gremlins

Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: <example>Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Great work! Now let me use the code-reviewer agent to review the implementation against our plan and coding standards" <commentary>Since a major project step has been completed, use the code-reviewer agent to validate the work against the plan and identify any issues.</commentary></example> <example>Context: User has completed a significant feature implementation. user: "The API endpoints for the task management system are now complete - that covers step 2 from our architecture document" assistant: "Excellent! Let me have the code-reviewer agent examine this implementation to ensure it aligns with our plan and follows best practices" <commentary>A numbered step from the planning document has been completed, so the code-reviewer agent should review the work.</commentary></example>

Use when planning or designing features and you need to understand current codebase state, find existing patterns, or verify assumptions about what exists. Prevents hallucination by grounding plans in reality. Examples: <example>Context: Starting brainstorming phase and need to understand current implementation. user: "I want to add OAuth support to our app" assistant: "Let me use the codebase-investigator agent to understand how authentication currently works before we design the OAuth integration" <commentary>Before designing new features, investigate existing patterns to ensure the design builds on what's already there.</commentary></example> <example>Context: Writing implementation plan and need to verify file locations. user: "Create a plan for adding user profiles" assistant: "I'll use the codebase-investigator agent to verify the current user model structure and find where user-related code lives" <commentary>Investigation prevents hallucinating file paths or assuming structure that doesn't exist.</commentary></example>

Fast, lightweight subagent for tasks requiring less analysis. Good for research, summarization, file operations, and quick tool calls. Use when speed and cost matter more than deep reasoning.

Use when planning or designing features and you need current information from the internet, API documentation, library usage patterns, or external knowledge. Examples: <example>Context: Designing integration with external service. user: "I want to integrate with the Stripe API for payments" assistant: "Let me use the internet-researcher agent to find the current Stripe API documentation and best practices for integration" <commentary>Before designing integrations, research current API state to ensure plan matches reality.</commentary></example> <example>Context: Evaluating technology choices. user: "Should we use library X or Y for this feature?" assistant: "I'll use the internet-researcher agent to research both libraries' current status, features, and community recommendations" <commentary>Research helps make informed technology decisions based on current information.</commentary></example>

Heavyweight subagent for tasks requiring deep reasoning, complex analysis, or nuanced judgment. Good for architectural decisions, difficult debugging, and tasks where quality is paramount. Use sparingly due to cost.

Use when completing development phases and project context files may need updating - analyzes what changed since phase start, identifies affected CLAUDE.md files, and coordinates updates to maintain accurate project documentation

Balanced subagent for tasks requiring attention to detail, thinking, and analysis. Good for implementation, code review, and moderate complexity tasks. Use when you need quality without the cost of opus.

Fixes issues identified by code-reviewer and triggers re-review. Use when code-reviewer returns any issues that need to be addressed before merge approval.

Implements individual tasks from plans with TDD, skill application, verification, and git commits. Use when executing a specific task that requires writing, modifying, or testing code as part of a larger plan.