Austin, drawn from real OpenStreetMap data, on a hex lattice where every cell is a self-describing GYST UUIDv8.
Live: austinsays.com/city · austinsays.com/about
A Claude Code Agent Skill built from Dex Horthy's (HumanLayer) playbook on David Ondrej's podcast.
"Once the model has written thousands of lines of code, it is harder to change. The sessions that generate design docs are context-light — you get the most model intelligence when you do the hard thinking early."
By default, agents build horizontally: all the backend, then all the frontend, then a 2,000-line diff lands in your lap and reviewing it is your problem. This skill flips that. Every decision that matters gets made before the code exists — where changing your mind costs a sentence, not a rewrite.
Owner: SoMaCoSF
Status: In build
Base repo: https://github.com/SoMaCoSF/poincake
Goal: Turn Poincake into a hyperbolic knowledge browser where every entity is a self-describing GYST UUIDv8, and navigation follows icosahedral/dither3d glyph logic.
| # SoMaCoSF Platform — Session Build Log | |
| **somacosf.com | 2026-05-06 → 2026-05-07** | |
| --- | |
| ## What Was Built | |
| ### 1. Polymarket CLOB + Kalshi Execution Bridge (`62c1535`) | |
| - `app/api/poly/execute` — CLOB order submission via Polymarket API | |
| - `app/api/kalshi/execute` — Kalshi market order bridge |
SoMaCo Part 2 — 11 Polymarket market drafts w/ full resolution criteria, Cu/Al trade thesis, IBEW labor signal, board interlocks, platform API
Part 2 of 2 | First gist: https://gist.github.com/SoMaCoSF/6af0a31f9197d2b148f20b1a2baff1c0 Published: 2026-04-28 | Platform: somacosf.com
SoMaCo AI Datacenter Supply Chain Intelligence — C-Suite network, 95B capex flows, GYST UUID registry, Polymarket gap analysis, Mermaid diagrams
Published: 2026-04-28 | Platform: somacosf.com | Stack: Next.js 15 + Turso + Python harvesters
Six hyperscaler CEOs have publicly committed $295 billion to AI datacenter infrastructure in FY2025. That capital flows through a documented supply chain — copper miners, aluminum producers, cable tray manufacturers, liquid cooling companies.
A practical guide for researchers, traders, and builders Methodology extracted from production intelligence systems — applies to any domain with public data and market gaps
A corpus is a structured, machine-readable knowledge base built around a single thesis. It combines:
| #!/usr/bin/env python3 | |
| """ | |
| SoMaCo Corpus Builder — build_corpus.py | |
| Slurps all SoMaCoSF gists + repos via gh CLI into Ghost Catalog–formatted CSV. | |
| Ghost Catalog fields (SOM-DOC convention): | |
| file_id, type, entity_id, description, category, visibility, | |
| language, created_at, updated_at, url, files_or_stars, | |
| is_fork, stack, status, tags |
THESIS: The AI datacenter build-out is the largest coordinated commodity procurement event since the interstate highway system. Aluminum, copper, and galvanized steel embedded in physical infrastructure are not priced into LME/SHFE/CME futures. Polymarket has zero coverage of this supply chain. First-mover market creation position available across 11 distinct commodity-prediction-market pairs.