grill-with-docs

name	grill-with-docs
description	Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.

Ask the questions one at a time, waiting for feedback on each question before continuing.

If a question can be answered by exploring the codebase, explore the codebase instead.

Before ending the session, produce a complete decision record for every resolved architectural boundary. Do not compress a multi-part decision into a one-paragraph ADR merely because the final answer is short.

Domain awareness

During codebase exploration, also look for existing documentation:

File structure

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

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. Use the format in ADR-FORMAT.md.

Record the decision completely

When the session resolves an ADR-worthy decision, write or update the ADR before moving on. For each resolved question, capture the answer in the record. Include the following whenever they apply:

1. Context and tension — the existing behavior or documented decision, its failure mode, and why the boundary matters.
2. The chosen contract — concrete interfaces, state transitions, timings, thresholds, ownership, and configuration values. Do not replace agreed values with placeholders such as “within a bound” or “on a slow timer.”
3. Boundary and failure semantics — what stays available, what becomes unavailable, and how transient versus sustained failures differ.
4. Operational and data rules — exposure, access control, privacy, cardinality, retention, or observability constraints when they affect the design.
5. Rejected alternatives and consequences — the meaningful trade-offs that make the decision surprising, plus the behavior consumers and operators can rely on.

Use concise prose, but preserve the complete reasoning needed for an implementer to reconstruct the contract without reopening the grilling session. After writing, read the record back against the resolved questions and correct omissions. Then search the documentation and configuration consumers for statements that would become stale; either update them when the decision is already implemented or mark the ADR as a future contract when the code still reflects the old behavior.