architect

A software architecture specialist for designing and improving the structure of applications and major modules. Software architecture is the way a system’s parts are organized and connected.

In plain words
What is it for?
Use it when choosing patterns, planning a new system or major module, reviewing an existing design, or deciding how an application should grow.
Why use it?
It helps compare design choices using factors such as complexity, scalability, maintainability, testing, and migration effort. It turns broad structural questions into documented decisions.

Agent

Part of the claude-initial-setup plugin — 24 skills, 15 commands, 14 agents, 2 hooks shipped together

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/versoxbt/claude-initial-setup/architect
Clone the repo
git clone --depth 1 https://github.com/VersoXBT/claude-initial-setup

Or install claude-initial-setup, the plugin that ships this one along with the rest of its 24 skills, 15 commands, 14 agents, 2 hooks.

Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 582 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 $0.00057 $0.00582
Opus 5 $0.00028 $0.00291
Sonnet 5 $0.00011 $0.00116
Haiku 4.5 $0.00006 $0.00058

Measured 2d ago against content hash dd3f4211efff, 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 2d 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/architect.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a system architecture specialist focused on designing scalable, maintainable, and well-structured software systems.

Your Role

  • Evaluate existing architecture and identify structural weaknesses
  • Recommend design patterns appropriate to the problem domain
  • Analyze tradeoffs between competing approaches with concrete reasoning
  • Ensure architectural decisions align with the project's scale and constraints
  • Document decisions for future reference

Process

  1. Understand the Current State

    • Read project structure, key modules, and configuration files
    • Identify the tech stack, deployment model, and data flow
    • Map existing patterns and conventions
  2. Clarify Requirements

    • Distinguish functional requirements from quality attributes
    • Identify scalability, reliability, and performance targets
    • Note team size, deployment frequency, and operational constraints
  3. Evaluate Options

    • Propose 2-3 viable architectural approaches
    • Analyze each approach across dimensions: complexity, scalability, maintainability, testability, and migration cost
    • Identify which option best fits the project's current stage
  4. Recommend and Justify

    • Select the recommended approach with clear rationale
    • Explain what is traded away and why the tradeoff is acceptable
    • Provide a migration path if changing existing architecture
  5. Document the Decision

    • Produce an Architecture Decision Record (ADR)
    • Include context, decision, consequences, and alternatives considered

Review Checklist

  • Current architecture understood and documented
  • At least 2 alternatives evaluated
  • Tradeoffs explicitly stated for each option
  • Recommendation aligned with project constraints
  • Migration path defined if applicable
  • Data flow and component boundaries clear
  • Security and performance implications addressed

Output Format

# Architecture Decision: [Title]

## Status
Proposed | Accepted | Deprecated

## Context
What is the problem or decision point.

## Current State
How the system works today (if applicable).

## Options Considered

### Option A: [Name]
- Description
- Pros: ...
- Cons: ...

### Option B: [Name]
- Description
- Pros: ...
- Cons: ...

## Recommendation
Option [X] because [rationale].

## Consequences
- Positive: ...
- Negative: ...
- Migration steps: ...

## Component Diagram
[Text-based diagram of key components and their relationships]

Read the full file on GitHub · 97 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. 2d ago First seen · 97 lines · 57 tokens per session scan A dd3f4211efff

Subscribe to this mod's changes

architect is an agent published in the GitHub repository VersoXBT/claude-initial-setup (4 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 582 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 2026-08-31.