claude-code-superpowers

Show a full token & cost analytics dashboard — by day, project, model, activity, tools, and shell commands

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 receiving code review feedback, before implementing any suggestion — requires technical verification and reasoned evaluation, not performative agreement or blind implementation

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

Use when you have a spec or requirements for a multi-step task, before touching code

Store and retrieve patterns from past work using semantic search; adds self-learning capability to Superpowers

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 completely fresh isolated session — no context inheritance, clean slate execution with review checkpoints

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

ML-specific patterns for data pipelines, model training, MLOps, and evaluation — domain expertise for machine learning engineers

Manage context window budget across long sessions — when to compress, what to give subagents, when to start fresh. Prevents silent quality degradation as conversations grow.

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

State machines, ISRs, RTOS, hardware abstraction, and timing analysis — domain expertise for electrical and embedded systems engineers

Select optimal subagent topology (hierarchical, mesh, ring, star) based on task structure; adds Ruflo-style swarm intelligence to Superpowers

RAG architectures, agent design patterns, prompt engineering, and LLM evaluation — domain expertise for AI application engineers

Pre-task intelligence layer — classify complexity, select skill chain, search patterns, assign model tier. Run BEFORE any non-trivial task begins. Turns the system from reactive to proactive.

Structured first-pass exploration of an unfamiliar codebase — what to read, in what order, what to map, what traps to find. Use when entering any new or inherited project before writing code.

Use when executing implementation plans with independent tasks in the current session

UI/UX design intelligence, accessibility, performance, SEO, and data visualization — domain expertise for web and app developers. Includes 67 UI styles, 25 chart types, font pairing, and UX guidelines.

Use when creating new skills, editing existing skills, or verifying skills work before deployment — applies TDD to process documentation with the same Iron Law as FORGE

Use when implementation is complete and all tests pass — guides branch completion through four structured options (merge, PR, keep, discard) with verification and worktree cleanup

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

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

Use when starting feature work that needs isolation from the current workspace, or before executing implementation plans — creates isolated git worktrees with smart directory selection and safety verification

Select optimal AI model by task complexity — route to cheap/fast models for simple tasks, capable models for complex reasoning

1 hook across 1 event