round 3, evaluate if more rounds are needed and continue until no improvements remain.

Round 1: Structural improvements (DRY, method extraction)
   ↓ run tests + lint → verify
Round 2: Readability (naming, nesting reduction)
   ↓ run tests + lint → verify
Round 3: Convention compliance (patterns, best practices)
   ↓ run tests + lint → verify
Round N: Continue if improvements remain

Phase 1: Identify Target Files

Base Branch Detection

Detect the base branch automatically:

  1. git remote show origin → check HEAD branch
  2. Check for main, master, or develop branches
  3. If undetectable, ask the user

Collect Changed Files

git branch --show-current
git diff --name-only {base_branch}...HEAD
git diff {base_branch}...HEAD

Important: Refactor source code and related test code together. If no related tests exist, refactor source only and note the missing test coverage.

Phase 2: Environment Detection

Auto-detect the project's test and lint commands from configuration files. If undetectable, ask the user.

Read project conventions from CLAUDE.md and AGENTS.md if present.

  • Non-interactive mode: Always run commands in non-interactive mode to prevent watch-mode hangs.

Phase 3: Iterative Refactoring Rounds

Round 1: Structural Improvements

  • Eliminate duplicate code (DRY principle)
  • Split long methods/functions (target ≤ 20 lines)
  • Reduce deep nesting (use early returns)
  • Separate responsibilities (Single Responsibility Principle)

Round 2: Readability

  • Improve variable/function/method names (clear intent)
  • Remove unnecessary comments (self-evident code)
  • Simplify conditional expressions
  • Extract magic numbers to named constants

Read the full file on GitHub · 158 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 158 lines · 70 tokens per session scan A f9bd644c9b12

Subscribe to this mod's changes

refactor is a skill published in the GitHub repository kzytateishi/spikeee-plugins-marketplace (5 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 1,362 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.