dotnet-architecture-reviewer.USAGE

dotnet-architecture-reviewer.USAGE is an agent for coding agents from StefanTheCode/dotnet-ai-toolkit. It costs 0 tokens per session (372 once invoked), scanned A, original, MIT.

A .NET code-review agent that reads an entire repository, maps how its projects depend on one another, identifies the intended architecture, and reports structural problems with suggested fixes.

In plain words
What is it for?
Use it to review an inherited repository, check Clean Architecture or another intended style, find dependency and coupling issues, assess CQRS and Entity Framework boundaries, and improve testability.
Why use it?
It provides a second opinion on how a .NET codebase is organised, including problems that may be missed when reviewing one file at a time.

Agent

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.

agentmods
npx agentmods add agents/stefanthecode/dotnet-ai-toolkit/dotnet-architecture-reviewer.usage
Clone the repo
git clone --depth 1 https://github.com/StefanTheCode/dotnet-ai-toolkit

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 dotnet-architecture-reviewer.USAGE

README.md
[![agentmods](https://agentmods.dev/badge/agents/stefanthecode/dotnet-ai-toolkit/dotnet-architecture-reviewer.usage.svg)](https://agentmods.dev/agents/stefanthecode/dotnet-ai-toolkit/dotnet-architecture-reviewer.usage)
Your own site
<a href="https://agentmods.dev/agents/stefanthecode/dotnet-ai-toolkit/dotnet-architecture-reviewer.usage"><img src="https://agentmods.dev/badge/agents/stefanthecode/dotnet-ai-toolkit/dotnet-architecture-reviewer.usage.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 372 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00372
Opus 5 $0.00000 $0.00186
Sonnet 5 $0.00000 $0.00074
Haiku 4.5 $0.00000 $0.00037

Measured 4d ago against content hash 1000f647b4c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dotnet-architecture-reviewer.USAGE 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 4d 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.

agents/dotnet-architecture-reviewer.USAGE.md · 19 lines

What it actually says

How to use — .NET Architecture Reviewer (agent)

What it is. An agent (not a single-shot skill) that reads a whole .NET repository, maps the project dependency graph, detects the intended architecture style, and produces a ranked report: layering/dependency-rule violations, coupling, CQRS hygiene, EF boundary leaks, testability — each with a concrete fix, plus a prioritized action list.

When to reach for it. A structural second opinion on a codebase, onboarding to an inherited project, a "is my architecture clean" check, or a periodic health review.

How to use it. Point it at a repo or solution folder. Because it's an agent, it explores files on its own — you don't need to paste code. Example prompts:

  • "Review the architecture of this solution."
  • "I inherited this .NET repo — map the structure and tell me what's wrong."
  • "Is this following Clean Architecture properly? What violates it?"

How to get the best out of it.

  • Give it the whole solution, not one file — its value is seeing the dependency graph across projects.
  • Tell it the intended style if you know it ("this is meant to be Vertical Slice") so it reviews against the right rules; otherwise it infers.
  • Ask for the prioritized action list to be the focus if you want a get-started-now plan rather than a full audit.
  • Run it periodically (it pairs well with a monthly cadence) and diff the reports to track whether the structure is improving or rotting.

What it won't do. It reviews structure, not runtime behavior or business correctness. It's deliberately practical — it'll tell you when a "violation" is actually the right call for your team size rather than flagging dogma.

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. 4d ago First seen · 19 lines · 0 tokens per session scan A 1000f647b4c3

Subscribe to this mod's changes

dotnet-architecture-reviewer.USAGE is an agent published in the GitHub repository StefanTheCode/dotnet-ai-toolkit (19 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 372 tokens. 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.