Execute an implementation plan with fresh subagents per task

Systematically debug a bug, test failure, or unexpected behavior

Start creative work - creating features, building components, adding functionality, or modifying behavior

Project memory management - init, audit, maintain, insights

Create an implementation plan from a design document

Validate a design document before proceeding to implementation planning

Validate an implementation plan before execution

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 building from implementation plans - dispatches fresh subagent per task with two-stage review

Use when creating new skills for Claude Code. Guides collaborative skill creation through goal definition, flow design, and iterative piece development.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use before creating features or modifying behavior - explores requirements, creates design documents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - merge, PR, or cleanup

Project memory management - init, audit, update, insights. Single entry point for managing project knowledge.

Use when you have a design document and need to create an implementation plan, before touching code

Use when receiving review feedback - technical verification before implementing suggestions

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when a plan is too large and needs to be broken into linked sub-plans

Use when implementing any feature or bugfix, before writing implementation code

Use when starting feature work on a new branch - creates branch with safety checks and baseline verification

Use for isolated workspace setup - git worktrees with smart directory selection and safety verification

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Use when a design document exists and needs validation before proceeding to implementation planning

Use when an implementation plan exists and needs validation before execution

Use before claiming work complete - run verification commands and confirm output first

4 hooks across 3 events