eval

Pure development workflow with test-first development and coverage review. Used by coordinator as a subagent. Never manages beads issues or commits.

Autonomous codebase cruft discovery. Scans for duplication, dead code, leaky abstractions, pattern divergence, and complexity. Files findings as beads issues. Invoked via /refactor-finder.

Single entry point for all implementation work. Triages tasks, manages beads issues, delegates to implementer skill, runs reviewers, creates PRs.

Resolves rebase conflicts by gathering full context from beads issues, git diffs, and surrounding code. Invoked by coordinator and merge-queue after a fast-path rebase fails.

Process open PRs — merge when CI passes, handle rebases, file issues for failures. Run in a dedicated window.

Collaboratively plan epics by exploring the codebase, discussing tradeoffs, filing issues, and running plan review. Invoked via /plan.

Review PR for duplication, pattern divergence, and architectural issues by comparing against the full codebase. Spawned by coordinator before PR creation.

Review PR diff for bugs, error handling gaps, security issues, and API contract mismatches. Spawned by coordinator before PR creation.

Review PR test quality — meaningful coverage, edge cases, integration tests, and test accuracy. Spawned by coordinator before PR creation.

Lightweight sub-agent that runs quality gates and returns a concise pass/fail result. Used by implementer to preserve context.

Guide for writing, running, and debugging Playwright E2E tests in eval.

Review filed implementation plans for architectural issues, duplication risks, and completeness. Spawned by planner as a subagent.

Investigate production issues using logs, database, and Identity Platform. Read-only by default.