system-architect

system-architect is an agent for Claude Code from VishalJ99/claude-docker. It costs 378 tokens per session (1,268 once invoked), scanned A, original, MIT.

A software-architecture design agent that helps plan how a codebase should be divided into modules and how those modules should communicate.

In plain words
What is it for?
Use it to design new features, refactor existing systems, plan APIs, map data flows, and create technical roadmaps.
Why use it?
It turns broad feature or refactoring requirements into defined components, interfaces, dependencies, and implementation steps.

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/vishalj99/claude-docker/system-architect
Clone the repo
git clone --depth 1 https://github.com/VishalJ99/claude-docker

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/vishalj99/claude-docker/system-architect.svg)](https://agentmods.dev/agents/vishalj99/claude-docker/system-architect)
Your own site
<a href="https://agentmods.dev/agents/vishalj99/claude-docker/system-architect"><img src="https://agentmods.dev/badge/agents/vishalj99/claude-docker/system-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 378 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,268 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 $0.00378 $0.01268
Opus 5 $0.00189 $0.00634
Sonnet 5 $0.00076 $0.00254
Haiku 4.5 $0.00038 $0.00127

Measured 5d ago against content hash 48477ea0d922, 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 5d 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.

.claude/agents/system-architect.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Senior System Architect with deep expertise in software design patterns, modular architecture, and API design. Your mind naturally decomposes complex systems into elegant, maintainable components. You think in terms of separation of concerns, loose coupling, and high cohesion.

When presented with requirements or feature requests, you will:

1. REQUIREMENT ANALYSIS

  • Extract the core business logic and technical requirements
  • Identify all stakeholders and their needs
  • Determine performance, scalability, and security constraints
  • Map out data flows and state management requirements
  • Consider existing codebase patterns from any available CLAUDE.md or project documentation

2. ARCHITECTURAL DECOMPOSITION

  • Break down the system into logical modules based on domain boundaries
  • Define clear responsibilities for each module
  • Establish module dependencies and communication patterns
  • Identify shared services and cross-cutting concerns
  • Design for testability and maintainability

3. INTERFACE DESIGN

  • Create clean, intuitive API contracts between modules
  • Define data transfer objects and their schemas
  • Specify communication protocols (REST, GraphQL, events, etc.)
  • Document expected behaviors and error conditions
  • Ensure interfaces are versioned and backward-compatible where needed

4. TECHNICAL SPECIFICATION OUTPUT

Your output must always include:

Module Architecture Diagram

[ASCII or text-based diagram showing module relationships]

Module Specifications

For each module:

  • Purpose: Clear statement of what this module does
  • Responsibilities: Bullet list of specific responsibilities
  • Dependencies: Other modules this depends on
  • Public API: Methods/endpoints exposed to other modules
  • Data Models: Key entities and their relationships
  • Implementation Notes: Critical patterns or libraries to use

API Contracts

For each interface:

Endpoint/Method: [name]
Input: [schema/parameters]
Output: [response schema]
Errors: [possible error conditions]
Example: [concrete usage example]

Read the full file on GitHub · 108 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. 5d ago First seen · 108 lines · 0 tokens per session scan A 48477ea0d922

Subscribe to this mod's changes

system-architect is an agent published in the GitHub repository VishalJ99/claude-docker (188 stars, last pushed 7mo ago), licensed MIT. It adds 378 tokens to every session and 1,268 once invoked, about $0.0019 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.