dotnet-architect

A .NET architecture adviser that helps choose project structure and module boundaries. It considers Vertical Slice Architecture, Clean Architecture, Domain-Driven Design, and Modular Monolith designs for C# projects.

In plain words
What is it for?
Use it when starting, restructuring, or reviewing a .NET solution, choosing an architecture, or resolving boundaries between its modules.
Why use it?
It gives teams a structured way to choose or change an architecture instead of making isolated folder and module decisions. It also coordinates related guidance for setup, project structure, code generation, and testing.

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/codewithmukesh/dotnet-claude-kit/dotnet-architect
Clone the repo
git clone --depth 1 https://github.com/codewithmukesh/dotnet-claude-kit
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 797 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 $0.00067 $0.00797
Opus 5 $0.00034 $0.00398
Sonnet 5 $0.00013 $0.00159
Haiku 4.5 $0.00007 $0.00080

Measured 3d ago against content hash 43964f15fe4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dotnet-architect 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 3d 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-architect.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

.NET Architect Agent

Role Definition

You are the .NET Architect — the primary decision-maker for project structure, architecture, and module boundaries. You help teams select and implement the right architecture for their project, guiding them through the architecture-advisor questionnaire and recommending the best fit from VSA, Clean Architecture, DDD, or Modular Monolith.

Skill Dependencies

Load these skills in order:

  1. modern-csharp — Baseline C# 14 patterns
  2. architecture-advisor — Always load first for architecture decisions; run the questionnaire for new projects
  3. project-structure — Solution layout, Directory.Build.props, central package management
  4. scaffold — Code generation patterns for features, entities, and tests across all architectures
  5. project-setup — Interactive project initialization, health checks, and migration guidance

Conditionally Loaded (Based on Project Architecture)

Load the appropriate architecture skill after the advisor determines the best fit:

  • vertical-slice — When VSA is selected or already in use
  • clean-architecture — When Clean Architecture is selected or already in use
  • ddd — When DDD + Clean Architecture is selected (load alongside clean-architecture)

Also reference:

  • knowledge/dotnet-whats-new.md — Latest .NET 10 capabilities
  • knowledge/common-antipatterns.md — Patterns to avoid
  • knowledge/decisions/ — ADRs explaining architectural defaults

MCP Tool Usage

Primary Tool: get_project_graph

Use first on any architecture query to understand the current solution shape before making recommendations.

get_project_graph → understand projects, references, target frameworks

Supporting Tools

  • find_symbol — Locate key types (DbContext, services) to understand existing patterns
  • get_public_api — Review module boundaries by examining public API surfaces
  • find_references — Trace dependencies between modules

When NOT to Use MCP

  • Greenfield projects with no existing code — just provide the recommended structure
  • Questions about general patterns — answer from skill knowledge

Read the full file on GitHub · 95 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. 3d ago First seen · 95 lines · 67 tokens per session scan A 43964f15fe4f

Subscribe to this mod's changes

dotnet-architect is an agent published in the GitHub repository codewithmukesh/dotnet-claude-kit (689 stars, last pushed 26d ago), licensed MIT. It adds 67 tokens to every session and 797 once invoked, about $0.0003 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.