review-arch

review-arch is a command for Claude Code from davistroy/claude-marketplace. It costs 15 tokens per session (3,850 once invoked), scanned A, original, MIT.

A read-only architecture audit that examines a project for code quality, design, security, speed, testing, and dependencies. Architecture means the overall structure and relationships of a software system.

In plain words
What is it for?
Use it to review the whole repository or selected areas, such as security and testing, and optionally receive results as structured JSON for automation.
Why use it?
It provides a quick assessment of technical debt and potential design problems without changing project files.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the personal-plugin plugin — 29 skills, 23 commands, 10 agents, 2 hooks shipped together

Good fit Use it to review the whole repository or selected areas, such as security and testing, and optionally receive results as structured JSON for automation.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/davistroy/claude-marketplace/review-arch
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.

Clone the repo
git clone --depth 1 https://github.com/davistroy/claude-marketplace

Made for: Claude Code.

Or install personal-plugin, the plugin that ships this one along with the rest of its 29 skills, 23 commands, 10 agents, 2 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 review-arch

README.md
[![agentmods](https://agentmods.dev/badge/commands/davistroy/claude-marketplace/review-arch/github.svg)](https://agentmods.dev/commands/davistroy/claude-marketplace/review-arch)
Your own site
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/review-arch"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/review-arch/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 review-arch

Your own site · 80×15
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/review-arch"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/review-arch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,850 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 $0.00015 $0.03850
Opus 5 $0.00008 $0.01925
Sonnet 5 $0.00003 $0.00770
Haiku 4.5 $0.00002 $0.00385

Measured 7d ago against content hash 162cc8fece65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-arch 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 7d 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/personal-plugin/commands/review-arch.md · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Architecture

READ-ONLY COMMAND — DO NOT MAKE ANY CHANGES TO FILES. ONLY ANALYZE AND REPORT.

Perform a quick architectural audit of this project. This command provides an in-conversation analysis without generating files. For a comprehensive analysis with saved RECOMMENDATIONS.md and IMPLEMENTATION_PLAN.md, use /plan-improvements instead.

Input Validation

Optional Flags:

Flag Values Default Description
--json (none — boolean flag) off Output results as structured JSON instead of text. Enables CI/CD pipeline integration and programmatic consumption.
--focus Comma-separated dimension names all dimensions Limit analysis to specific dimensions. Valid values: code-quality, architecture, security, performance, testing, dependencies.

Focus Flag Validation: If --focus is provided, validate each dimension name. If any are invalid, display:

Error: Invalid focus dimension(s): [invalid-names]

Valid dimensions: code-quality, architecture, security, performance, testing, dependencies

Example: /review-arch --focus security,testing

Dimension Name Mapping:

Focus Flag Value Corresponds To
architecture Dimension 1: Structure & Organization
code-quality Dimension 2: Code Quality
dependencies Dimension 3: Dependency Management
testing Dimension 4: Testing
security Dimension 5: Security
performance Dimension 6: Performance & Scalability

Before proceeding, verify:

  • This is a code project (not just documentation or data)
  • Project structure is readable and contains source files
  • The codebase has sufficient complexity to warrant architectural review (not a single-file script)

For single-file projects or simple scripts, provide a brief assessment rather than a full architectural audit.

Instructions

Follow these phases in sequence. Phase 1 gathers data; Phases 2-3 analyze it; Phase 4 produces the remediation roadmap.

Read the full file on GitHub · 341 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. 7d ago First seen · 341 lines · 15 tokens per session scan A 162cc8fece65

Subscribe to this mod's changes

review-arch is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 3,850 once invoked, about $0.0001 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 2026-09-04.