Hyperplan — Testing skill for Claude Code
Thinking - Adversarial review - 5 hostile critics stress-test a plan/decision/draft in parallel, then keep only what survives.
How to install Hyperplan
Installs to ~/.claude/commands/brianarfi-ai-second-brain-hyperplan.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/BrianArfi/ai-second-brain/HEAD/.claude/commands/hyperplan.md -o ~/.claude/commands/brianarfi-ai-second-brain-hyperplan.md Restart Claude Code, or start a new session, for it to be picked up.
What Hyperplan does
description: Thinking - Adversarial review - 5 hostile critics stress-test a plan/decision/draft in parallel, then keep only what survives argument-hint: ""
Read `.agent/skills/hyperplan/SKILL.md` and follow it exactly. It is the single source of truth for the adversarial-review procedure: frame the target, spawn 5 `hyperplan-critic` subagents in parallel (one lens each: skeptic, stakeholder, evidence, strategist, contrarian; strategist + contrar
Alternatives in Testing
- Darwin Skill — 达尔文.skill —— 一个让你的Skill无限进化的系统:评估→改进→测试→保留或回滚 Autoresearch-inspired autonomous skill optimization for Claude C 5.7k ★
- Adversarial Spec — A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until a 514 ★
- Spec Draft PR — Turn a feature idea or GitHub issue into a one-page spec saved to Documentation/specs/ and opened as a draft P 324 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Plan Refine
Autonomously stress-test and harden a plan through 6 adversarial perspectives
Grilling
Grill the user relentlessly to stress-test a plan, decision, or idea
Anti Sloppifier
Audits a PM work session for AI slop, decision abdication, and thinking replacement. Run after strategy, specs
Decision Memo
Produce a senior-leadership decision memo before proposing a non-trivial change. Seven sections — observation,
Plan Phase
Architecture-first planning for a specific spec phase. Define files, symbols, and code-level interfaces first,
Speckit Orchestrate
Optionally run TCHES metaprompt, then chain Spec Kit passes (specify→plan→tasks→implement). Usage: /speckit-or
Related Agents
Hyperplan Critic
Read-only adversarial critic for /hyperplan. Given a target (plan, decision, or draft) and ONE lens, reads the
Red Team Agent
Adversarial review agent. Use when a draft, design, or plan needs to be attacked the way a hostile stakeholder
Adversarial Reviewer
Red-team agent that attacks every assumption, breaks every feature, and finds every way to abuse the system. R