Agent skill

Architecture Quality

by AnastasiyaW in AnastasiyaW/codex-claude-code-config

Keep web applications, APIs and services readable as they grow: choose feature or domain seams, assign state ownership, enforce dependency direction, keep adapters thin, and verify file shape.

MITAuto-check passedDevelopment

Install Architecture Quality

skills CLI
$ npx skills add AnastasiyaW/codex-claude-code-config --skill architecture-quality -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AnastasiyaW/codex-claude-code-config architecture-quality --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/development/architecture-quality .claude/skills/architecture-quality && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
architecture-quality
GitHub stars
154
Token cost
~1.6k tokens
SKILL.md length
829 words
Files
1
Skills in repo
50
Repo updated
First seen
Licence
MIT

At a glance

Keep web applications, APIs and services readable as they grow: choose feature or domain seams, assign state ownership, enforce dependency direction, keep adapters thin, and verify file shape.

  • Works in 5 steps: Feature/domain modules — name them by… → Ownership — each mutable state, database… → Dependency direction — policy/domain… → …
  • Extending a web app
  • SKILL.md covers Working contract, Web application shape, Shape checks and Review questions, plus 2 more sections
  • Calls python

What it does

Architecture Quality is an agent skill from AnastasiyaW/codex-claude-code-config. Keep web applications, APIs and services readable as they grow: choose feature or domain seams, assign state ownership, enforce dependency direction, keep adapters thin, and verify file shape. Use when starting or extending a web app, backend, frontend, API or multi-page product; when a change makes a module hard to read; when architecture review finds a god file, cross-feature imports, a circular dependency or a framework-heavy domain. Load architecture-first first for a new system, and refactoring-safely for an…

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Software architecture and Refactoring. The repository describes itself as: Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development. The licence is MIT.

When your agent uses it

  • Extending a web app
  • Multi-page product
  • A change makes a module hard to read
  • Architecture review finds a god file

Example prompts

  • “/architecture-quality”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Feature/domain modules — name them by reason to change, not by a generic
  2. Ownership — each mutable state, database table boundary and external side
  3. Dependency direction — policy/domain code is independent of the web
  4. Vertical slice — prove one user-visible path from entry point to state and
  5. Verification boundary — list the architecture checks and the test command

What it can do on your machine

Read from SKILL.md and the folder at commit 67709af. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Architecture Quality loads about 1.6k tokens when it runs. Until then it costs about 162 tokens; SKILL.md has 829 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~162
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from AnastasiyaW/codex-claude-code-config at commit 67709af, republished under its MIT licence (© AnastasiyaW). 829 words, ~1,639 tokens.

Download SKILL.mdSave it as .claude/skills/architecture-quality/SKILL.md (or your agent's skills folder).
name
architecture-quality
description
Keep web applications, APIs and services readable as they grow: choose feature or domain seams, assign state ownership, enforce dependency direction, keep adapters thin, and verify file shape. Use when starting or extending a web app, backend, frontend, API or multi-page product; when a change makes a module hard to read; when architecture review finds a god file, cross-feature imports, a circular dependency or a framework-heavy domain. Load architecture-first first for a new system, and refactoring-safely for an existing oversized module. Do not use for a one-file script, throwaway spike or a purely local naming change.

Architecture quality — readable by construction

This skill turns the architecture decision into a small, repeatable delivery contract. It complements architecture-first; it does not add layers for their own sake.

Working contract

Before a non-trivial web or service change, record these five facts in ARCHITECTURE.md or docs/architecture/README.md:

  1. Feature/domain modules — name them by reason to change, not by a generic utils, helpers or services bucket.
  2. Ownership — each mutable state, database table boundary and external side effect has one owner.
  3. Dependency direction — policy/domain code is independent of the web framework, ORM, queue and filesystem; adapters point inward through small ports.
  4. Vertical slice — prove one user-visible path from entry point to state and test before multiplying layers or pages.
  5. Verification boundary — list the architecture checks and the test command that must remain green after the change.

If the project is a small script or a single-module experiment, state that scope and skip the document. A missing document is a finding only once the project has enough shape to need one, not a reason to create ceremony around a toy.

Web application shape

  • Keep routes/controllers thin: parse input, call a use-case or feature API, map the result and return. Do not put business policy, SQL and provider retries in a route.
  • Keep domain/use-case code framework-free where practical. Inject ports for storage, clocks, queues and providers; keep concrete adapters at the edge.
  • Organize user-facing behavior by feature or bounded context. A page may compose features, but one feature must not reach into another feature's private state.
  • Give each page a stable route-level composition boundary. Shared UI primitives are visual primitives, not a second business-logic layer.
  • Treat a utils or common import that keeps growing as a boundary question. Move code to the module that owns its reason to change; do not create a universal bag.
  • Prefer a modular monolith until an independently deployable or scalable boundary is proven. A microservice split is not a substitute for a missing internal boundary.

