grill-with-docs

grill-with-docs

grillwriteshands-on

Use this when: you want a plan tested against your domain docs + the docs updated

Problem it solves — Plans drift from the project's own language. This grills your plan against the domain model and glossary, drafting the CONTEXT.md / ADR updates live as decisions crystallise — applied only on your confirm.

Grill with docs

<what-to-do>

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.

</what-to-do>

<supporting-info>

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. (Tempo is single-context: a root CONTEXT.md + docs/adr/.)

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?"

Track terms → propose the CONTEXT.md edit (never write it unprompted)

As each term resolves, track it with its precise definition (in the format in CONTEXT-FORMAT.md) so nothing's lost. But CONTEXT.md is a canonical doc — like every canonical write in this harness it's surface-then-confirm: propose the addition/change and apply it only once the user confirms; don't silently edit it mid-interview. Surface the resolved terms as you go (so they're visible), but the write itself is gated — or hand the actual edit to qa-philosophy, which owns canonical-doc reconciliation.

Don't couple CONTEXT.md to implementation details. Only include terms that are meaningful to domain experts.

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. (Tempo ADRs are append-only — supersede, don't rewrite.)

</supporting-info>

Where it sits

• Not qa-philosophy — that's a batch audit of doc drift run after the fact; grill-with-docs proposes the edits live during the interview (both are surface-then-confirm — neither writes a canonical doc unprompted). Hand the actual write to qa-philosophy if you'd rather it own the reconcile.
• Not grill-me — same interview engine, but this one is domain/terminology-led and proposes canonical-doc edits as it goes (gated). Reach for plain grill-me when the plan isn't about domain language.