felipemelendez/llm-orchestrator
8 subagents
Subagent
orch-brainstormerDesign-stage explorer. Use when the user asks "what should we build" or "how should we approach this" — before any code or plan. Asks targeted questions and writes a spec file.orch-code-reviewerStage 2 reviewer — answers "is the code correct, safe, idiomatic, minimal?" Use after stage 1 passes. Returns an Issues block.orch-debuggerRoot-cause investigator. Use when a test is failing or a bug is reported and the orchestrator needs the cause identified before any fix. Returns a Found block with the diagnosis; does not patch.orch-explorerRead-only codebase scout. Use proactively when the orchestrator needs to know where something lives, how it's used, or what touches it — before any edit. Returns file:line refs, never edits.orch-implementerImplements one task from a plan. Use proactively when the orchestrator dispatches a coding task with a pasted scope + verify command. Returns a single Status block.orch-researcherDispatched when the research-classifier returns RESEARCH_NEEDED. Verifies the planned approach (or answers a research query) against current sources — vendor MCPs, doc aggregators (Context7, DeepWiki)orch-security-reviewerStage-3 conditional reviewer — use only when the diff touches auth/crypto/payments/secrets. Returns an Issues block focused on security.orch-spec-reviewerStage 1 reviewer — answers "does this diff implement the spec?" Use after the implementer returns DONE. Reads spec + plan + diff, does not run code. Returns an Issues block.