Token-efficient parallel execution mode using Haiku and Sonnet agents

Use when executing phases from PLAN.md, running implementation work units, or resuming work from a previous session. Enforces architecture principles, layer-specific testing, and DOE integration.

Parallel Agent Orchestration

Parallel Agent Orchestration

Orchestrate complex development with AUTOMATIC parallel subagent execution, continuous dispatch scheduling, dependency analysis, file conflict detection, and IOSM quality gates. Analyzes task...

Transform raw data from CSVs, Google Sheets, or databases into executive-ready reports with visualizations, key metrics, trend analysis, and actionable recommendations. Creates data-driven...

Spawn and coordinate multiple parallel agents for maximum throughput. Optimized for 64-core systems. Includes safety rules, coordination patterns, and swarm templates.

Use when partner provides a complete implementation plan to execute in

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Dispatches one subagent per independent domain to parallelize investigation/fixes. Use when you have 2+ unrelated failures (e.g., separate failing test files, subsystems, bugs) with no shared...