Agent skill · product strategy · code-yeongyu
hyperplan
Adversarial multi-agent planning: a hostile team cross-critiques a plan before it is formalized. Use when planning needs maximum rigor or the user asks for a hyperplan / adversarial or cross-critique plan.
Why this skill is useful
Adds a complex orchestration script for managing a multi-agent adversarial planning process that isn't covered in standard AI training.
What it needs
About 12k tokens when loaded. Last updated 2026-08-07. 67,387 stars on the source repository.
What this skill does
HYPERPLAN — Adversarial Multi-Agent Planning MANDATORY: First action when this skill loads — say "HYPERPLAN MODE ENABLED!" so the user knows orchestration started. WHAT THIS IS You (the orchestrator) become the Lead of a 5-member adversarial team. The 5 members are maximally hostile to each other — they attack each other's findings ruthlessly. You then synthesize only the defensible insights that survived the attacks, and hand them to a dedicated planner for formalization. This is not consensus building. This is intellectual combat. Weakness gets exposed. Lazy thinking gets eviscerated. Only what survives the gauntlet makes it into the plan. HOW THIS MAPS TO omo-senpi This skill runs on the native lead team tools. Members are background children routed through a category; you coordinate them entirely with these tools: Purpose Tool Key arguments --------- ------ --------------- Spawn the team once teamcreate inlinespec: { name, description, members: [...] } → returns teamrunid Send a round task to a member tasksend to: "<member>", teamrunid, message, optional summary Collect member replies injected notifications replies auto-inject as they arrive — keep working or end your turn Hand off to the planner task category XOR subagenttype, loadskills: ["ulw-plan"], runinbackground: false Disband the team teamdelete teamrunid, force: true Members receive your rounds as injected follow-ups inside their child process; they reply to you with tasksend({ to: "lead", message: "..." }). You are the information broker — members never see each other's replies except through the bundles you forward. Delivery is injection-driven. A tasksend writes a durable message and returns immediately; it never interrupts the recipient. Member replies arrive as injected notifications at your next tool-call boundary or idle edge. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills code-yeongyu/hyperplan--b79d47