improve-codebase-architecture

A code-review guide that examines a codebase using its domain terms and recorded architecture decisions. It identifies places where modules could hide more complexity behind simpler interfaces.

In plain words
What is it for?
Use it to find refactoring opportunities, combine tightly connected modules, improve testability, and make a codebase easier for an AI agent to navigate.
Why use it?
It helps reveal tangled code, unclear responsibilities, and changes that are hard to test or understand. It also gives maintainers a shared vocabulary for discussing those problems.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/modernweb-dev/rocket/improve-codebase-architecture
Any agent
npx skills add modernweb-dev/rocket --skill improve-codebase-architecture
Clone the repo
git clone --depth 1 https://github.com/modernweb-dev/rocket

Made for: Claude Code, Codex.

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,467 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 77% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00068 $0.01467
Opus 5 $0.00034 $0.00733
Sonnet 5 $0.00014 $0.00293
Haiku 4.5 $0.00007 $0.00147

Measured 2d ago against content hash f00de04c7bb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

improve-codebase-architecture scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

77% identical to improve-codebase-architecture — 70 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/improve-codebase-architecture/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.

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?

Read the full file on GitHub · 82 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 82 lines · 68 tokens per session scan A f00de04c7bb8

Subscribe to this mod's changes

improve-codebase-architecture is a skill published in the GitHub repository modernweb-dev/rocket (394 stars, last pushed 4d ago), licensed MIT. It adds 68 tokens to every session and 1,467 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 77% identical to improve-codebase-architecture, differing in 70 lines, and is treated as a copy.

Related

Other skills, from other repositories

marmite-development

Guidelines and workflows for contributing to the marmite codebase - covers code quality, testing, architecture patterns, and contribution checklists.

rochacbruno/marmite · 31 tokens

marmite

Build and manage static sites with marmite - a zero-config static site generator that turns markdown files into websites.

rochacbruno/marmite · 25 tokens

resume-builder

Generate professional resumes that conform to the Reactive Resume schema. Use when the user wants to create, build, or generate a resume through conversational AI, or asks about resume structure, sections, or content. This skill guides the agent to ask clarifying questions, avoid hallucination, and produce valid JSON…

amruthpillai/reactive-resume · 71 tokens

dependency-flow

MAUI-specific dependency flow rules, channel conventions, and feed lookup workflows. Use when asked about darc, BAR, Maestro, feeds for .NET MAUI, build promotion, asset lookup, channel mappings, or dependency flow for dotnet/maui. Wraps the maestro-cli skill and maestro MCP tools with MAUI-specific guardrails.

dotnet/maui · 71 tokens

evaluate-pr-tests

Evaluates tests added in a PR for coverage, quality, edge cases, and test type appropriateness. Checks if tests cover the fix, finds gaps, and recommends lighter test types when possible. Prefer unit tests over device tests over UI tests. Triggers on: 'evaluate tests in PR', 'review test quality', 'are these tests…

dotnet/maui · 94 tokens

pr-finalize

Finalizes any PR for merge by verifying title/description match implementation AND performing code review for best practices. Use when asked to "finalize PR", "check PR description", "review commit message", before merging any PR, or when PR implementation changed during review. Do NOT use for extracting lessons (use…

dotnet/maui · 92 tokens