hyperplan
Orchestrates a five-member adversarial agent team that cross-critiques a planning request, distills only the surviving insights, and hands them to a dedicated planner agent to formalize an executable
What it does
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', 'adversarial plan', 'hostile planning', 'cross-critique plan', '하이퍼플랜', '적대적 계획', '교차 비평'.
Quality judgment
A highly detailed, well-structured adversarial workflow with explicit member prompts, phase gates, anti-patterns, and mandatory handoff contract. However, the document is truncated mid-sentence in the final NOTES section, and it relies heavily on environment-specific tooling (team_*, specific agent names, config paths) that may not generalize; concrete worked examples of the insight bundle output are templates rather than real instances.