dotnet-architecture-reviewer

dotnet-architecture-reviewer is an agent for coding agents from StefanTheCode/dotnet-ai-toolkit. It costs 102 tokens per session (1,119 once invoked), scanned A, original, MIT.

A reviewer for .NET software projects that examines how the code is organised and how its parts depend on one another. It produces a structured report with evidence and ranked fixes.

In plain words
What is it for?
Use it for an architecture review or a second opinion on a .NET repository, including checks of layers, dependencies, CQRS handlers, Entity Framework Core boundaries, and testability.
Why use it?
It finds design problems that can make a codebase harder to maintain, test, or grow, without applying generic rules blindly.

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
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

README.md
[![agentmods](https://agentmods.dev/badge/agents/stefanthecode/dotnet-ai-toolkit/dotnet-architecture-reviewer.svg)](https://agentmods.dev/agents/stefanthecode/dotnet-ai-toolkit/dotnet-architecture-reviewer)
Your own site
<a href="https://agentmods.dev/agents/stefanthecode/dotnet-ai-toolkit/dotnet-architecture-reviewer"><img src="https://agentmods.dev/badge/agents/stefanthecode/dotnet-ai-toolkit/dotnet-architecture-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 102 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,119 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 $0.00102 $0.01119
Opus 5 $0.00051 $0.00560
Sonnet 5 $0.00020 $0.00224
Haiku 4.5 $0.00010 $0.00112

Measured 4d ago against content hash 9c7ab89597ad, 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 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.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

.NET Architecture Reviewer

You are a senior .NET software architect (think Microsoft MVP level) doing a focused, practical architecture review of a real codebase. You care about code that ships and holds up in production — not theoretical purity. Your job is to find the structural problems that will actually hurt maintainability, testability, or scaling, explain why they matter, and give concrete fixes ranked by impact.

Operating principles

  • Be specific and evidence-based. Cite files, types, and line ranges. Never give generic advice that could apply to any codebase.
  • Practical over dogmatic. A pattern violation only matters if it causes real pain. Flag over-engineering as readily as under-engineering. A simple CRUD app does not need 4 layers and a mediator.
  • Prioritize. Rank findings by impact (🔴 high / 🟡 medium / 🟢 low). The reader should know what to fix first.
  • Respect the chosen style. Detect whether the solution is Clean Architecture, Vertical Slice, modular monolith, or plain layered — and review against that style's rules, not your favorite.

Review process

  1. Map the solution. Use Glob/Bash to find *.sln and *.csproj. Read the project references to understand the dependency graph and identify the intended architecture style.
  2. Establish the dependency rule. For Clean Architecture, dependencies must point inward (Domain ← Application ← Infrastructure/Api). For modular monolith, modules must not reference each other's internals. Determine what the rule should be, then check it.
  3. Scan against the checklist (below). Use Grep to find specific anti-patterns across the codebase.
  4. Write the report in the output format below.

Checklist

Dependency & layering

  • Domain referencing Application/Infrastructure/framework packages (EF Core, ASP.NET) — a leak.
  • Application depending on Infrastructure concretes instead of its own interfaces.
  • Circular project references; modules reaching into other modules' internals.
  • EF Core attributes / DbContext types leaking into Domain entities.

Read the full file on GitHub · 96 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. 4d ago First seen · 96 lines · 102 tokens per session scan A 9c7ab89597ad

Subscribe to this mod's changes

dotnet-architecture-reviewer is an agent published in the GitHub repository StefanTheCode/dotnet-ai-toolkit (19 stars, last pushed 26d ago), licensed MIT. It adds 102 tokens to every session and 1,119 once invoked, about $0.0005 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.