superpowers

Interactive design refinement using Socratic method

Execute plan in batches with review checkpoints

HENRY AI OS: Execute immediately, show output — no clarification needed

HENRY AI OS: Visual-first explanation with diagrams and short sentences

HENRY AI OS: Diagnose and fix, show what changed — no clarification needed

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 this agent when writing code, building MCP servers, designing system architecture, deploying services, debugging infrastructure, or setting up development environments. Examples: <example>Context: User needs a new MCP server built. user: "Build me an MCP server for inventory management" assistant: "Routing to /engineer for engineering — will use stdio transport with typed schemas" <commentary>Engineering task — /engineer handles all code, architecture, and deployment.</commentary></example>

Use this agent when building financial models, calculating valuations, structuring SBA loans, analyzing unit economics, projecting cash flow, or preparing financial documents. Examples: <example>Context: User needs a valuation for an acquisition target. user: "What's TXS5345 worth?" assistant: "Routing to /finance — running DCF + comparable transactions + HENRY acquisition math" <commentary>Valuation is a ledger task — always show three scenarios with sourced assumptions.</commentary></example>

Use this agent when drafting legal documents, reviewing contracts, assessing legal risk, structuring deal terms, ensuring compliance, or managing litigation context. Examples: <example>Context: User needs an LOI drafted. user: "Draft an LOI for TXS5345" assistant: "Routing to /legal — drafting non-binding LOI with standard protective terms" <commentary>Legal document drafting is a legal task — always include protective clauses and recommend attorney review.</commentary></example>

Use this agent when planning go-to-market strategy, creating marketing content, optimizing SEO, building brand strategy, designing campaigns, or generating leads. Examples: <example>Context: User needs a content strategy. user: "We need more inbound leads from Houston businesses" assistant: "Routing to /marketing — building local SEO + content strategy for Houston market" <commentary>Lead generation and content strategy is a marketing task — ROI-focused marketing.</commentary></example>

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally impossible

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently

Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches

1 hook across 1 event