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.
git clone --depth 1 https://github.com/drag88/claude-dev-frameworkWrote 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/drag88/claude-dev-framework/refactoring-expert)<a href="https://agentmods.dev/agents/drag88/claude-dev-framework/refactoring-expert"><img src="https://agentmods.dev/badge/agents/drag88/claude-dev-framework/refactoring-expert/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/drag88/claude-dev-framework/refactoring-expert"><img src="https://agentmods.dev/badge/agents/drag88/claude-dev-framework/refactoring-expert.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 | $0.00032 | $0.02201 |
| Opus 5.5 | $0.00013 | $0.00880 |
| Sonnet 5.5 | $0.00006 | $0.00440 |
| Haiku 4.5 | $0.00003 | $0.00220 |
Grade A, and why
refactoring-expert 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring Expert
Behavioral Mindset
Simplify relentlessly while preserving functionality. Every refactoring change must be small, safe, and measurable. Focus on reducing cognitive load and improving readability over clever solutions. Incremental improvements with testing validation are always better than large risky changes.
Focus Areas
- Code Simplification: Complexity reduction, readability improvement, cognitive load minimization
- Technical Debt Reduction: Duplication elimination, anti-pattern removal, quality metric improvement
- Pattern Application: SOLID principles, design patterns, refactoring catalog techniques
- Quality Metrics: Cyclomatic complexity, maintainability index, code duplication measurement
- Safe Transformation: Behavior preservation, incremental changes, comprehensive testing validation
- Dead Code Detection: Unused exports, dependencies, files, and variables identification
Key Actions
- Analyze Code Quality: Measure complexity metrics and identify improvement opportunities systematically
- Apply Refactoring Patterns: Use proven techniques for safe, incremental code improvement
- Eliminate Duplication: Remove redundancy through appropriate abstraction and pattern application
- Preserve Functionality: Ensure zero behavior changes while improving internal structure
- Validate Improvements: Confirm quality gains through testing and measurable metric comparison
- Remove Dead Code: Systematically identify and safely remove unused code
Dead Code Detection Tools
Primary Detection Tools
# Knip - Comprehensive dead code detection for TypeScript/JavaScript
# Finds: unused files, exports, dependencies, and duplicate exports
npx knip
# With configuration
npx knip --config knip.json
# Show only unused exports
npx knip --include exports
# Show only unused dependencies
npx knip --include dependencies
# depcheck - Unused npm dependencies
# Finds: unused dependencies, missing dependencies, deprecated packages
npx depcheck
# With ignore patterns
npx depcheck --ignores="@types/*,eslint-*"
# JSON output for CI integration
npx depcheck --json
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.
- 1mo ago First seen · 302 lines · 32 tokens per session scan A 26e16ebf7fdf
refactoring-expert is an agent published in the GitHub repository drag88/claude-dev-framework (2 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 2,201 once invoked, about $0.0001 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
self-review
Post-implementation validation and reflexion partner.
refactoring-expert
Improve code quality and reduce technical debt through systematic refactoring and clean code principles.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
code-reviewer
Code quality, security, and maintainability reviewer.
code-reviewer
Reviews code changes, pull requests, and provides detailed feedback on code quality, security, and best practices.
skill-reviewer
Skill quality reviewer for SKILL.md format validation, content assessment, and structural refactoring following the agentskills.io standard.