second-brain-os: Skill for Codex

Domain Modeling

Actively build and sharpen the project's domain model as you design. This is the active discipline — challenging terms, inventing edge-case scenarios, and writing the glossary and decisions down the moment they crystallise. (Merely reading CONTEXT.md for vocabulary is not this skill — that's a one-line habit any skill can do. This skill is for when you're changing the model, not just consuming it.)

Where the files live

Resolve the project first from docs/agents/project-context.md.

• Code (an app repo): the repo layout below: CONTEXT.md and docs/adr/ at the app repo's root.
• Knowledge work (a project folder in <workspace.root>/<workspace.projects>/):
  • glossary.md at the project root (or <effort>/glossary.md in a multi-effort project), using the same format as CONTEXT.md, with frontmatter type: reference.
  • A decision that passes the three-part test below is offered as a decision record. On yes it's written to decisions/001-slug.md, with three-digit numbering and the ADR format. This is the same offer as an ADR in code; only the path differs.
  • Routine decisions stay in the project's memory.md decision log.

File structure (code repos)

Most repos have a single context:

/
├── CONTEXT.md
├── docs/
│   └── adr/
│       ├── 0001-event-sourced-orders.md
│       └── 0002-postgres-for-write-model.md
└── src/

If a CONTEXT-MAP.md exists at the root, the repo has multiple contexts. The map points to where each one lives:

/
├── CONTEXT-MAP.md
├── docs/
│   └── adr/                          ← system-wide decisions
├── src/
│   ├── ordering/
│   │   ├── CONTEXT.md
│   │   └── docs/adr/                 ← context-specific decisions
│   └── billing/
│       ├── CONTEXT.md
│       └── docs/adr/

Create files lazily — only when you have something to write. If no CONTEXT.md exists, create one when the first term is resolved. If no docs/adr/ exists, create it when the first ADR is needed.

During the session