Hyperplan — Adversarial Multi-Agent Planning

What it does

Hyperplan replaces consensus planning with intellectual combat. The orchestrator becomes the Lead of a five-member adversarial team:

• skeptic — attacks over-engineering, scope creep, premature abstraction ("delete this, prove it's needed")
• validator — hunts edge cases, cross-module fragility, blast radius, regressions
• researcher — demands file:line or doc-URL evidence; vibes-based claims are invalidated
• architect — exposes leaky abstractions, hidden coupling, accumulating tech debt
• creative — forces at least three alternative framings before any solution is accepted

Seven phases: acknowledge the request → spawn the team → Round 1 independent findings → Round 2 ruthless cross-attack → Round 3 defend/refine/concede → Lead distills survivors into four buckets (hard constraints, decisions, risks & mitigations, open questions) → mandatory handoff to the plan agent, then team cleanup.

The contract is strict: the Lead never writes the plan. The insight bundle is input; the planner owns sequencing, dependencies, parallelization, and per-task success criteria.

Who it's for

• Engineers facing an irreversible refactor or migration who want weak assumptions surfaced before writing code
• Tech leads who tend to anchor on their first idea when planning solo
• opencode / oh-my-opencode users with team mode enabled who want a real multi-agent debate pipeline

⚠️ Preconditions: team_* tools must be available (team_mode.enabled: true), you must run in the main session, and as a lead-eligible agent — not a planner agent.

Examples

1. "hyperplan: plan the migration of the payments module to an event-driven design" — the skeptic questions whether the event bus earns its keep, the validator enumerates which existing payment tests break, the architect flags coupling; only defended constraints reach the plan.
2. "hpp: design the new onboarding flow" — the creative challenger proposes sidestepping onboarding entirely, while the researcher demands real usage data, filtering out unfounded UX assumptions.
3. "adversarial plan for splitting the monolith" — points where the debate never converged become Open Questions and are promoted to user-input gates in the final plan.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/HEAD/.opencode/skills/hyperplan/SKILL.md

What I want: (describe your task here)

Install the skill I found on Claude Skill Mart.
Copy the .opencode/skills/hyperplan folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/code-yeongyu-hyperplan/.
When it's done, tell me in one line what this skill can do.