refactor

A command for reorganising one file according to the project's documented rules. Refactoring means changing code structure while keeping its intended behaviour.

In plain words
What is it for?
For reading the target and project guidance, then splitting, typing, extracting, and cleaning the file. In dry-run mode it reports proposed changes without modifying files, and it can create a feature branch when started on the main branch.
Why use it?
It reduces the risk of changing code without understanding project conventions, architecture, or type-checking requirements.

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/thedecipherist/claude-code-mastery-project-starter-kit/refactor
Clone the repo
git clone --depth 1 https://github.com/TheDecipherist/claude-code-mastery-project-starter-kit

Made for: Claude Code.

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,281 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 $0.00017 $0.02281
Opus 5 $0.00009 $0.01141
Sonnet 5 $0.00003 $0.00456
Haiku 4.5 $0.00002 $0.00228

Measured 3d ago against content hash 5a3da2d4a9ec, 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 · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactor — Best Practices Enforcement

Refactor the target file following every rule in this project's CLAUDE.md.

Target: $ARGUMENTS

If --dry-run is passed, report what WOULD change without modifying any files.

Step 0 — Auto-Branch (if on main)

Before making any changes, check the current branch:

git branch --show-current

Default behavior (auto_branch = true in claude-mastery-project.conf):

  • If on main or master: automatically create a feature branch and switch to it:
    git checkout -b refactor/<filename-without-extension>
    
    Report: "Created branch refactor/<name> — main stays untouched."
  • If already on a feature branch: proceed
  • If not a git repo: skip this check

To disable: Set auto_branch = false in claude-mastery-project.conf. When disabled, warn and ask the user before proceeding on main.

Step 0.5 — Read Before Touching

NEVER refactor blind. Read these files first:

  1. The target file (fully — every line)
  2. CLAUDE.md — to know the current project rules
  3. project-docs/ARCHITECTURE.md — to understand where things belong (if it exists)
  4. tsconfig.json — to check TypeScript strict mode settings (if it exists)

Also check:

# What imports this file? (understand the blast radius)
# Search for the filename in all source files

Report: "This file is imported by X other files. Changes here affect: [list]"

Step 1 — Audit the File

Run through EVERY check below. For each violation found, note the line number, what's wrong, and what the fix is.

1A. File Size (Rule 7: Quality Gates)

  • > 300 lines = MUST split. No exceptions.
  • Identify logical sections that can become their own files
  • Group by: types, constants, helpers/utilities, main logic, exports

1B. Function Size (Rule 7: Quality Gates)

  • > 50 lines = MUST extract. No exceptions.
  • Identify functions that do multiple things — each "thing" becomes its own function
  • Name extracted functions by what they DO, not where they came from

Read the full file on GitHub · 268 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 · 268 lines · 17 tokens per session scan A 5a3da2d4a9ec

Subscribe to this mod's changes

refactor is a command published in the GitHub repository TheDecipherist/claude-code-mastery-project-starter-kit (337 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 2,281 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 2026-08-30.