Hyperplan — Adversarial Multi-Agent Planning

Five mutually hostile agents debate your plan across three rounds, and only the surviving insights get formalized into an executable plan by a dedicated planner.

AutomationAdvanced★ 67,531⑂ 5,507AI score 7/10Last updated: Aug 9, 2026

What it does

Turns the orchestrator into the Lead of a 5-member adversarial team: Pragmatist Skeptic, Integration Tester, Autonomous Researcher, Architect Strategist, and Creative Challenger — each with a full hostile system prompt.
Runs three rounds: independent findings → ruthless cross-attack → defend / refine / concede, so weak assumptions and over-engineering die early.
The Lead distills only surviving insights into four buckets: hard constraints, decisions, risks & mitigations, and open questions (which become user-input gates).
Mandatory handoff: the insight bundle goes to a separate planner task loading the ulw-plan skill, which owns sequencing, dependencies, parallelization, and per-task success criteria.
Cleans up with team_delete({ force: true }) so no runtime state leaks.

Who it's for

omo-senpi users who have the native lead team tools enabled
Senior engineers stress-testing a large refactor or architecture change before committing
Leads who prefer adversarial vetting over consensus brainstorming

Example uses

"hyperplan: plan the migration of the billing module to an event-driven design" → returns a plan whose every constraint survived attack on blast radius and complexity.
"adversarial plan for the auth refactor" → the researcher forces file:line citations, killing vibes-based claims; unresolved contentions become explicit approval gates.
"hpp: should we add a caching layer?" → the skeptic attacks 'do we need it TODAY', pruning the unnecessary layer before a single line is written.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

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

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.

↓ Download ZIP

Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the packages/omo-senpi/skills/hyperplan folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/code-yeongyu-hyperplan-2/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/code-yeongyu/oh-my-openagent.git && mkdir -p ~/.claude/skills && cp -r oh-my-openagent/packages/omo-senpi/skills/hyperplan ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

Open a terminal and clone the repo: git clone https://github.com/code-yeongyu/oh-my-openagent.git
Create the skills directory: mkdir -p ~/.claude/skills
Copy the skill: cp -r oh-my-openagent/packages/omo-senpi/skills/hyperplan ~/.claude/skills/
Also install the ulw-plan skill from the same repo — the Phase 6 planner handoff requires it.
Restart omo-senpi without the --no-omo-task flag so team_create, task_send, and team_delete are registered.
From a top-level (non-child) session, type "hyperplan: <what you want planned>"; you should see "HYPERPLAN MODE ENABLED!".
Because five agents × three rounds burns a lot of tokens, try a small scoped request first to verify the flow.

View source on GitHub ↗License: NOASSERTION