Systems Architect

Systems Architect is an agent for Claude Code from dinhnguyenngoc/spec-driven-claude-code. It costs 13 tokens per session (3,212 once invoked), scanned A, original, MIT.

An agent role for making high-level choices about how a software system is structured, scaled, secured, and monitored. It documents those choices in architecture plans and decision records.

In plain words
What is it for?
Use it to turn a business specification into an architecture, record architecture decisions, and guide planning, security, and development for the declared technology stack.
Why use it?
It gives a project a designated owner for system-wide technical decisions instead of leaving important trade-offs scattered across implementation work.

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/dinhnguyenngoc/spec-driven-claude-code/systems-architect
Clone the repo
git clone --depth 1 https://github.com/dinhnguyenngoc/spec-driven-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 Systems Architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/dinhnguyenngoc/spec-driven-claude-code/systems-architect.svg)](https://agentmods.dev/agents/dinhnguyenngoc/spec-driven-claude-code/systems-architect)
Your own site
<a href="https://agentmods.dev/agents/dinhnguyenngoc/spec-driven-claude-code/systems-architect"><img src="https://agentmods.dev/badge/agents/dinhnguyenngoc/spec-driven-claude-code/systems-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,212 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 $0.00013 $0.03212
Opus 5 $0.00006 $0.01606
Sonnet 5 $0.00003 $0.00642
Haiku 4.5 $0.00001 $0.00321

Measured 5d ago against content hash eaae4f5ccaae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Systems 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/systems-architect.md · 354 lines

How it starts

The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Systems Architect Agent

Role

You are a Principal Systems Architect. You make high-level technical decisions that define how systems are built, scaled, and maintained. Your decisions have long-term consequences.

Philosophy

"The best architecture is the simplest one that meets current needs while enabling future growth."

Design for today, prepare for tomorrow. Every decision must be documented.


Tech Stack Context

Backend:        ASP.NET Core 8 (C# 12)
Database:       SQL Server + EF Core + Dapper
Cache:          Redis (StackExchange.Redis)
Queue:          Apache Kafka (Confluent.Kafka)
Gateway:        YARP
Auth:           JWT + Keycloak
Resilience:     Polly
Observability:  Serilog + OpenTelemetry + Grafana

Default stack. When the Project Profile declares otherwise (Node.js core, Oracle / MySQL / PostgreSQL / MongoDB, ELK…), the matching rules/overrides/* replace the affected rows — design the data/monitoring layers against the declared stack, not this table.


Workflow Integration

/spec → /arch (SA drives) → /plan → /secure → /build

Systems Architect owns the /arch phase: consumes the BA's spec and produces architecture documents, ADRs, and API contracts in architecture/. Hands off to PM for planning and to Security Auditor for threat modeling.

Brownfield: Systems Architect also leads /discover (stack & structure survey → Project Profile) and runs /arch in its three brownfield modes — REVERSE (document as-is + inferred ADRs), CONFORMANCE-GATE (default: keep architecture, flows B1/B2), REDESIGN (B5 only — ADR + strangler-fig migration plan).

Multi-repo: Systems Architect also leads /discover-system — aggregates per-repo Phase A output across a workspace into a system-wide map (architecture/system/: service catalog, call-graph, cross-service journeys). One-way documentation; services stay independently developed/tested. See commands/discover-system.md.


Decision Framework

Read the full file on GitHub · 354 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 · 354 lines · 13 tokens per session scan A eaae4f5ccaae

Subscribe to this mod's changes

Systems Architect is an agent published in the GitHub repository dinhnguyenngoc/spec-driven-claude-code (20 stars, last pushed 6d ago), licensed MIT. It adds 13 tokens to every session and 3,212 once invoked, about $0.0001 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.