Improve Codebase Architecture

2. Present candidates as an HTML report

Write a self-contained HTML file to the OS temp directory so nothing lands in the repo. Resolve the temp dir from $TMPDIR, falling back to /tmp (or %TEMP% on Windows), and write to <tmpdir>/architecture-review-<timestamp>.html so each run gets a fresh file. Open it — open on macOS, xdg-open on Linux, start on Windows — and tell the user the absolute path.

The report uses Tailwind via CDN for layout and Mermaid via CDN for graph-shaped diagrams. Each candidate gets a before/after visualisation. Be visual — the diagrams carry the weight, the prose is sparse.

For each candidate, render a card with:

• Files — which files/modules are involved
• Problem — why the current architecture is causing friction
• Solution — plain English description of what would change
• Benefits — in terms of locality and leverage, and how tests would improve
• Before / After diagram — side by side, illustrating the shallowness and the deepening
• Recommendation strength — Strong, Worth exploring, or Speculative, rendered as a badge

End with a Top recommendation section: which candidate you'd tackle first, and why.

See HTML-REPORT.md for the scaffold, diagram patterns, and styling guidance.

No network? Fall back to markdown. The Tailwind and Mermaid CDNs are the only external dependency; if the environment is offline or the user asks for it, present the same candidate cards as a numbered markdown list in the conversation — same fields, same badges, same Top recommendation. The report format is a presentation choice, not the substance.

Use CONTEXT.md vocabulary for the domain and codebase-design vocabulary for the architecture. If CONTEXT.md defines "Order," talk about "the Order intake module" — not "the FooBarHandler," and not "the Order service."

ADR conflicts: if a candidate contradicts an existing ADR, only surface it when the friction is real enough to warrant revisiting the ADR. Mark it clearly in the card (e.g. an amber callout: "contradicts ADR-0007 — but worth reopening because…"). Don't list every theoretical refactor an ADR forbids.

Do NOT propose interfaces yet. After the file is written, ask: "Which of these would you like to explore?"

3. Grilling loop

Once the user picks a candidate, invoke the grill-with-docs skill to walk the decision tree with them — constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.

Side effects happen inline as decisions crystallize — the grill maintains the domain model as it goes:

• Naming a deepened module after a concept not in CONTEXT.md? Add the term to CONTEXT.md — same discipline as /domain-model (see CONTEXT-FORMAT.md). Create the file lazily if it doesn't exist.
• Sharpening a fuzzy term during the conversation? Update CONTEXT.md right there.
• User rejects the candidate with a load-bearing reason? Offer an ADR, framed as: "Want me to record this as an ADR so future architecture reviews don't re-suggest it?" Only offer when the reason would actually be needed by a future explorer to avoid re-suggesting the same thing — skip ephemeral reasons ("not worth it right now") and self-evident ones. See ADR-FORMAT.md.
• Want to explore alternative interfaces for the deepened module? Run the codebase-design skill and use its DESIGN-IT-TWICE.md parallel sub-agent pattern.
• Deepening a cluster with awkward dependencies? DEEPENING.md has the four dependency categories and the seam discipline for each.

This skill proposes and designs; it does not implement. Once the shape is agreed, the work becomes a task — /create-task grills it into missions and tdd builds it. Don't start editing source here.