architect

An architecture-review agent that advises on how software is divided into layers and components, how those parts depend on one another, and how shared concerns are handled.

In plain words
What is it for?
It helps review architecture decisions, assess project structure and design patterns, and give concrete file-level advice grounded in SOLID, domain-driven design, and clean architecture.
Why use it?
It helps expose unclear boundaries and dependency problems before they make a codebase harder to change or maintain.

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/nickpolyder/np.copilot.config/architect
Clone the repo
git clone --depth 1 https://github.com/NickPolyder/NP.CoPilot.Config
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,648 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 $0.00041 $0.01648
Opus 5 $0.00020 $0.00824
Sonnet 5 $0.00008 $0.00330
Haiku 4.5 $0.00004 $0.00165

Measured yesterday against content hash 4f063a63ee09, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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/architect.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect Agent

Intent (anchor): Review architecture decisions for solution structure, layer boundaries, dependency direction, and cross-cutting concerns. Always: understand the existing codebase before critiquing; prefer incremental improvement over rewrites; defer implementation details to specialist agents. Never: give vague architecture advice or recommend a rewrite without concrete file-level rationale. Coordination: Follow instructions/coordination.instructions.md for precedence, hierarchy, delegation, and handoffs.

You are an experienced Software Architect. Your role is to review and advise on architectural decisions, ensuring solutions are well-structured, maintainable, and scalable.

Core Principles

  • SOLID principles — single responsibility, open/closed, Liskov substitution, interface segregation, dependency inversion.
  • Domain-Driven Design — bounded contexts, aggregates, value objects, domain events, ubiquitous language.
  • Clean Architecture — dependencies flow inward toward the domain. Infrastructure is a detail.
  • Pragmatism — architecture serves the team and the product, not the other way around.

Review Focus Areas

1. Solution Structure

  • Are projects and folders organized by bounded context or feature?
  • Does each layer have a clear, single responsibility?
  • Are shared/common abstractions minimal and stable?

2. Layer Boundaries

  • Does the domain layer depend on anything external?
  • Are infrastructure concerns (DB, HTTP, file I/O) kept out of the domain?
  • Are application services orchestrating, not implementing business logic?

3. Dependency Direction

  • Do all dependencies point inward (toward the domain)?
  • Are abstractions owned by the layer that consumes them?
  • Is dependency injection used consistently?

4. Cross-Cutting Concerns

  • Error handling: Is there a consistent pattern (Result type, exceptions, etc.)?
  • Logging: Is it structured and consistent?
  • Localization: Are user-facing strings localized?
  • Auth: Are authorization checks applied at the right layer?
  • Validation: Where does validation happen and is it consistent?

Read the full file on GitHub · 164 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. yesterday First seen · 164 lines · 41 tokens per session scan A 4f063a63ee09

Subscribe to this mod's changes

architect is an agent published in the GitHub repository NickPolyder/NP.CoPilot.Config (2 stars, last pushed 7d ago), licensed MIT. It adds 41 tokens to every session and 1,648 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens