Specialist subagents with restricted tool allowlists: research, exploration, debugging, review, planning, documentation, and synthesis agents, plus the skills that dispatch them. Every subagent in Awakened lives here (B-6).
7 skills · 27 agents
Core engineering workflow: planning, implementation discipline, test-driven development, systematic debugging, verification before completion, and git workflow guidance. The stable baseline - it depends on no agents, memory infrastructure, or project-specific tooling (B-1).
18 skills · 9 commands
Project-scoped structural context: codebase onboarding, code maps, documentation upkeep, conventions, domain modeling, and CLAUDE.md scaffolding. Structural context only; it stores no history (B-4).
7 skills · 2 commands
Marketplace meta tooling: skill creation, writing for agents, context budgeting, skill scouting, component auditing, and linting. Marketplace maintenance, not user workflow execution (B-7).
6 skills · 2 commands
Code review and analysis: review discipline, production audit, architecture inspection, AI-debt detection, and security-oriented review. Analysis and review only - implementation stays outside this plugin (B-2).
7 skills · 1 command
Session management and momentum: save and resume sessions, handoffs, checkpoints, and focused asides. Session momentum only - it duplicates no planning, debugging, or review system (B-5).
1 skill · 4 commands