Shape checks

Run the repository audit before broadening a new app and after a structural change:

powershell
python scripts/architecture_audit.py --root .

The audit is intentionally conservative. It reports, rather than invents, findings:

  • a sizeable application with no ARCHITECTURE.md or architecture directory;
  • a source file crossing the calibrated shape thresholds;
  • an explicitly declared project marker without a readable architecture anchor.

The live module-shape-advisor.py hook repeats the file-shape check after Write|Edit|MultiEdit in both Codex and Claude. It is advisory: acknowledge the finding, split at an ownership boundary, or record why the file is intentionally large. CLAUDE_ALLOW_BIG_MODULES=1 is an explicit, reviewable escape hatch, not a default.

For dependency rules, use the tool native to the stack when the project has earned it:

  • Python: import-linter contracts for allowed import direction;
  • JavaScript/TypeScript: dependency-cruiser for cycles, orphans and forbidden folder edges;
  • Java: ArchUnit architecture tests alongside unit tests;
  • C/C++: compiler/include tooling plus explicit CMake target boundaries; do not infer a domain architecture from a raw include graph alone.

Do not install all four. Pick one boundary mechanism, commit its rules, and run it in the same CI lane as the tests that prove the behavior.

Show full SKILL.md (316 more words)Show less

Review questions

  • Can a new feature be changed without editing an unrelated feature's internals?
  • Does a route, page or controller own policy that belongs inside a use-case/domain?
  • Is state ownership named, or are modules reaching into shared mutable objects?
  • Are imports crossing a documented boundary? If yes, is the exception recorded with a reason and expiry?
  • Is the file becoming large because one change is crossing multiple reasons to change? If yes, split the seam before adding more behavior.
  • Did the change update the architecture document and the focused architecture/test evidence together?

Gotchas

  • Folders are not boundaries. Moving files without changing imports or ownership only makes the same coupling harder to see.
  • Thin controllers can still hide a fat service. Inspect the next boundary; a generic ApplicationService is often a god module with a nicer name.
  • A metric is a signal, not a verdict. Generated code, migrations and large declarative tables need explicit exemptions; production logic needs an explanation before an exemption.
  • Microservices can multiply unreadability. Network boundaries add failure, deployment and observability costs; prove the module boundary first.

Troubleshooting

SymptomLikely causeAction
The audit reports a missing architecture anchorAn app marker and several source files exist, but the boundary is implicitWrite the small module/ownership/dependency map before adding more features
module-shape-advisor reports a large fileLocal edits accumulated in one ownership boundaryAdd characterization tests, split one named slice, then rerun the audit
A cycle appearsTwo modules own part of the same concept or one imports an implementation detailMove the concept behind an inner port or extract a genuinely shared concept
Every change touches many foldersLayer-first layout scatters a feature across technical layersRecut the next slice by feature; migrate incrementally with tests
The guard is noisy on generated codeThe file is outside the built-in exemption listAdd a narrow, documented project exemption; do not silence the whole hook

© AnastasiyaW, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/development/architecture-quality of AnastasiyaW/codex-claude-code-config.

Open the folder on GitHubat commit 67709af

Compare with similar skills

Architecture Quality next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Architecture Quality compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Architecture Quality this skillAnastasiyaW/codex-claude-code-config154—~1.6kAutomated safety check: PassMIT
Architecture PatternsKartikLabhshetwar/better-shot2.4k2 repos~1.4kAutomated safety check: PassCustom licence
Brooks Audithyhmrright/brooks-lint1.5k1 repos~537Automated safety check: PassMIT
Birdview ReviewQiuner/birdview726—~580Automated safety check: PassMIT
Py Rigmudrii/hermesd118—~6.3kAutomated safety check: PassMIT
Vanity Engineering Reviewbencium/bencium-marketplace446—~2.4kAutomated safety check: PassMIT

Similar skills

  • Architecture Patterns

    KartikLabhshetwar/better-shot

    Deep dive into software architecture for macOS. An agent skill from KartikLabhshetwar/better-shot.

    2.4k GitHub starsUsed in 2 repos~1.4k tokens
    DevelopmentAuto-check passed
  • Brooks Audit

    hyhmrright/brooks-lint

    Architecture audit that maps module dependencies, checks layering integrity, and flags structural decay across a codebase, drawing on twelve classic engineering books.

    1.5k GitHub starsUsed in 1 repo~537 tokens
    DevelopmentAuto-check passed
  • Birdview Review

    Qiuner/birdview

    Review and improve codebase architecture with source-backed current/proposed diagrams, tradeoffs and verification.

