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 model lives

The glossary is a repo file; the decisions are Kairos ADRs.

Most repos have a single context — one CONTEXT.md at the root:

/
├── CONTEXT.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
└── src/
    ├── ordering/
    │   └── CONTEXT.md
    └── billing/
        └── CONTEXT.md

Create files lazily — only when you have something to write. If no CONTEXT.md exists, create one when the first term is resolved. Decisions never get repo files: record them as Kairos ADRs per ADR-FORMAT.md.

During the session

Challenge against the glossary

When the user uses a term that conflicts with the existing language in CONTEXT.md, call it out immediately. "Your glossary defines 'cancellation' as X, but you seem to mean Y — which is it?"

Sharpen fuzzy language

When the user uses vague or overloaded terms, propose a precise canonical term. "You're saying 'account' — do you mean the Customer or the User? Those are different things."

Discuss concrete scenarios

When domain relationships are being discussed, stress-test them with specific scenarios. Invent scenarios that probe edge cases and force the user to be precise about the boundaries between concepts.

Cross-reference with code

When the user states how something works, check whether the code agrees. If you find a contradiction, surface it: "Your code cancels entire Orders, but you just said partial cancellation is possible — which is right?"

Update CONTEXT.md inline

When a term is resolved, update CONTEXT.md right there. Don't batch these up — capture them as they happen. Use the format in CONTEXT-FORMAT.md.

CONTEXT.md should be totally devoid of implementation details. Do not treat CONTEXT.md as a spec, a scratch pad, or a repository for implementation decisions. It is a glossary and nothing else.

Offer ADRs sparingly

Only offer to create an ADR when all three are true:

1. Hard to reverse — the cost of changing your mind later is meaningful
2. Surprising without context — a future reader will wonder "why did they do it this way?"
3. The result of a real trade-off — there were genuine alternatives and you picked one for specific reasons

If any of the three is missing, skip the ADR. Create it per ADR-FORMAT.md.

Record this decision

One short path when the user says "record this decision", or when implement finds one at the end of a task (COLLIERY-I-0628). A decision about the system under work goes to Kairos, not to local memory.

1. Find the ADR board of the team: adr_board in the SessionStart context, else my_boards.
2. Draft from the conversation: the title (the decision in one clause), the context (what was true, what forced the choice), the decision, the consequences (what changes for the code and the people). Show the draft to the user. Keep the words the conversation used.
3. create_item with item_type: adr, board: <adr board>, parent: <the task or the initiative that produced it>, the draft as content (ADR-FORMAT.md).
4. link_items with impacts from the ADR to each repository that it is about.
5. A decision that changes an existing ADR: link_items with supersedes from the new ADR to the old one. The old one stays as it is.
6. Show the short code of the ADR, and write it on the task or the initiative.
7. A spec or a plan that the decision needs is a document, not an ADR. promote_note with kind: document makes a draft. When the user agrees with the text, set_lifecycle with lifecycle: published publishes it. A document is not on a board, so transition_item does not move it.