Agent
Autonomous flow metrics analyst that investigates process health, forecasts delivery, and interprets data using Vacanti's framework. Use when asked "why are things slow?", "are we on track?", "what should we focus on?", or any question about flow, predictability, or delivery timing.
Agent
Use this agent when the user reports errors, bugs, problems, failures, or needs to debug/fix something. This agent autonomously performs root cause analysis using the five whys methodology before allowing solution attempts. Examples.
Agent
General code review for project guidelines, style, and bug detection.
Agent
Find unnecessary complexity, redundant code, and opportunities for simplification.
Agent
Analyze code comments and documentation for accuracy and completeness.
Agent
Reviews findings through a panel of 14 domain experts, auto-selected by content. Debates conflicts and reaches consensus. Used by code review fix loops and plan review commands.
Agent
Applies consensus-approved code fixes from the expert panel. Edits files sequentially and resolves any lint issues introduced by each fix.
Agent
Hunt for silent failures, inadequate error handling, and missing logging.
Agent
Analyze test coverage quality, gaps, and resilience.
Agent
Analyze type design quality including encapsulation, invariants, and usefulness.
Agent
Use this agent when autonomous testing of REST or GraphQL APIs is needed to validate endpoints, error handling, authentication, and response schemas. Examples.
Agent
Use this agent when autonomous browser-based testing of web applications is needed to find functional bugs, visual issues, accessibility problems, or performance bottlenecks. Examples.
Agent
Use this agent when autonomous testing of command-line tools and scripts is needed to validate functionality, error handling, and output correctness. Examples.
Agent
Autonomous exploratory testing agent that validates implementation against plan scenarios.