improve-codebase-architecture

name	improve-codebase-architecture
description	Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Improve Codebase Architecture

Surface architectural friction and propose deepening opportunities — refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.

Glossary

Use these terms exactly in every suggestion. Consistent language is the point — don't drift into "component," "service," "API," or "boundary." Full definitions in LANGUAGE.md.

• Module — anything with an interface and an implementation (function, class, package, slice).
• Interface — everything a caller must know to use the module: types, invariants, error modes, ordering, config. Not just the type signature.
• Implementation — the code inside.
• Depth — leverage at the interface: a lot of behaviour behind a small interface. Deep = high leverage. Shallow = interface nearly as complex as the implementation.
• Seam — where an interface lives; a place behaviour can be altered without editing in place. (Use this, not "boundary.")
• Adapter — a concrete thing satisfying an interface at a seam.
• Leverage — what callers get from depth.
• Locality — what maintainers get from depth: change, bugs, knowledge concentrated in one place.

Key principles (see LANGUAGE.md for the full list):

• Deletion test: imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it was earning its keep.
• The interface is the test surface.
• One adapter = hypothetical seam. Two adapters = real seam.

This skill is informed by the project's domain model. The domain language gives names to good seams; ADRs record decisions the skill should not re-litigate.

Process

1. Explore

Read the project's domain glossary and any ADRs in the area you're touching first.

If the host supports subagents, use an exploration subagent to walk the codebase. Otherwise inspect files directly. Don't follow rigid heuristics — explore organically and note where you experience friction:

• Where does understanding one concept require bouncing between many small modules?
• Where are modules shallow — interface nearly as complex as the implementation?
• Where have pure functions been extracted just for testability, but the real bugs hide in how they're called (no locality)?
• Where do tightly-coupled modules leak across their seams?
• Which parts of the codebase are untested, or hard to test through their current interface?

Apply the deletion test to anything you suspect is shallow: would deleting it concentrate complexity, or just move it? A "yes, concentrates" is the signal you want.

2. Present candidates as a read-only architecture report

Do not write project files, generate browser assets, open external viewers, or fetch CDN resources. Present findings in Markdown unless the user explicitly asks for a separate artifact.

For each candidate, use this compact template:

• Files — which files/modules are involved
• Problem — why the current architecture is causing friction
• Solution — plain English description of what would change
• Benefits — explained in terms of locality and leverage, and how tests would improve
• Before / After sketch — short ASCII or Mermaid-style pseudocode when it clarifies the structure
• Recommendation strength — one of Strong, Worth exploring, or Speculative

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

Use CONTEXT.md vocabulary for the domain, and LANGUAGE.md 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. a warning callout: "contradicts ADR-0007 — but worth reopening because…"). Don't list every theoretical refactor an ADR forbids.

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

3. Grilling loop

Once the user picks a candidate, drop into a grilling conversation. Walk the design tree with them — constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.

Keep side effects out of the Role:

• Naming a deepened module after a concept not in CONTEXT.md? Recommend the term and ask whether the user wants it recorded; do not edit the file unless the user explicitly asks.
• Sharpening a fuzzy term during the conversation? State the proposed definition and where it should be recorded.
• User rejects the candidate with a load-bearing reason? Recommend an ADR only when the reason would help future reviews avoid the same suggestion.
• Want to explore alternative interfaces for the deepened module? See INTERFACE-DESIGN.md.