core

Systematic debugging with deep reasoning. Use for: investigating errors, tracing bugs, analyzing stack traces, or methodically diagnosing unexpected behavior. Example: "/debug TypeError: Cannot read property 'map' of undefined"

Unified 6-phase SDLC with plan persistence, resume mode, and autonomous execution

Thorough technical discussion with context-aware clarifying questions

Comprehensive verification with automated quality gates, confession gathering, and confidence-based issue filtering. Default: self-review with gates. --deep: multi-agent review via code-reviewer agent. Use before committing, after fixing bugs, or to validate feature completeness.

Deep research on technical topics with intelligent caching. Supports: research, promote, refresh, and list operations. Example: "/research domain-driven design" or "/research promote ddd"

Single-problem deep reasoning with the deep-think-partner agent. Use for: debugging complex issues, evaluating tradeoffs, validating logic, or thinking through a specific decision. Example: "/think should I use Redis or PostgreSQL for session storage?"

Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences

Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development

Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter

Deep research specialist using EXA tools for comprehensive topic investigation. Use when needing to research patterns, architectures, technologies, or best practices. Manages a two-tier cache system for cross-project reuse and team knowledge sharing.

Elite reasoning partner for complex logical problems, multi-step reasoning, and strategic decisions. Use PROACTIVELY when facing architectural choices, difficult tradeoffs, or decisions with significant long-term implications. Trigger when user asks "should I", "what are the tradeoffs", "help me decide", "think through", or needs to evaluate multiple options.

Deep research on technical topics using EXA tools with intelligent two-tier caching. Use when user asks to research a topic, investigate best practices, look up information, find patterns, or explore architectures. Also invoked by /research command. Triggers: "research", "look up", "investigate", "deep dive", "find information about", "what are best practices for", "how do others implement".

Orchestrates 6-phase SDLC pipeline (discovery, requirements, architecture, workstreams, implementation, summary) for guided feature development. Use when user runs /core:develop command, requests spec-driven development, wants to create implementation plans with architecture decisions, or mentions "SDLC", "spec-driven", "plan feature", "development pipeline". Supports plan persistence, wave-based resume, autonomous mode, and architecture/implementation verification.

Coordinate structured thinking and multi-agent parallel execution for complex tasks. Use when tackling multi-step projects, planning parallel work, breaking down complex problems, coordinating specialist tasks, facing architectural decisions, or when user mentions "workflow", "orchestration", "multi-step", "coordinate", "parallel execution", "structured thinking", "break this down", "plan this out", "how should I approach", or needs help planning complex implementations.