Use this agent when you need to create foundational templates, boilerplate code, or starter configurations for new projects, components, or features. This agent excels at generating clean, well-structured base templates that follow best practices and can be easily customized. Examples: Context: User needs to start a…
Enforces engineering standards and code quality policies. Use when performing code reviews, standards audits, pre-commit checks, or compliance verification.
Multi-perspective plan review specialist that coordinates VP Product, VP Engineering, and VP Design perspectives to identify blockers, anti-patterns, conflicts, and regressions. Use when reviewing implementation plans, design docs, or wave plans.
Generate comprehensive performance reports for swarm operations. There is no analysis verb and no performance report subcommand in v3 — the CLI surface is performance metrics; the MCP surface is mcprufloperformancereport.
Analyze token usage patterns and optimize for efficiency. There is no analysis verb and no token-usage command in v3 — token savings come from hooks token-optimize, and per-model routing stats come from hooks model-stats.
Automatically route a task to the optimal agent using Q-Learning. There is no auto agent family in v3 — the closest live surface is route, backed by swarm coordinate / autopilot for full multi-agent orchestration.
There is no automation verb and no smart-spawn subcommand in v3 — no single command replicates "analyze workload, then auto-spawn agents." The closest live building blocks are hooks route (route a task to the agent learned patterns favor) and hooks build-agents (generate agent configs from pretrain data), combined…