refactor

refactor is a command for Claude Code from satanyakiv/NutriSport. It costs 0 tokens per session (487 once invoked), scanned A, original, MIT.

A guided code-refactoring command for a Kotlin project. It checks the project’s architecture rules, adds tests when needed, applies structural changes without changing behavior, and verifies the result.

In plain words
What is it for?
Use it to move models between data, domain, and user-interface layers; extract or update mappers and use cases; and run the relevant tests and compilation checks.
Why use it?
It reduces the risk of breaking existing behavior while reorganizing code. It also makes layer and model-boundary problems visible before changes are made.

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/satanyakiv/nutrisport/refactor
Clone the repo
git clone --depth 1 https://github.com/satanyakiv/NutriSport

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/satanyakiv/nutrisport/refactor.svg)](https://agentmods.dev/commands/satanyakiv/nutrisport/refactor)
Your own site
<a href="https://agentmods.dev/commands/satanyakiv/nutrisport/refactor"><img src="https://agentmods.dev/badge/commands/satanyakiv/nutrisport/refactor.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 487 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 $0.00000 $0.00487
Opus 5 $0.00000 $0.00244
Sonnet 5 $0.00000 $0.00097
Haiku 4.5 $0.00000 $0.00049

Measured 4d ago against content hash a09a6950f954, 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 · 48 lines

What it actually says

Read .claude/rules/architecture.md, .claude/rules/models.md, .claude/rules/testing.md, .claude/rules/conventions.md

Refactor

$ARGUMENTS

Process

  1. AUDIT: Read all affected files. List violations against architecture rules. Show:

    • Files to change (with line numbers)
    • What moves where (which layer/module)
    • What gets extracted/merged/renamed
    • Model boundaries: any Dto leaking? Domain model in UI? Missing mappers? Wait for "go".
  2. TEST FIRST (if tests don't exist yet):

    • Write tests capturing CURRENT behavior before refactoring
    • These are the safety net — must still pass after refactor
    • Run: ./gradlew :{module}:allTests --tests "*TestClass" — must PASS
  3. REFACTOR: Apply changes. Zero behavior changes.

    • Move models to correct layers with proper suffixes (Dto/Ui)
    • Extract/update mappers (.toDomain(), .toUi())
    • Keep ViewModel logic in feature, data logic in network, domain pure
    • Extract UseCase if ViewModel business logic > 10 lines
  4. VERIFY:

    • ./gradlew :{module}:allTests — all pass
    • ./gradlew :{module}:compileCommonMainKotlinMetadata — compiles
  5. CHECKLIST:

    • No file > 150 lines, no function > 20 lines
    • No Dto outside :network, no domain models in Composables
    • No Firebase/network imports in feature modules
    • All mappers tested
    • Convention plugins used (no manual plugin config)
    • Koin registration in :di only
    • Screen uses Route-Screen separation (ViewModel not injected in Screen)
  6. UPDATE .claude/rules/ files if architecture changed

Rules

  • ZERO behavior changes. Same inputs → same outputs.
  • Never ./gradlew test without --tests filter
  • Never break existing tests
  • If unsure → ask, don't guess
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 · 48 lines · 0 tokens per session scan A a09a6950f954

Subscribe to this mod's changes

refactor is a command published in the GitHub repository satanyakiv/NutriSport (11 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 487 tokens. 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.