← ClaudeAtlas

worldthreatmodellisted

Persistent world-model harness that stress-tests ideas, strategies, and investments against 11 time horizons from 6 months to 50 years, each a deep analysis of geopolitics, tech, economics, society, and security, in Fast/Standard/Deep tiers. USE WHEN threat model, world model, test idea, future analysis, time horizon, stress test against future, long-term risk. NOT FOR single-shot idea attack (use RedTeam).
DorShaer/Husk · ★ 12 · AI & Automation · score 67
Install: claude install-skill DorShaer/Husk
# World Threat Model Harness ## What It Does Stress-tests an idea, strategy, or investment against 11 time horizons from 6 months to 50 years. Each horizon is a deep (~10 page) world model covering geopolitics, technology, economics, society, environment, security, and wildcards. Three speed tiers: Fast (~2 min, single synthesizer), Standard (~10 min, 11 parallel agents plus RedTeam and FirstPrinciples), Deep (~1 hr, adds Research and Council). Three workflows: TestIdea returns a probability-weighted scenario matrix across all 11 horizons; UpdateModels and ViewModels handle the rest. (A dedicated TestScenario workflow for named alternative-future scenarios is planned, not yet built — scenario files under `Scenarios/` are consumed by TestIdea today.) ## The Problem Most plans get tested against the present, or against the next year or two at most — so they break the moment the world shifts on a timeline you never modeled. A strategy that looks great at the 1-year horizon can be fatal at 10 years, and a 50-year bet can ignore the near-term cascade that kills it first. Holding all those horizons in your head at once, with real geopolitical, economic, and technological reasoning behind each, is more than any single pass can do. This harness keeps 11 persistent world models warm and runs your idea against all of them at the same time, with adversarial analysis on top. ## How It Works A system of 11 persistent world models spanning 6 months to 50 years. Each model is a deep (