    726 GitHub stars~580 tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Py Rig

    mudrii/hermesd

    A skill your agent uses when building, reviewing, or refactoring Python code that requires strong maintainability discipline: SRP, DRY, OCP, explicit dependency injection, TDD/ATDD workflow, strict…

    118 GitHub stars~6.3k tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • Vanity Engineering Review

    bencium/bencium-marketplace

    Reviews codebases, architectures, PRs, and technical plans for vanity engineering — code and systems built for the developer's ego, resume, or intellectual pleasure rather than delivering user or…

    446 GitHub stars~2.4k tokensUpdated 7 days ago
    DevelopmentAuto-check passed
  • A Philosophy of Software Design

    ciembor/agent-rules-books

    Apply John Ousterhout-inspired software design rules when reducing complexity, designing module boundaries, or reviewing APIs and abstractions.

    2.9k GitHub stars~181 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from AnastasiyaW/codex-claude-code-config

All 50 skills in this repo
  • Bug Reproducer

    AnastasiyaW/codex-claude-code-config

    Find likely software bugs in a codebase, rank concrete bug candidates, and prove or reject them with focused regression tests before proposing a fix.

    154 GitHub stars~4.1k tokensUpdated today
    Auto-check passed
  • Motion Framer

    AnastasiyaW/codex-claude-code-config

    A skill your agent uses when implementing Motion or Framer Motion in React/JavaScript: interactive UI components, micro-interactions, gestures, layout or page transitions, and scroll-based animation.

    154 GitHub starsUsed in 1 repo~5.2k tokens
    Auto-check passed
  • Proof Verify

    AnastasiyaW/codex-claude-code-config

    Plan-based verification - freeze acceptance criteria before building, then verify after with an independent fresh-context agent (the builder must not verify their own work).

    154 GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • Workflow Orchestration

    AnastasiyaW/codex-claude-code-config

    Написание и запуск Claude Code dynamic workflows (JS-оркестратор субагентов).

    154 GitHub stars~3.8k tokensUpdated today
    Auto-check passed
  • Notebooklm Grounded Research

    AnastasiyaW/codex-claude-code-config

    A skill your agent uses when: NotebookLM, notebooklm MCP, large documentation sets, courses, books, papers, or citation-backed research are mentioned.

    154 GitHub stars~2.4k tokensUpdated today
    Auto-check: warnings
  • Deepseek Provider Contract

    AnastasiyaW/codex-claude-code-config

    Validate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode tool-call history, strict-schema assumptions, bounded output, and provider data boundaries.

    154 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

Categories

Questions about Architecture Quality

What does Architecture Quality do?

Keep web applications, APIs and services readable as they grow: choose feature or domain seams, assign state ownership, enforce dependency direction, keep adapters thin, and verify file shape. Architecture Quality is an agent skill from AnastasiyaW/codex-claude-code-config. Keep web applications, APIs and services readable as they grow: choose feature or domain seams, assign state ownership, enforce dependency direction, keep adapters thin, and verify file shape.

When should I use Architecture Quality?

Architecture Quality fits situations like: extending a web app; multi-page product; A change makes a module hard to read; architecture review finds a god file.

How do I install Architecture Quality in Claude Code?

Run `npx skills add AnastasiyaW/codex-claude-code-config --skill architecture-quality -a claude-code`. Or copy the skill folder (skills/development/architecture-quality in AnastasiyaW/codex-claude-code-config) into .claude/skills/architecture-quality in your project. Claude Code loads it when a task matches its description.

How do I install Architecture Quality in Codex?

Run `npx skills add AnastasiyaW/codex-claude-code-config --skill architecture-quality -a codex`. Or copy the skill folder (skills/development/architecture-quality in AnastasiyaW/codex-claude-code-config) into .agents/skills/architecture-quality in your project. Codex loads it when a task matches its description.

Can I use Architecture Quality in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AnastasiyaW/codex-claude-code-config --skill architecture-quality -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/architecture-quality, .gemini/skills/architecture-quality, .github/skills/architecture-quality and .opencode/skills/architecture-quality in your project.

What does Architecture Quality need to run?

Going by SKILL.md and its folder, Architecture Quality needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Architecture Quality access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Architecture Quality safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Architecture Quality use?

Architecture Quality is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Architecture Quality use?

About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Architecture Quality?

Skills that share tags, products or a category with Architecture Quality: Architecture Patterns (KartikLabhshetwar/better-shot, 2.4k stars), Brooks Audit (hyhmrright/brooks-lint, 1.5k stars), Birdview Review (Qiuner/birdview, 726 stars) and Py Rig (mudrii/hermesd, 118 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Architecture Quality?

AnastasiyaW (a GitHub user) maintains it in AnastasiyaW/codex-claude-code-config, which has 154 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on October 9, 2026.

Source: AnastasiyaW/codex-claude-code-config on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.