refactor

refactor is a command for Claude Code from design-and-deliver/claude-code-autoconfig. It costs 15 tokens per session (935 once invoked), scanned A, original, MIT.

A command for cleaning up one structurally oversized or complicated source file along a meaningful code boundary. It first checks project rules, tests, and uncommitted changes before choosing or using a target file.

In plain words
What is it for?
Use it to select a high-payoff file for refactoring or to refactor a specified file after its tests and repository conditions pass the required checks.
Why use it?
It prevents refactoring from starting when the project is already failing or when a file is unsafe to edit. It focuses the work on reducing future maintenance cost rather than merely moving code around.

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/design-and-deliver/claude-code-autoconfig/refactor
Clone the repo
git clone --depth 1 https://github.com/design-and-deliver/claude-code-autoconfig

Made for: Claude Code.

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/commands/design-and-deliver/claude-code-autoconfig/refactor.svg)](https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/refactor)
Your own site
<a href="https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/refactor"><img src="https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/refactor.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 935 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 $0.00015 $0.00935
Opus 5 $0.00008 $0.00467
Sonnet 5 $0.00003 $0.00187
Haiku 4.5 $0.00002 $0.00093

Measured 4d ago against content hash ce9ea9f7ec33, 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 4d 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 · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactor

One session, one target: make the codebase structurally cheaper for every future session. The thresholds (~500 LOC per file, ~CC 10 per function) nominate targets — they never grade the output. Never split code just to move a number.

Argument: $ARGUMENTS — optional path to the target file. Empty → rank and pick (Step 1).

Step 0: preconditions (hard gates)

  1. Read CLAUDE.md and .claude/rules/ for invariants and trap lists (canonical-copy files, generated files, machine-parsed wording, append-only files). Anything named there is OFF LIMITS as a target unless the user explicitly passed it — and then flag the trap before touching it.
  2. Run the project's test suite. Not green → STOP and report; a refactor never starts from red.
  3. git status — uncommitted changes in the target file → stop and ask.

Step 1: pick the target (skip if a path was passed)

Rank candidate source files by payoff = churn × structural weight:

  • Churn: commits touching each file in the last 90 days — git log --since="90 days ago" --name-only --pretty=format: | sort | uniq -c | sort -rn
  • Size: LOC.
  • Branch density: count of branch tokens (if, else if, case, catch, &&, ||, ternary ?) — a cheap complexity proxy; good enough for ranking, no linter needed.

Exclude: generated files, vendored code, tests, lockfiles, and the Step-0 trap list. Show the top 5 with their numbers; target = #1.

Read the full file on GitHub · 80 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. 4d ago First seen · 80 lines · 15 tokens per session scan A ce9ea9f7ec33

Subscribe to this mod's changes

refactor is a command published in the GitHub repository design-and-deliver/claude-code-autoconfig (2 stars, last pushed 6d ago), licensed MIT. It adds 15 tokens to every session and 935 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.