analyze
01Command
Investigate a task/bug read-only via the researcher agent, no code changes.
Deep, autonomous AI developer agent for Claude Code (and an experimental OpenCode port) -- architect, researcher, ux-designer, developer, frontend-developer, tester, reviewer, with project-boundary safety and resumable execution state.
Command
Investigate a task/bug read-only via the researcher agent, no code changes.
Command
Deep, autonomous end-to-end development workflow -- target verification, project discovery, Obsidian history, architecture/UX (when needed), research, implementation, testing, visual QA (when available), security/performance/final review, Definition of Done, persistent resumable state, Obsidian write-back.
Command
Run the reviewer agent against current working tree changes.
Command
Run the tester agent against current working tree changes.