hyperplan
Makes your agent plan rigorously, with critiques from other agents. It's useful when a plan needs to be very robust or you ask for critical analysis.
What it does
This mode creates an AI team with opposing personalities to critique and refine a plan. The goal is to expose weaknesses and ensure only the best ideas survive.
When to use it
- ✓When you need a highly rigorous plan.
- ✓When you want ideas to be tested thoroughly.
- ✓When you ask for a 'hyperplan' or cross-critique plan.
Example of what to ask your AI
“Create a plan to launch a new app, but ensure it's heavily critiqued from all sides before being finalized.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
The AI takes on the role of a 'lead' coordinating a team of 5 AIs with conflicting personalities. Each AI attacks the others' ideas, and only the strongest, most defensible concepts are kept.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add code-yeongyu/oh-my-openagent --skill hyperplanOr download just the file:
curl -L https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/dev/packages/omo-senpi/skills/hyperplan/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
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 | team_create |
inline_spec: { name, description, members: [...] } → returns team_run_id |
| Send a round task to a member | task_send |
to: "<member>", team_run_id, 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 subagent_type, load_skills: ["ulw-plan"], run_in_background: false |
| Disband the team | team_delete |
team_run_id, force: true |
Members receive your rounds as injected follow-ups inside their child process; they reply to you with task_send({ 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 task_send 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. After sending round N to all members, keep doing independent lead work or end your turn — each reply lands as an injected notification, and the round is complete once every expected reply has arrived.
HARD PRECONDITIONS
Before starting, verify:
- The lead team tools must be available —
team_create,task_send,team_delete. They register by default with the task component. If they are absent, the task component was disabled; STOP and tell the user:"Hyperplan needs the omo-senpi team tools, which are disabled. Restart without
--no-omo-task(omoon OmO Native,senpion a plain senpi install; the task component is on by default), then retry." - You are the current top-level lead session — the team tools are lead-only and never reach a child. If you are yourself a spawned member/child, this skill is the wrong tool; a member cannot lead a team.
THE 5 ADVERSARIAL MEMBERS — RnR & CHARACTERISTICS
Each member is a kind: "category" team member. The category selects the member's model and prompt shaping; the prompt field below is the system prompt that establishes its adversarial identity.
Required categories are unspecified-low, unspecified-high, ultrabrain, and artistry. Include deep-low only when that category resolves in this project; if team_create rejects deep-low as unresolvable, retry once without only the researcher member and state the degraded roster.
CATEGORY CHARACTERISTICS REFERENCE
| Category | Native Mindset | Why This Adversarial Role Fits |
|---|---|---|
unspecified-low |
Mid-tier, simplicity-leaning, structure-demanding | Pragmatist Skeptic — bias toward simplicity makes it the natural enemy of over-engineering |
unspecified-high |
High-effort, broad-impact, coordination-aware | Integration Tester — broad-scope thinking exposes cross-module fragility |
deep-low |
Autonomous, exploration-heavy, evidence-driven | Autonomous Researcher — natural exploration bias attacks unfounded claims |
ultrabrain |
Hard-logic, simplicity-biased, strategic advisor | Architect Strategist — deep reasoning sees structural flaws others miss |
artistry |
Unconventional, pattern-breaking, lateral | Creative Challenger — pattern-breaking bias attacks orthodox thinking |
MEMBER 1: skeptic (category: unspecified-low)
Role: The Pragmatist Skeptic. Position: Defender of simplicity. Enemy of complexity.
…
FAQ
What does 'adversarial planning' mean?
It means the AIs don't easily agree. They act like opponents, attacking each other's ideas to find flaws and improve the plan.
Why use opposing personalities?
To ensure all possible weaknesses are identified. One AI might be too simplistic, another too complex, covering all angles.
What happens to ideas that don't survive?
They are discarded. Only ideas that withstand all criticism and are deemed sound are used in the final plan.
Details
Original description by the author
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.
Popularity
- GitHub stars
- 70k
- Ranking position
- #1725
- License
- NOASSERTION
- Updated
- 10/16/2026
Comments
- …
More skills from this repository
comment-checker
Helps your agent understand and respond to feedback from automatic comment checkers. It's useful when the agent needs to process information from tools that automatically review code or content.
code-yeongyu/oh-my-openagent
lcx-contribute-bug-fix
Helps your agent contribute bug fixes for LazyCodex-related projects. It creates issues or pull requests to ensure code quality.
code-yeongyu/oh-my-openagent
lcx-doctor
Lets your agent check the health of LazyCodex and Codex CLI installations. It's useful when the system behaves oddly after updates or changes.
code-yeongyu/oh-my-openagent
lcx-report-bug
Helps your agent report bugs in detail for LazyCodex projects. It creates issues with useful information for developers to fix the problem.
code-yeongyu/oh-my-openagent
Similar skills
agent-architecture-audit
Makes your agent check if everything is working correctly. It finds and fixes problems in AI systems, ensuring they perform as expected.
affaan-m/ECC
agent-eval
Helps your agent compare different AI coding tools. It measures which one is faster, cheaper, and more reliable for specific tasks.
affaan-m/ECC
agent-harness-construction
Makes your agent better understand how to perform tasks. It optimizes the tools and instructions the agent uses to increase its chances of success.
affaan-m/ECC