Hunts ambiguity in a story or task description before planning starts. Surfaces open questions, undefined terms, missing acceptance criteria, conflicting requirements, and assumed-but-unstated constraints.
Synthesizes findings from parallel reviewer agents into one consolidated report — dedupes, filters false positives, applies cross-iteration state, classifies the diff into a risk tier, and decides which sub-agents to spawn.
Identifies rollback paths, blast radius, breaking-change risk, data-migration danger, and operational risk for a planned change. Output feeds into the plan so risky steps get extra scrutiny.
Build phase 1 specialist — creates the file structure, types/interfaces, function signatures, and empty stubs for a planned change. Does not implement logic; produces the skeleton the next phases fill in. Constrained by all relevant .claude/rules/.
Breaks a story or task into atomic, independently-testable steps with explicit sequencing and dependencies. Identifies what can run in parallel and what must happen in order.
Reviews changed code for SOLID principle violations — Open/Closed, Liskov Substitution, Interface Segregation, Dependency Inversion. Cites the solid rule. SRP (the S of SOLID) is owned by purity-reviewer.
Decides what tests at what level (unit / integration / e2e / contract / property) for a planned change. Output feeds into the plan so the build phase generates the right tests.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: