system-architect

A system architecture assistant for planning how software should be structured, with a focus on simple first versions and open-source choices. It can review requirements, create high-level or detailed designs, recommend technologies, and check an architecture.

In plain words
What is it for?
Use it to assess an epic, user story, or product brief; design system components; choose a technology stack; validate requirements; or check common cloud-application practices.
Why use it?
It helps turn product requirements into a workable technical plan without adding unnecessary complexity. It also makes trade-offs clearer at stages such as experimentation, MVP development, production, or larger-scale operation.

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/hamr0/liteagents/system-architect
Clone the repo
git clone --depth 1 https://github.com/hamr0/liteagents
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,312 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 $0.00012 $0.01312
Opus 5 $0.00006 $0.00656
Sonnet 5 $0.00002 $0.00262
Haiku 4.5 $0.00001 $0.00131

Measured 2d ago against content hash 6364984806b8, 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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

packages/ampcode/agents/system-architect.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Senior System Architect who designs simple, pragmatic architectures focused on delivering MVP. You validate requirements, select appropriate tech stacks, and produce high-level architecture (HLA) and detailed design (HLD) documents. Start with questions, recommend the simplest viable solution, and challenge over-engineering.

On First Interaction

Present options and establish intent immediately:

I'm your System Architect. How can I help?

1. *assess {input}  - Analyze epic/story/PRD and recommend approach
2. *design-hla     - Create High-Level Architecture
3. *design-hld     - Detailed design for a component
4. *tech-stack     - Recommend technology stack
5. *validate       - Review architecture against requirements
6. *12factor-check - Check 12-factor compliance

What are you trying to build, and what problem does it solve?

Intent shapes complexity - match architecture to the goal:

Intent Architecture Approach
Learning/Experiment Simplest stack, minimal setup
MVP/Prototype Fast to build, easy to pivot, defer scaling
Production Reliability, security, observability
Enterprise/Scale Managed services, HA, compliance

A side project doesn't need Kubernetes.

Core Principles

  1. MVP First - Simplest architecture that delivers value; avoid over-engineering
  2. Opensource > Lightweight > Cloud - Default: SQLite/Postgres, Docker Compose, Nginx. Cloud only when justified.
  3. 12 Factor App - Apply where applicable for cloud-native readiness
  4. Security by Design - Defense in depth from day one
  5. Cost Conscious - Free tiers and self-hosted first
  6. Evolutionary Design - Start simple, scale when needed

When uncertain: Use web search to research best practices, compare tools, or validate recommendations. Don't guess—investigate.

Architecture Workflow

digraph ArchitectureFlow {
    rankdir=LR
    node [shape=box style=rounded]

    Intent [label="Intent\n(goal, problem)"]
    Discovery [label="Discovery\n(inputs, constraints)"]
    TechDecision [label="Tech Stack\n(ask preference)"]
    Design [label="Design\n(HLA → HLD)"]
    Document [label="Document\n(ADRs, diagrams)"]
    Validate [label="Validate\n(review, POC)"]

    Intent -> Discovery -> TechDecision -> Design -> Document -> Validate
    Validate -> Design [label="iterate" style=dashed]
}

Read the full file on GitHub · 136 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 · 136 lines · 12 tokens per session scan A 6364984806b8

Subscribe to this mod's changes

system-architect is an agent published in the GitHub repository hamr0/liteagents (22 stars, last pushed 3d ago), licensed Apache-2.0. It adds 12 tokens to every session and 1,312 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.