Augustus — Design skill for Claude Code

Design community

Agent skill: design judgment-assisted systems with TypeSafe Jev (System One).

How to install Augustus

This entry records only its repository, not the path inside it, so there is no exact command to give. Open 24601/Augustus and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Augustus does

Agent skill: design judgment-assisted systems with TypeSafe Jev (System One). Maps Choice/Score/Noul onto decision theory, reranking, and routing. Composition algebra, question design, validation gates. MIT.

Alternatives in Design

Mckinsey Deck — Build a McKinsey-style PPTX deck from a brief 566 ★
Design Handoff — Generate a developer handoff document from a Figma file — spacing specs, token maps, component APIs, and produ 309 ★
Design Council — Convene parallel role-specialized peer agents to debate a cross-domain decision 178 ★

README

Augustus

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) [![Version](https://img.shields.io/github/v/release/24601/Augustus)](https://github.com/24601/Augustus/releases) [![Claude Code](https://img.shields.io/badge/Claude_Code-marketplace-purple.svg)](.claude-plugin/marketplace.json) [![Skills.sh](https://img.shields.io/badge/skills.sh-compatible-green.svg)](https://www.skills.sh/)

**Augustus** — named for Augustus De Morgan (1806–1871), mentor and professor of William Stanley Jevons — is an agent skill for designing judgment-assisted systems with [TypeSafe](https://docs.typesafe.ai/) Jev System One models. Code stays in control; Jev supplies narrow, typed semantic judgments (Choice, Score, Noul) that software can act on directly.

Companion, not replacement, to the official [`typesafe-ai` skill](https://github.com/typesafe-ai/skills). That skill owns integration contracts; Augustus owns the **design judgment**: which classical methods map onto Jev primitives, what breaks in translation, and what experiment would prove a design wrong.

The skill

.agents/skills/augustus/SKILL.md — working protocol + decision-design card
.agents/skills/augustus/references/mappings.md — 5 classical-method mappings with boundaries, counterexamples, acceptance tests
.agents/skills/augustus/references/validation.md — design gate, eval recipes, Jev-for-skills (routing, self-monitoring, testing, modularity, frontmatter)
.agents/skills/augustus/references/boundary-audit.md — existing-system insertion: fit test, opportunity map, smallest boundary, red flags
.agents/skills/augustus/scripts/evaluate_decisions.py — offline evaluator for selective binary decisions (Brier, reliability, threshold/cost sweep)

Plus `research/` — the living evidence archive behind the skill, refreshed hourly (see `research/README.md`).