A command for working through a system-design problem step by step, from requirements and rough capacity estimates to architecture, trade-offs, failure cases, and diagrams. System design means planning how a software system's parts work together as it grows.

Use it for architecture discussions, design reviews, and system-design interview practice involving APIs, databases, caches, queues, scaling, reliability, and related building blocks.

It prevents jumping straight to an architecture without checking what the system must do, how much traffic it may handle, or where it could fail. It keeps the design discussion structured and collaborative.

design — Command for Claude Code by proyecto26/system-design-skills

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.

Clone the repo

git clone --depth 1 https://github.com/proyecto26/system-design-skills

Made for: Claude Code.

Or install system-design-skills, the plugin that ships this one along with the rest of its 22 skills, 1 command, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/proyecto26/system-design-skills/design/github.svg)](https://agentmods.dev/commands/proyecto26/system-design-skills/design)

Your own site

<a href="https://agentmods.dev/commands/proyecto26/system-design-skills/design"><img src="https://agentmods.dev/badge/commands/proyecto26/system-design-skills/design/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/proyecto26/system-design-skills/design"><img src="https://agentmods.dev/badge/commands/proyecto26/system-design-skills/design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 660 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.00660
Opus 5.5	$0.00016	$0.00264
Sonnet 5.5	$0.00008	$0.00132
Haiku 4.5	$0.00004	$0.00066

Measured 2mo ago against content hash 1e7b26e9b387, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 2mo 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/design.md · 23 lines

What it actually says

Run the system-design process for: $ARGUMENTS

Drive this as a collaborative design session using the system-design-skills plugin, following the GUIDE reasoning loop. Do not jump to a finished architecture.

Launch the orchestrator. Use the Task tool to run the system-design-orchestrator agent on the problem above. It loads the system-design skill (the method) and composes the building-block skills.
- If subagent launch is unavailable, run the loop inline yourself: invoke the system-design skill first, then route to building-block skills as each concern arises — invoke each skill, don't paraphrase it. The full catalog (the 20 building blocks, bottom-up layers) is the building-blocks index inside the system-design skill; reach for whichever fit, including the less-obvious ones (service-decomposition, dns, sequencer, blob-store, observability, distributed-logging, distributed-search, task-scheduling, sharded-counters) alongside the core (requirements-scoping, back-of-the-envelope, api-design, data-storage, caching, load-balancing, messaging-streaming, consistency-coordination, resilience-failure, content-delivery, scaling-evolution). For "monolith vs microservices / where are the service boundaries", that is service-decomposition.
Work the loop out loud: clarify requirements (functional / non-functional / out-of-scope) → estimate scale with numbers → propose a high-level design + API → articulate trade-offs (solves / worsens / when-to-change) per major choice → stress-test failure modes → iterate, pivoting the affected part when a constraint changes.
Ask a clarifying question whenever an answer is load-bearing (consistency model, single vs multi-region, sync vs async) and cannot be assumed safely. Treat the user as a collaborator, not an audience.
Capture & persist the running design with the system-design skill's design-doc template, write the settled artifacts to a file (suggest docs/design/<system>.md), and when it stabilizes render it with the architecture-diagram skill.
Score, then close. Rate the design with the quality bar + Quick Diagnostic in the system-design skill's references/failure-modes.md, state the weakest dimension, then name the current bottleneck and what would change at the next order of magnitude. Never claim the design is perfect.

If $ARGUMENTS is empty, ask the user what system they want to design (and at what rough scale) before starting.

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.

2mo ago First seen · 23 lines · 40 tokens per session scan A 1e7b26e9b387

Subscribe to this mod's changes

design is a command published in the GitHub repository proyecto26/system-design-skills (123 stars, last pushed 11d ago), licensed MIT. It adds 40 tokens to every session and 660 once invoked, about $0.0002 per session on Opus 5.5. 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.

Claude Code Planning claude-code-plugin claude-plugin claude-skills distributed-systems high-level-architecture

design next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
designproyecto26/system-design-skills	Command	123	11d ago	MIT	A	40	Claude Code
diagnose-underperformermarkifact/markifact-mcp	Command	57	8d ago	MIT	A	64	Claude Code
edit-meta-creativemarkifact/markifact-mcp	Command	57	8d ago	MIT	A	88	Claude Code
launch-meta-campaignmarkifact/markifact-mcp	Command	57	8d ago	MIT	A	36	Claude Code
launch-pmaxmarkifact/markifact-mcp	Command	57	8d ago	MIT	A	41	Claude Code
negative-keyword-sweepmarkifact/markifact-mcp	Command	57	8d ago	MIT	A	50	Claude Code
duck-offcentsandcode/rubber-duck	Command	15	2mo ago	MIT	A	8	Claude Code