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 when one is available. The domain language gives names to good seams; ADRs record decisions the skill should not re-litigate.

Process

1. Explore

Domain glossary check. Before exploring code:

• If the project has a CONTEXT.md / domain glossary, read it. If docs/adr/ exists, read ADRs in the area you're touching.
• If CONTEXT.md does NOT exist, surface this to the user — say something like: "This project has no CONTEXT.md. I'll proceed using LANGUAGE.md architectural vocabulary, but my candidate names will be generic. Want me to seed a CONTEXT.md once we identify the first deepening candidate's domain, or proceed without?" Don't block on the answer — proceed if AFK.
• If docs/adr/ does NOT exist, mention it once at the moment a candidate would warrant an ADR (Step 3) — not up front.

Then use the Agent tool with subagent_type=Explore to walk the codebase. 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

Present a numbered list of deepening opportunities. For each candidate:

• 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 also in how tests would improve

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." If no CONTEXT.md exists yet, name candidates with the most domain-precise term you can extract from the code, and flag the term as a candidate to seed CONTEXT.md with.

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 (e.g. "contradicts ADR-0007 — but worth reopening because…"). Don't list every theoretical refactor an ADR forbids.

Do NOT propose interfaces yet. 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.

Side effects happen inline as decisions crystallize:

• Naming a deepened module after a concept not in CONTEXT.md? Add the term to CONTEXT.md — same discipline as /grill-with-docs (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? See INTERFACE-DESIGN.md.
• Implementation strategy after the interface is chosen? See DEEPENING.md for how to deepen safely given the candidate's dependency category (in-process / local-substitutable / remote-but-owned / true-external).

Use with

• grill-with-docs — peer producer of CONTEXT.md. Use when the conversation is about a plan (not yet code); use this skill when the conversation is about existing code shape. They share CONTEXT-FORMAT.md and ADR-FORMAT.md discipline.
• diagnose — after a diagnose session ends with "no correct seam exists for the regression test," that's the trigger for this skill. The bug is telling you the architecture needs deepening.
• blueprint — once you've picked a candidate and grilled it, use blueprint to turn the chosen deepening into a multi-PR roadmap.
• architecture-decision-records — your existing ADR detection skill. This skill writes ADRs sparingly during the grilling loop; the standalone skill catches decisions that slip past in other contexts.

Origin

Adapted from mattpocock/skills — engineering/improve-codebase-architecture. License: MIT.