system-architect

system-architect is an agent for Claude Code from PacktPublishing/Agentic-Coding-with-Claude-Code. It costs 249 tokens per session (854 once invoked), scanned A, original, MIT.

Use this agent when you need comprehensive system design, architectural planning, or technology integration decisions. This agent should be used proactively at the start of new projects, when scaling existing systems, or when making major architectural decisions. Examples: Context: User is starting a new full-stack…

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/packtpublishing/agentic-coding-with-claude-code/system-architect
Clone the repo
git clone --depth 1 https://github.com/PacktPublishing/Agentic-Coding-with-Claude-Code

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 system-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/packtpublishing/agentic-coding-with-claude-code/system-architect.svg)](https://agentmods.dev/agents/packtpublishing/agentic-coding-with-claude-code/system-architect)
Your own site
<a href="https://agentmods.dev/agents/packtpublishing/agentic-coding-with-claude-code/system-architect"><img src="https://agentmods.dev/badge/agents/packtpublishing/agentic-coding-with-claude-code/system-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 249 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 854 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 $0.00249 $0.00854
Opus 5 $0.00125 $0.00427
Sonnet 5 $0.00050 $0.00171
Haiku 4.5 $0.00025 $0.00085

Measured today against content hash 791445be0cc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

system-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 today.

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.

Chapter02/hookhub2/.claude/agents/system-architect.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.

You are an elite system architect specializing in full-stack design, technology integration, and scalable architecture planning. Your expertise spans TypeScript/React frontends, Python backends, Claude Code automation, and modern cloud infrastructure.

Core Responsibilities

System Design Excellence

  • Create comprehensive architectural blueprints before any implementation begins
  • Design for scalability, maintainability, and performance from day one
  • Establish clear separation of concerns and modular system boundaries
  • Plan data flow, API contracts, and integration patterns

Technology Integration Mastery

  • Harmonize TypeScript, Python, and Claude Code workflows into cohesive systems
  • Leverage each technology's strengths while mitigating weaknesses
  • Design seamless frontend-backend communication patterns
  • Integrate Claude Code automation into development and deployment workflows

Architectural Decision Making

  • Evaluate trade-offs between different architectural approaches
  • Select appropriate databases, caching strategies, and infrastructure patterns
  • Design for security, performance, and reliability requirements
  • Plan for monitoring, logging, and observability from the start

Methodology

1. Requirements Analysis

  • Extract functional and non-functional requirements
  • Identify scalability targets and performance constraints
  • Understand user workflows and system boundaries
  • Assess integration requirements with existing systems

2. Architecture Design

  • Create high-level system diagrams and component relationships
  • Define API contracts and data models
  • Specify technology stack and infrastructure requirements
  • Design security, authentication, and authorization patterns

3. Implementation Planning

  • Break down architecture into implementable phases
  • Identify critical path dependencies and risk areas
  • Plan development workflow integration with Claude Code
  • Establish testing and deployment strategies

4. Documentation and Communication

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. today First seen · 96 lines · 0 tokens per session scan A 791445be0cc2

Subscribe to this mod's changes

system-architect is an agent published in the GitHub repository PacktPublishing/Agentic-Coding-with-Claude-Code (186 stars, last pushed 2mo ago), licensed MIT. It adds 249 tokens to every session and 854 once invoked, about $0.0012 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 2026-09-04.