audit-architecture

audit-architecture is a skill for Claude Code, Codex from panbanda/omen. It costs 33 tokens per session (938 once invoked), scanned A, original, Apache-2.0.

A process for reviewing the structure of a codebase, including how its modules depend on one another and how focused they are.

In plain words
What is it for?
Generating dependency graphs, finding design smells, measuring class cohesion and coupling, and detecting files that change together without clear imports.
Why use it?
It reveals circular dependencies, overly central modules, hidden connections, and classes that have too many responsibilities.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Part of the omen-development plugin — 13 skills shipped together

Good fit Generating dependency graphs, finding design smells, measuring class cohesion and coupling, and detecting files that change together without clear imports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/panbanda/omen/audit-architecture
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 panbanda/omen --skill audit-architecture
Clone the repo
git clone --depth 1 https://github.com/panbanda/omen

Made for: Claude Code, Codex.

Or install omen-development, the plugin that ships this one along with the rest of its 13 skills.

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 audit-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/panbanda/omen/audit-architecture.svg)](https://agentmods.dev/skills/panbanda/omen/audit-architecture)
Your own site
<a href="https://agentmods.dev/skills/panbanda/omen/audit-architecture"><img src="https://agentmods.dev/badge/skills/panbanda/omen/audit-architecture.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 938 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00033 $0.00938
Opus 5 $0.00016 $0.00469
Sonnet 5 $0.00007 $0.00188
Haiku 4.5 $0.00003 $0.00094

Measured 8d ago against content hash 1e7df9185b2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

audit-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 8d 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.

plugins/development/skills/audit-architecture/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Architecture

Analyze the structural health of a codebase by examining coupling, cohesion, hidden dependencies, and design patterns.

Prerequisites

Omen CLI must be installed and available in PATH.

Workflow

Step 1: Map Module Dependencies

Run the dependency graph analysis:

omen -f json graph

Look for:

  • Circular dependencies
  • God modules (too many dependents)
  • Orphan modules (no connections)

Step 2: Detect Architectural Smells

Run the smells analysis:

omen -f json smells

Detects cyclic dependencies, hub modules, unstable dependencies, and central connectors using Tarjan's SCC algorithm.

Step 3: Measure Cohesion

Run the cohesion analysis for CK metrics:

omen -f json cohesion

Metrics to watch:

  • LCOM (Lack of Cohesion): > 0.7 indicates class doing too many things
  • WMC (Weighted Methods per Class): > 30 indicates too complex
  • CBO (Coupling Between Objects): > 10 indicates too many dependencies

Step 4: Find Hidden Dependencies

Run the temporal coupling analysis:

omen -f json temporal

Files that always change together but don't have explicit imports indicate:

  • Shared global state
  • Implicit contracts
  • Missing abstractions

Step 5: Check Ownership Distribution

Run the ownership analysis:

omen -f json ownership

Look for:

  • Modules with no clear owner
  • Over-concentrated ownership (bus factor = 1)
  • Fragmented ownership (many contributors, none dominant)

Architecture Smells

Common issues to identify:

Smell Detection Impact
Circular Dependency A -> B -> C -> A in graph Hard to test, modify
God Module > 50% of code depends on it Single point of failure
Shotgun Surgery High temporal coupling Changes ripple everywhere
Feature Envy Low cohesion in classes Wrong abstraction boundaries
Knowledge Silo Bus factor = 1 Team risk

Output Format

Present architecture review as:

Read the full file on GitHub · 161 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. 8d ago First seen · 161 lines · 33 tokens per session scan A 1e7df9185b2c

Subscribe to this mod's changes

audit-architecture is a skill published in the GitHub repository panbanda/omen (19 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 938 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 2026-08-30.

Related

Other skills, from other repositories

plan-eng-review

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…

GCWing/BitFun · 116 tokens

pre-landing-review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by OpenBitFun's unified Review mechanism instead.…

GCWing/BitFun · 75 tokens

pr-review-canvas

Create a OpenBitFun Canvas for reviewing a pull request, branch diff, or change set with Cursor-style diff cards, review maps, risk callouts, and focused reviewer flow. Use when the user asks for a PR review canvas, diff walkthrough, change-set overview, or visual review summary.

GCWing/BitFun · 64 tokens

improve

Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.

SethGammon/Citadel · 48 tokens

github-review-pr

Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for…

feiskyer/claude-code-settings · 90 tokens

brooks-sweep

Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…

hyhmrright/brooks-lint · 178 tokens