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.)

The contracts come first

If this repo was scaffolded by setup-agentic-repository, it already carries the authoritative contracts for both artefacts this skill writes:

• agents-docs/AGENTS_CONTEXT.md — the CONTEXT.md / CONTEXT-MAP.md contract.
• agents-docs/AGENTS_ADRS.md — the ADR contract.
• agents-docs/AGENT_WORKFLOW.md §§ 4–5 — the canonical upkeep triggers.

Read those before writing anything, and follow them over this file where they differ. They are the project's source of truth; this skill only tells you how to drive the conversation that fills them in. Never edit those contract files themselves — they're agent instruction infrastructure.

Discover the docs dir; don't hardcode it. It defaults to agents-docs/, but setup-agentic-repository accepts a --docs-dir override:

1. Read AGENTS.md at the repo root — every Mimas-generated one lists its docs paths in the first block. The directory in those paths is the docs dir.
2. If that fails, search for the contract directly: find . -maxdepth 3 -name AGENTS_CONTEXT.md. The directory containing it is the docs dir.