Coordinates project structure: SCAFFOLD new or RESTRUCTURE existing to Clean Architecture
E2E Critical Coverage audit worker. Validates E2E coverage for critical paths (Money 20+, Security 20+, Data 15+). Pure risk-based - no pyramid percentages.
Research standards/patterns via MCP Ref. Generates Standards Research for Story Technical Notes subsection. Reusable worker.
Checks isolation (APIs/DB/FS/Time/Random/Network), determinism (flaky, order-dependent), and 7 anti-patterns.
Detects tests that validate framework/library behavior (Prisma, Express, bcrypt, JWT, axios, React hooks) instead of OUR code. Returns findings with REMOVE decisions.
Checks layer leakage in method signatures, missing DTOs, entity leakage to API, inconsistent error contracts. Returns findings with penalty-based scoring.
Universal project bootstrapper: CREATE new or TRANSFORM existing project to production-ready structure
Creates task management documentation (docs/tasks/README.md + kanban_board.md). Sets up Linear integration and task tracking rules.
Generates GitHub Actions CI workflow configuration
Traffic-First opportunity discovery. KILL funnel filters ideas by traffic channel, demand, competition, revenue, interest, MVP-ability. Outputs one idea + one channel recommendation.
Builds and launches Docker containers with health verification using best practices
Configures structured logging (Serilog/.NET, structlog/Python)
Creates 4 core project docs (requirements.md, architecture.md, tech_stack.md, patterns_catalog.md). ALWAYS created.
Creates ALL task types (implementation, refactoring, test). Generates task documents from templates, validates type rules, creates in Linear, updates kanban.
Configures ESLint, Prettier, Ruff, mypy, and .NET analyzers
Checks async races, thread safety, TOCTOU, deadlocks, blocking I/O, resource contention, cross-process races. Two-layer detection: grep + agent reasoning.
Creates design_guidelines.md for frontend projects. Invoked when hasFrontend detected.
Checks bootstrap initialization order, graceful shutdown, resource cleanup, signal handling, liveness/readiness probes. Returns findings.
Updates ALL task types (implementation/refactoring/test). Compares IDEAL plan vs existing tasks, categorizes KEEP/UPDATE/OBSOLETE/CREATE, applies changes in Linear and kanban.
Identifies missing tests for critical paths (Money 20+, Security 20+, Data Integrity 15+, Core Flows 15+). Returns list of untested critical business logic with priority justification.