system-design

system-design is a command for coding agents from Ashfaqbs/software-dev-ai-claude-toolkit. It costs 6 tokens per session (377 once invoked), scanned A, original, MIT.

A guided discussion tool for planning how a software system should work, including its components, data, APIs, scaling, and reliability. It can also represent the design with text diagrams.

In plain words
What is it for?
Use it to plan a new service or application, compare architecture and database choices, design APIs, and think through performance, scaling, and failures.
Why use it?
It helps turn a broad system-design problem into smaller questions, so important requirements and failure risks are less likely to be missed.

Command

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 commands/ashfaqbs/software-dev-ai-claude-toolkit/system-design
Clone the repo
git clone --depth 1 https://github.com/Ashfaqbs/software-dev-ai-claude-toolkit

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-design

README.md
[![agentmods](https://agentmods.dev/badge/commands/ashfaqbs/software-dev-ai-claude-toolkit/system-design.svg)](https://agentmods.dev/commands/ashfaqbs/software-dev-ai-claude-toolkit/system-design)
Your own site
<a href="https://agentmods.dev/commands/ashfaqbs/software-dev-ai-claude-toolkit/system-design"><img src="https://agentmods.dev/badge/commands/ashfaqbs/software-dev-ai-claude-toolkit/system-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 377 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 $0.00006 $0.00377
Opus 5 $0.00003 $0.00188
Sonnet 5 $0.00001 $0.00075
Haiku 4.5 $0.00001 $0.00038

Measured 4d ago against content hash 5dcf37454d0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

system-design 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 4d 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.

commands/system-design.md · 48 lines

What it actually says

System Design

Help me think through the system design for: $ARGUMENTS

Framework

Walk through these areas step by step. Ask me clarifying questions at each step before moving on.

1. Requirements

  • What are the functional requirements?
  • What are the non-functional requirements (latency, throughput, availability, consistency)?
  • What scale are we designing for? (users, requests/sec, data volume)

2. High-Level Architecture

  • What are the main components/services?
  • How do they communicate (sync REST/gRPC vs async Kafka/queues)?
  • Draw the architecture using text diagrams.

3. Data Design

  • What data needs to be stored?
  • SQL vs NoSQL decisions for each entity (and why).
  • Schema design, indexing strategy, partitioning/sharding if needed.

4. API Design

  • Key endpoints between services and to clients.
  • Authentication and authorization approach.

5. Scaling & Performance

  • Where are the bottlenecks?
  • Caching strategy (what, where, TTL, invalidation).
  • Database read replicas, connection pooling, query optimization.
  • Horizontal scaling approach.

6. Reliability

  • Single points of failure and how to eliminate them.
  • Failure modes and graceful degradation.
  • Monitoring, alerting, circuit breakers.

Rules

  • Explain trade-offs for every decision (e.g., "CP vs AP", "SQL vs NoSQL for this use case").
  • Use real numbers when estimating (requests/sec, storage in GB, latency in ms).
  • Reference technologies I know: Spring Boot, FastAPI, PostgreSQL, MongoDB, Redis, Kafka, Flink, Docker, K8s.
  • This is a learning exercise — teach me the reasoning, not just the answer.
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. 4d ago First seen · 48 lines · 6 tokens per session scan A 5dcf37454d0e

Subscribe to this mod's changes

system-design is a command published in the GitHub repository Ashfaqbs/software-dev-ai-claude-toolkit (24 stars, last pushed 6mo ago), licensed MIT. It adds 6 tokens to every session and 377 once invoked, about $0.0000 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.