refactor

refactor is a skill for Claude Code, Codex from RamonBedin/mcp-game-deck. It costs 17 tokens per session (694 once invoked), scanned A, original, MIT.

A code-refactoring assistant for a file, directory, or wider system. Refactoring means reorganizing code without changing its intended behavior.

In plain words
What is it for?
Use it to address duplicated code, overloaded responsibilities, testing difficulties, or performance concerns. It compares the original and revised code and checks related usages.
Why use it?
It first asks what is wrong and what must remain compatible, helping prevent an improvement from breaking existing callers or behavior.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the mcp-game-deck plugin — 24 skills, 10 agents shipped together

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 skills/ramonbedin/mcp-game-deck/refactor
Any agent
npx skills add RamonBedin/mcp-game-deck --skill refactor
Clone the repo
git clone --depth 1 https://github.com/RamonBedin/mcp-game-deck

Made for: Claude Code, Codex.

Or install mcp-game-deck, the plugin that ships this one along with the rest of its 24 skills, 10 agents.

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/skills/ramonbedin/mcp-game-deck/refactor.svg)](https://agentmods.dev/skills/ramonbedin/mcp-game-deck/refactor)
Your own site
<a href="https://agentmods.dev/skills/ramonbedin/mcp-game-deck/refactor"><img src="https://agentmods.dev/badge/skills/ramonbedin/mcp-game-deck/refactor.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 694 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 $0.00694
Opus 5 $0.00009 $0.00347
Sonnet 5 $0.00003 $0.00139
Haiku 4.5 $0.00002 $0.00069

Measured 4d ago against content hash 154e16c6d160, 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.

Plugin~/skills/refactor/SKILL.md · 80 lines

What it actually says

When this skill is invoked:

  1. Parse the target path from the user's message. If the user wrote /refactor Assets/Scripts/Combat/DamageSystem.cs, the target is that file. If a directory was given, treat all scripts in it as the target. If no path was provided, ask for one.

  2. Ask for the following inputs before doing any analysis:

    • Problem: "What's wrong with the current code? What problem are you trying to solve?" (e.g., too many responsibilities, hard to test, performance issues, code duplication)
    • Constraints: "What must NOT change? List any API contracts, public interfaces, or behaviors that must remain compatible." (e.g., "other systems call DamageSystem.Apply(), that signature must stay the same")

    Wait for the user to answer both before proceeding.

  3. Read the target file(s) in full using the Read tool. Also read:

    • Files that reference the target (use Grep to find usages)
    • Related KB docs for recommended patterns:
      • ${CLAUDE_PLUGIN_ROOT}/knowledge/01-unity-project-architecture.md for structure
      • ${CLAUDE_PLUGIN_ROOT}/knowledge/03-unity-design-patterns.md for patterns
      • Other KB docs as relevant to the specific problem
  4. Analyze the current architecture and identify:

    • Single Responsibility violations
    • Dependency direction issues
    • Unity anti-patterns (Find, GetComponent in Update, public fields, etc.)
    • Code duplication
    • Methods exceeding 40 lines
    • Missing event-driven communication
    • Testability concerns
  5. Propose the refactored version with a clear explanation:

    ## Refactor Plan: [File/System Name]
    
    ### Problem
    [Summarize what's wrong]
    
    ### Constraints
    [List what must not change]
    
    ### Changes
    [For each change]:
    - **What**: [description of the change]
    - **Why**: [which principle or pattern this fixes]
    - **Before**: [relevant code snippet]
    - **After**: [proposed code snippet]
    
    ### Impact
    - Files modified: [list]
    - Files created: [list, if extracting new classes]
    - Public API changes: [none / list breaking changes]
    
    ### Risk
    [What could break, what to test after]
    
  6. Wait for user confirmation before applying any changes. Ask: "Apply these changes? I'll modify the files and you can review the diff. Say 'apply' to proceed or tell me what to adjust."

  7. Apply changes only after the user confirms. Use Edit for surgical changes, Write only for new files. After applying:

    • List all modified files
    • Suggest running tests or compilation to verify
    • Note any manual steps needed (e.g., updating serialized references in the Inspector)
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 · 17 tokens per session scan A 154e16c6d160

Subscribe to this mod's changes

refactor is a skill published in the GitHub repository RamonBedin/mcp-game-deck (6 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 694 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens