super-radical-powers

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores requirements and design before implementation.

Execute plan in batches with review checkpoints

Create detailed implementation plan with bite-sized tasks

Create detailed implementation plan with bite-sized tasks

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>

Worktree-isolated implementation agent for PARALLEL task execution. Use when subagent-driven-development dispatches a wave of parallel-eligible tasks (same `wave`, disjoint file ownership, no cross-dependencies). Each dispatch runs in its own temporary git worktree via `isolation: worktree`, so concurrent edits never collide. For sequential single-task execution in the shared worktree, use the inline implementer-prompt.md template instead — this agent exists specifically for the parallel-wave path.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

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

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use ONLY at the end of a full plan/sprint when EVERY task is complete and tests pass — invoked once by subagent-driven-development or executing-plans after the final task, never after an individual task, mid-session, or whenever implementation "feels done". Guides merge/PR/keep/discard with archive-tagging so the feature branch is preserved for rewind/history.

Use when your human partner asks to execute an implementation plan while spending local GPU/Ollama compute instead of Claude API tokens — triggers: "offload", "local model", "ollama", "use my GPU", "save tokens", "spend local compute instead of API".

8 hooks across 4 events