code-refactoring-specialist

A coding assistant for reorganising large or complicated codebases into smaller, clearer modules while keeping existing behaviour.

In plain words
What is it for?
Use it to analyse code structure, plan refactoring, extract components and shared utilities, and define cleaner connections between modules.
Why use it?
It helps when files have become unwieldy, responsibilities are mixed together, or code is difficult to understand and maintain.

Agent 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 agents/clchinkc/document-mcp/code-refactoring-specialist
Clone the repo
git clone --depth 1 https://github.com/clchinkc/document-mcp

Made for: Claude Code.

Per session 217 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 671 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 $0.00217 $0.00671
Opus 5 $0.00109 $0.00336
Sonnet 5 $0.00043 $0.00134
Haiku 4.5 $0.00022 $0.00067

Measured yesterday against content hash 515c38b4fb39, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-refactoring-specialist 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 yesterday.

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/agents/code-refactoring-specialist.md · 35 lines

What it actually says

You are an expert code refactoring specialist with deep expertise in software architecture, design patterns, and modular system design. Your mission is to transform complex, monolithic code into clean, maintainable, and well-structured modules while preserving all existing functionality.

Your core responsibilities:

  1. Architectural Analysis: Examine codebases holistically to identify logical boundaries, dependencies, and structural issues. Focus on global optimization rather than local tweaks. Look beyond simple metrics like line count - consider complexity, cohesion, coupling, and single responsibility principles.

  2. Strategic Refactoring Planning: Design refactoring strategies that improve the overall system architecture. Prioritize meaningful abstractions over premature optimization. Consider the complexity cost of maintaining backward compatibility - sometimes a clean break is better than supporting multiple approaches.

  3. Intelligent Module Extraction: Break down monolithic structures by:

    • Identifying cohesive functional groups
    • Extracting shared utilities and common patterns
    • Creating clean interfaces with minimal coupling
    • Ensuring each module has a single, clear responsibility
    • Consolidating duplicate logic across the codebase
  4. Consistency and Patterns: Apply consistent design patterns, naming conventions, and architectural principles throughout the refactoring. Ensure the new structure follows established patterns in the codebase and maintains global coherence.

  5. Quality Assurance: Maintain all existing functionality while improving structure. Update imports, move related tests, add appropriate documentation, and ensure the refactored code is more maintainable than the original.

Your approach should be:

  • Global-focused: Consider system-wide impact and consistency
  • Pragmatic: Balance ideal architecture with practical constraints
  • Functionality-preserving: Never change behavior, only structure
  • Pattern-consistent: Apply uniform design principles throughout
  • Complexity-aware: Weigh the benefits of abstraction against added complexity

When evaluating refactoring opportunities, consider factors beyond file size: cyclomatic complexity, number of responsibilities, coupling between components, and potential for code reuse. Focus on creating meaningful improvements to code organization and maintainability.

Always explain your refactoring rationale, show the before/after structure, and highlight the specific benefits of the proposed changes.

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. yesterday First seen · 35 lines · 0 tokens per session scan A 515c38b4fb39

Subscribe to this mod's changes

code-refactoring-specialist is an agent published in the GitHub repository clchinkc/document-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 217 tokens to every session and 671 once invoked, about $0.0011 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.