refactor

A step-by-step guide for restructuring code while keeping its behavior unchanged.

In plain words
What is it for?
Use it to remove unused code, refactor selected files, check types and style, run tests, and confirm that inputs still produce the same results.
Why use it?
It reduces the risk that cleanup, renaming, or reorganizing code introduces hidden bugs.

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/codeverbojan/claude-code-kickstart/refactor
Clone the repo
git clone --depth 1 https://github.com/codeverbojan/claude-code-kickstart

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 246 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 $0.00013 $0.00246
Opus 5 $0.00006 $0.00123
Sonnet 5 $0.00003 $0.00049
Haiku 4.5 $0.00001 $0.00025

Measured yesterday against content hash 3c8cc168eeeb, 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 yesterday.

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 · 33 lines

What it actually says

Refactor Playbook

1. Scope

  • State what you're refactoring and why (not just "cleanup").
  • Name the exact files. Refactors that touch >5 files need phases.

2. Delete First

  • Before restructuring: remove dead props, unused exports, unused imports, debug logs. Commit cleanup separately.

3. Refactor

  • Change structure, not behavior. Tests must still pass.
  • When renaming, search thoroughly: calls, types, strings, imports, re-exports, tests, mocks. Assume a single grep missed something.

4. Verify

  • Run type-checker
  • Run linter
  • Run full test suite (refactors can break things you don't expect)
  • Verify no behavior change — same inputs, same outputs.
  • Show passing output. "It's just a rename, it'll be fine" is rationalization.

5. Review

  • Ask yourself: "Is this actually simpler, or did I just move complexity?"
  • If the refactor made things harder to understand, reconsider.

$ARGUMENTS

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. yesterday First seen · 33 lines · 13 tokens per session scan A 3c8cc168eeeb

Subscribe to this mod's changes

refactor is a command published in the GitHub repository codeverbojan/claude-code-kickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 246 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.