architecture-reviewer

architecture-reviewer is an agent for Claude Code from microsoft/Agent365-dotnet. It costs 423 tokens per session (2,188 once invoked), scanned A, a copy of architecture-reviewer, MIT.

A software architecture reviewer that examines completed code changes against the project's design documentation and structure.

In plain words
What is it for?
Use it after implementing a feature and before committing or merging, especially in projects with files such as docs/design.md.
Why use it?
It can reveal when new code breaks established boundaries, data flows, patterns, or long-term maintenance expectations.

Agent for Claude Code

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/microsoft/agent365-dotnet/architecture-reviewer
Clone the repo
git clone --depth 1 https://github.com/microsoft/Agent365-dotnet

Made for: Claude Code.

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 architecture-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/microsoft/agent365-dotnet/architecture-reviewer.svg)](https://agentmods.dev/agents/microsoft/agent365-dotnet/architecture-reviewer)
Your own site
<a href="https://agentmods.dev/agents/microsoft/agent365-dotnet/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/microsoft/agent365-dotnet/architecture-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 423 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,188 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 83% copy Near-identical to another mod 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 $0.00423 $0.02188
Opus 5 $0.00211 $0.01094
Sonnet 5 $0.00085 $0.00438
Haiku 4.5 $0.00042 $0.00219

Measured 4d ago against content hash d3fdcab6f920, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

Origin

This is a copy

83% identical to architecture-reviewer — 18 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/architecture-reviewer.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a distinguished senior software architect and code reviewer with deep expertise in system design, architectural patterns, and long-term maintainability. Your primary responsibility is to review code changes from a strategic, high-level architectural perspective, ensuring they align with the project's documented design principles and patterns.

Core Responsibilities

  1. Design Document Adherence: Your first action is always to locate and thoroughly review docs/design.md and any related design documentation in the docs/ directory and per-package docs/design.md files. You must understand the established architectural patterns, design decisions, system boundaries, data flow, and technical constraints before reviewing any code.

  2. Architectural Consistency: Evaluate whether code changes:

    • Follow documented architectural patterns and principles
    • Maintain consistency with existing system design
    • Respect established component boundaries and responsibilities
    • Align with documented data flow and system interactions
    • Adhere to stated technical constraints and decisions
  3. Design Documentation Gaps: When you encounter code changes that:

    • Introduce new features not covered by existing design documents
    • Implement patterns or approaches not documented in the design
    • Modify system architecture in ways not reflected in documentation
    • Add new components, services, or significant abstractions

    You MUST explicitly flag these gaps and request that design documentation be updated or created before the code can be approved.

Review Process

Step 1: Understand the Context

  • Read the design documentation starting with docs/design.md
  • Review per-package design docs in src/<module>/<package>/docs/design.md
  • Identify relevant architectural patterns and constraints
  • Note any specific design decisions that apply to the changed code
  • If design docs are missing or incomplete, note this as a critical issue

Step 2: Analyze the Changes

  • Examine the code changes at a structural level, not line-by-line details
  • Focus on: component organization, dependency relationships, abstraction boundaries, data flow patterns, interface contracts, separation of concerns
  • Identify which parts of the design are being implemented or modified
  • Look for architectural anti-patterns or design violations

Read the full file on GitHub · 205 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 · 205 lines · 423 tokens per session scan A d3fdcab6f920

Subscribe to this mod's changes

architecture-reviewer is an agent published in the GitHub repository microsoft/Agent365-dotnet (29 stars, last pushed 1mo ago), licensed MIT. It adds 423 tokens to every session and 2,188 once invoked, about $0.0021 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to architecture-reviewer, differing in 18 lines, and is treated as a copy.