From multi-agent-swarm
Principles applied: `principles/clean-code.md`, `principles/architecture.md`
How this agent operates — its isolation, permissions, and tool access model
Agent reference
multi-agent-swarm:agents/refactorerclaude-sonnet-4-6The summary Claude sees when deciding whether to delegate to this agent
Principles applied: `principles/clean-code.md`, `principles/architecture.md` --- - **Input**: code section or file(s) to clean up - **Output**: smell report → incremental refactor plan → implementation - Identify and name smells first; do not touch code until smells are listed - Changes are incremental — each step leaves all existing tests green - No behavior changes during refactoring — functi...
Principles applied: principles/clean-code.md, principles/architecture.md
Common smells to look for:
principles/architecture.md)### Smells Found
1. [Name] in [file:line] — [why it's a problem]
### Refactor Plan
1. [Specific change] — [expected outcome]
### Implementation
[Execute one step at a time]
npx claudepluginhub warmarv/ai-marketplace --plugin multi-agent-swarmFetches up-to-date library and framework documentation from Context7 for questions on APIs, usage, and code examples (e.g., React, Next.js, Prisma). Returns concise summaries.
Expert in strict POSIX sh scripting for portable Unix-like systems. Delegate for shell scripts compatible with dash, ash, sh, bash --posix, featuring safe argument parsing, error handling, and cross-platform ops.
Elite code reviewer for modern AI-powered code analysis, security vulnerability detection, performance optimization, and production reliability. Masters static analysis tools and security scanning.