Use ONLY when explicitly requested by user or when invoked by a protocol in sessions/protocols/. DO NOT use proactively. Reviews code for security vulnerabilities, bugs, performance issues, and adherence to project patterns during context compaction or pre-commit reviews. When using this agent, you must provide files…
Use when creating a new task OR when starting/switching to a task that lacks a context manifest. ALWAYS provide the task file path so the agent can read it and update it directly with the context manifest. Skip if task file already contains "Context Manifest" section.
Updates task context manifest with discoveries from current work session. Reads transcript to understand what was learned. Only updates if drift or new discoveries found.
Explores codebase and writes structured analysis documents. Spawned by map-codebase with a focus area (tech, arch, quality, concerns). Writes documents directly to reduce orchestrator context load.
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.
Verifies phase goal achievement through goal-backward analysis. Checks codebase delivers what phase promised, not just that tasks completed. Creates VERIFICATION.md report.
Use ONLY during context compaction or task completion protocols or if you and the user have identified that existing documentation has drifted from the code significantly. This agent updates CLAUDE.md files and module documentation to reflect current implementation, adapting to super-repo, mono-repo, or single-repo…