architecture-check

architecture-check is a skill for Claude Code from joris887/exosuit. It costs 30 tokens per session (2,021 once invoked), scanned A, original, MIT.

A codebase architecture checker that compares the project’s actual modules and dependencies with its written architecture rules. Architecture describes how parts of a system are separated and allowed to interact.

In plain words
What is it for?
Use it to review module boundaries, inspect imports, and check architecture documents and decision records. It can suggest automated tests for preventing architectural drift.
Why use it?
It helps find boundary violations, unwanted dependencies, and circular imports before the codebase becomes harder to change. It also points to tests that can enforce the intended structure.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Part of the exosuit plugin — 44 skills, 1 command, 9 agents, 10 hooks shipped together

Good fit Use it to review module boundaries, inspect imports, and check architecture documents and decision records. It can suggest automated tests for preventing architectural drift.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joris887/exosuit/architecture-check
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.

Any agent
npx skills add joris887/exosuit --skill architecture-check
Clone the repo
git clone --depth 1 https://github.com/joris887/exosuit

Made for: Claude Code.

Or install exosuit, the plugin that ships this one along with the rest of its 44 skills, 1 command, 9 agents, 10 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for architecture-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/joris887/exosuit/architecture-check/github.svg)](https://agentmods.dev/skills/joris887/exosuit/architecture-check)
Your own site
<a href="https://agentmods.dev/skills/joris887/exosuit/architecture-check"><img src="https://agentmods.dev/badge/skills/joris887/exosuit/architecture-check/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for architecture-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/joris887/exosuit/architecture-check"><img src="https://agentmods.dev/badge/skills/joris887/exosuit/architecture-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,021 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 5.1 $0.00030 $0.02021
Opus 5 $0.00015 $0.01010
Sonnet 5 $0.00006 $0.00404
Haiku 4.5 $0.00003 $0.00202

Measured 9d ago against content hash 142a4a439f9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

architecture-check 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 9d 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.

.claude/skills/architecture-check/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.


architecture-check

You are a software architect validating that the codebase adheres to its documented architecture.

1. Load Architecture Documentation

Read:

  • docs/architecture/ARCHITECTURE.md — documented module boundaries and dependencies
  • docs/reference/GROUND_RULES.md — architectural ground rules with enforcement channels (if exists)
  • docs/adr/ — architecture decision records (if any exist)
  • CLAUDE.md — architecture one-liner

If ARCHITECTURE.md doesn't exist or is a template, inform the user and suggest running /bootstrap or creating one.

2. Validate Module Boundaries

Apply the architectural_impact reasoning tool from .claude/skills/story-cycle/references/reasoning-tools.md to assess module boundaries systematically.

For each documented module/layer:

If the Module Map section contains explicit Dependency Rules (MUST/NEVER statements), use those as the primary validation criteria rather than inferring boundaries from the diagram alone.

Import Analysis

Scan imports to check for violations:

  • No cross-layer imports — e.g., presentation layer should not import from data layer directly
  • No circular dependencies — module A imports B which imports A
  • Dependency direction — imports should flow in the documented direction (e.g., handlers → services → repositories, not reversed)
# Example: Find imports across boundaries
# grep -r "from data_layer" presentation_layer/
# grep -r "import.*handler" repository_layer/

Boundary Check

For each module:

  • Does it only depend on modules it's allowed to depend on?
  • Are there any "reaching across" imports that skip layers?
  • Are shared types/interfaces in the right location?

3. Check for Architectural Drift

Compare the actual code structure against ARCHITECTURE.md:

  • New modules — code directories not documented in ARCHITECTURE.md
  • Missing modules — documented modules that don't exist (yet or anymore)
  • Changed responsibilities — modules doing things outside their documented scope
  • Undocumented dependencies — imports between modules not shown in the architecture

Read the full file on GitHub · 227 lines

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. 9d ago First seen · 227 lines · 30 tokens per session scan A 142a4a439f9a

Subscribe to this mod's changes

architecture-check is a skill published in the GitHub repository joris887/exosuit (4 stars, last pushed 19d ago), licensed MIT. It adds 30 tokens to every session and 2,021 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

audit-agents-skills

Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.

FlorianBruniaux/claude-code-ultimate-guide · 41 tokens

design-patterns

Detect, suggest, and evaluate GoF design patterns in TypeScript/JavaScript codebases. Use when refactoring code, applying singleton/factory/observer/strategy patterns, reviewing pattern quality, or finding stack-native alternatives for React, Angular, NestJS, and Vue.

FlorianBruniaux/claude-code-ultimate-guide · 59 tokens

pr-triage

4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…

FlorianBruniaux/claude-code-ultimate-guide · 86 tokens

eval-skills

Audit all skills in the current project for frontmatter completeness, effort level appropriateness, allowed-tools scoping, and content quality. Produces a scored report with effort-level recommendations for each skill. Use when onboarding to a new project, reviewing skill quality before shipping, or adding effort…

FlorianBruniaux/claude-code-ultimate-guide · 67 tokens

review-pr

Perform a comprehensive code review of a pull request.

FlorianBruniaux/claude-code-ultimate-guide · 12 tokens

sonarqube

Analyze SonarCloud quality issues for a specific PR.

FlorianBruniaux/claude-code-ultimate-guide · 14 tokens