caro: fast Rust CLI that turns natural‑language tasks into a safe POSIX command. Built for macOS (MLX/Metal) with a built‑in model; supports vLLM/Ollama/LM Studio. JSON‑only output, safety checks, confirmation, multi‑step goals, devcontainer included.
This repository also configures its own agents. See what caro tells them →
Agent Claude Code
Use this agent when developing, debugging, or enhancing the caro Rust CLI application. This includes implementing new features, optimizing performance, adding backend integrations, improving safety validation, handling cross-platform compatibility issues, or refactoring the codebase. Examples: Context: User is working…
Agent Claude Code
Use this agent when building production-grade Rust applications that require enterprise-level quality standards, comprehensive architecture design, or when implementing complex CLI tools with safety-critical requirements. Examples: Context: User is building a production Rust CLI tool with safety validation and…
Agent Claude Code
Use this agent when you need to refactor, optimize, or improve existing Rust code for better maintainability, performance, and idiomatic style. This agent specializes in applying Rust best practices, identifying anti-patterns, and optimizing code for both human and AI readability.\n\nExamples:\n\n \nContext: User has…
Agent Claude Code
Use this agent when you want to implement Spec-Driven Development using GitHub's spec-kit methodology. Examples: Context: User wants to build a new application using structured specification-first approach. user: 'I want to build a task management app for my team' assistant: 'I'll use the spec-driven-dev-guide agent…
Agent Claude Code
Use this agent when you need to write code that matches a specific author's style, patterns, and practices. This agent is designed to receive a detailed style report about an author and then implement new features or modifications that feel like the original author wrote them. It excels at maintaining consistency with…
Agent Claude Code
Use this agent when you need to systematically investigate bugs, diagnose failures, or perform root cause analysis. Inspired by GSD's debug agent pattern - spawns with fresh context to investigate specific issues without context contamination. Examples: Context: A test is failing intermittently and the cause is…
Agent Claude Code
Use this agent when you need to implement Rust projects following strict Test-Driven Development (TDD) practices and clean code principles. Examples include: building CLI tools, implementing domain logic with comprehensive test coverage, creating modular architectures with proper separation of concerns, or when you…
Agent Claude Code
Use this agent when the user wants to develop Rust code using strict Test-Driven Development (TDD) methodology with a file watcher. This agent should be used proactively during any Rust development session where TDD is appropriate, including:\n\n \nContext: User is starting work on a new Rust feature\nuser: "I need to…
Agent Claude Code
Use this agent when you need to create, edit, or improve technical documentation including README files, API documentation, user guides, tutorials, or any other technical content. This agent specializes in markdown (MD), MDX, and documentation platforms like Docusaurus and Mintlify. Examples: Context: User has just…
Agent Claude Code
Use this agent when you need to develop, migrate, or architect OS-level command-line programs, system utilities, or low-level infrastructure code following UNIX/POSIX engineering principles. This agent excels at creating modular, portable, and performant system software with clear separation between library components…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: