| name | improve-codebase-architecture |
| description | Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick. |
| disable-model-invocation | true |
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.
This command is built on a shared design vocabulary and informed by whatever domain knowledge the project already records:
- Run the
/codebase-design skill for the architecture vocabulary (module, interface, depth, seam, adapter, leverage, locality) and its principles (the deletion test, "the interface is the test surface", "one adapter = hypothetical seam, two = real"). Use these terms exactly in every suggestion — don't drift into "component," "service," "API," or "boundary."
- Discover and use existing domain knowledge and decision records when they are present. Do not assume specific filenames or create a documentation layout when they are absent.
Process
1. Explore
Scope before you scan — YAGNI. Deepening a module pays off by making future changes to it easier, so put extra weight on the parts of the codebase that have recently changed. Decide where to look before you look:
- If the user named a direction — a module, a subsystem, a pain point — take it, and skip the inference below.
- Otherwise, walk back a good stretch of the commit history (
git log --oneline) to find the codebase's hot spots — the files and areas that keep coming up — and let those paths pull your attention first. If the changes are scattered with no clear hot spot, widen the net.
Before scanning, discover and read any existing domain knowledge and decision records for the area you're touching. If none exist, use the language in the code and the user's request.
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 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 for the user — xdg-open <path> on Linux, open <path> on macOS, start <path> on Windows — and tell them the absolute path.
The report uses Tailwind via CDN for layout and styling, and Mermaid via CDN for diagrams where a graph/flow/sequence reliably communicates the structure. Mix Mermaid with hand-crafted CSS/SVG visuals — use Mermaid when relationships are graph-shaped (call graphs, dependencies, sequences), and hand-built divs/SVG when you want something more editorial (mass diagrams, cross-sections, collapse animations). Each candidate gets a before/after visualisation. Be visual.
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 — explained in terms of locality and leverage, and how tests would improve
- Before / After diagram — side-by-side, custom-drawn, illustrating the shallowness and the deepening
- Recommendation strength — one of
Strong, Worth exploring, Speculative, rendered as a badge
End the report with a Top recommendation section: which candidate you'd tackle first and why.
Use the project's existing domain vocabulary when available, and the /codebase-design vocabulary for the architecture. If the project calls the concept "Order," talk about "the Order intake module" — not "the FooBarHandler," and not "the Order service."
Recorded-decision conflicts: if a candidate contradicts an existing decision record, only surface it when the friction is real enough to warrant revisiting that decision. Mark it clearly in the card and name the actual record. Don't list every theoretical refactor a recorded decision forbids.
See HTML-REPORT.md for the full HTML scaffold, diagram patterns, and styling guidance.
Do NOT propose interfaces yet. After the file is written, ask the user: "Which of these would you like to explore?"
3. Grilling loop
Once the user picks a candidate, run the /grill-me 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 — update domain knowledge docs if they already exist (discover the repo's layout; don't invent one):
- New or sharpened domain term? Update the existing domain knowledge doc.
- User rejects the candidate with a load-bearing reason? Offer to record it in whatever decision-log format the repo already uses (e.g. an ADR), framed as: "Want me to record this so future architecture reviews don't re-suggest it?" Only offer when the reason would actually be needed by a future explorer — skip ephemeral reasons ("not worth it right now") and self-evident ones.
- Want to explore alternative interfaces for the deepened module? Run the
/codebase-design skill and use its design-it-twice parallel sub-agent pattern.
