Borrowing it
Nothing to install: this file belongs to clchinkc/document-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/clchinkc/document-mcp/main/.claude/agents/code-refactoring-specialist.mdgit clone --depth 1 https://github.com/clchinkc/document-mcpWrote 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.
[](https://agentmods.dev/agents/clchinkc/document-mcp/code-refactoring-specialist)<a href="https://agentmods.dev/agents/clchinkc/document-mcp/code-refactoring-specialist"><img src="https://agentmods.dev/badge/agents/clchinkc/document-mcp/code-refactoring-specialist/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/clchinkc/document-mcp/code-refactoring-specialist"><img src="https://agentmods.dev/badge/agents/clchinkc/document-mcp/code-refactoring-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00217 | $0.00671 |
| Opus 5.5 | $0.00087 | $0.00268 |
| Sonnet 5.5 | $0.00043 | $0.00134 |
| Haiku 4.5 | $0.00022 | $0.00067 |
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 2mo 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.
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:
-
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.
-
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.
-
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
-
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.
-
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.
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.
- 2mo ago First seen · 35 lines · 0 tokens per session scan A 515c38b4fb39
code-refactoring-specialist is an agent published in the GitHub repository clchinkc/document-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 217 tokens to every session and 671 once invoked, about $0.0009 per session on Opus 5.5. 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.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.