refactor

refactor is a command for Claude Code from dachivadachkoria/claude-code-starter-kit. It costs 11 tokens per session (1,425 once invoked), scanned A, original, MIT.

A refactoring workflow for changing code while checking that tests still pass. Refactoring means improving code structure without intending to change what it does.

In plain words
What is it for?
Use it to extract functions or classes, verify existing tests and coverage, and safely reorganize code with a way to restore the earlier state.
Why use it?
It reduces the risk of breaking behavior by checking coverage and tests first and creating a restore point before changes.

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/dachivadachkoria/claude-code-starter-kit/refactor
Clone the repo
git clone --depth 1 https://github.com/dachivadachkoria/claude-code-starter-kit

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/dachivadachkoria/claude-code-starter-kit/refactor.svg)](https://agentmods.dev/commands/dachivadachkoria/claude-code-starter-kit/refactor)
Your own site
<a href="https://agentmods.dev/commands/dachivadachkoria/claude-code-starter-kit/refactor"><img src="https://agentmods.dev/badge/commands/dachivadachkoria/claude-code-starter-kit/refactor.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,425 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 $0.00011 $0.01425
Opus 5 $0.00005 $0.00713
Sonnet 5 $0.00002 $0.00285
Haiku 4.5 $0.00001 $0.00143

Measured 3d ago against content hash 8c3523826364, 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 · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Safe Refactoring

Refactor: $ARGUMENTS

⚠️ Pre-Refactoring Checklist

Before ANY refactoring:

  1. Verify test coverage exists

    pytest --cov=$TARGET --cov-fail-under=70 tests/
    

    If coverage < 70%, generate tests first with /test $ARGUMENTS

  2. Ensure tests pass

    pytest tests/ -x
    
  3. Create restore point

    git stash push -m "pre-refactor-$(date +%s)"
    

Refactoring Patterns

1. Extract Function

When: Code block is reused or does a distinct thing

# Before
def process_order(order):
    # Validate
    if not order.items:
        raise ValueError("Empty order")
    if order.total < 0:
        raise ValueError("Invalid total")
    # Process
    ...

# After  
def validate_order(order):
    """Validate order has items and valid total."""
    if not order.items:
        raise ValueError("Empty order")
    if order.total < 0:
        raise ValueError("Invalid total")

def process_order(order):
    validate_order(order)
    # Process
    ...

2. Extract Class

When: A group of functions operate on the same data

# Before: Functions scattered around
def send_email(to, subject, body): ...
def send_email_with_template(to, template, data): ...
def validate_email(email): ...

# After: Cohesive class
class EmailService:
    def send(self, to, subject, body): ...
    def send_template(self, to, template, data): ...
    def validate(self, email): ...

3. Simplify Conditionals

When: Complex if/else chains

# Before
def get_discount(user):
    if user.is_premium:
        if user.years > 5:
            return 0.25
        else:
            return 0.15
    else:
        if user.years > 5:
            return 0.10
        else:
            return 0.05

# After
DISCOUNT_MATRIX = {
    (True, True): 0.25,   # premium, 5+ years
    (True, False): 0.15,  # premium, <5 years
    (False, True): 0.10,  # standard, 5+ years
    (False, False): 0.05, # standard, <5 years
}

def get_discount(user):
    key = (user.is_premium, user.years > 5)
    return DISCOUNT_MATRIX[key]

Read the full file on GitHub · 248 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 · 248 lines · 11 tokens per session scan A 8c3523826364

Subscribe to this mod's changes

refactor is a command published in the GitHub repository dachivadachkoria/claude-code-starter-kit (4 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 1,425 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.