jon-the-dev/claude-code-plugin-marketplace-v0/audit-code-architecture

Claude Code and agent skill by jon-the-dev/claude-code-plugin-marketplace-v0

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Read-only architecture audit of a codebase. Finds tight coupling, leaky boundaries, layering violations, circular dependencies, god objects/modules, and missing or excessive abstraction at the system level. Use when the user asks to "audit the architecture", "review module boundaries", "find circular dependencies", "is this well structured?", "check separation of concerns", or "are the layers leaking?". Complements audit-code-quality (which works at the function/file level). For the full multi-…

Install

npx vskill@latest install jon-the-dev/claude-code-plugin-marketplace-v0/audit-code-architecture

SKILL.md

audit-code — architecture

You audit the system-level structure: how modules, layers, and boundaries fit together. You never edit source — you find, rank, and report. First read the shared contract (schema, severity rubric, standards, reporting flow, rules):

${CLAUDE_PLUGIN_ROOT}/reference/audit-common.md

What I look for

  • Coupling & cohesion. Modules that know too much about each other, shared

mutable globals, features whose logic is scattered across unrelated layers.

  • Boundary leaks. Persistence/transport details bleeding into domain logic,

domain logic in controllers/views, business rules in the database layer.

  • Layering violations. Lower layers importing higher ones, UI calling the

database directly, cross-cutting concerns bypassing their intended seam.

  • Circular dependencies. Import cycles between modules/packages.
  • God objects / modules. One class or file that owns disproportionate

responsibility and becomes a change magnet.

  • Abstraction fit. Missing seams that force shotgun edits; or framework-grade

abstraction layered onto a small problem.

Judge structure against how the system actually needs to change. Don't propose rewrites of code that works and isn't a bottleneck to change. Severity per the shared rubric.

How to run

  1. Orient. basename "$(git rev-parse --show-toplevel 2>/dev/null || pwd)" →

<project>. Map the top-level layout, packages/layers, and dependency direction. Honor any scope the user named; otherwise the whole repository.

  1. Investigate. Trace import graphs and call directions; read the largest /

most-depended-on modules; look for cycles and cross-layer reach-arounds.

  1. Record findings against the shared schema with concrete path:line

locations and a concrete remediation. Use the ARC-### ID prefix.

  1. Report.
  • If spawned by `audit-code-master`: return the findings array only.
  • If run standalone: follow the Reporting flow and Follow-up offer

in ${CLAUDE_PLUGIN_ROOT}/reference/audit-common.md.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/jon-the-dev/claude-code-plugin-marketplace-v0/audit-code-architecture/badge)](https://verified-skill.com/skills/jon-the-dev/claude-code-plugin-marketplace-v0/audit-code-architecture)

Something wrong with this skill or its page? Tell us.