claude-soul: Command for Claude Code

.claude/commands/system-design.md

system-design is a command for Claude Code from tomdwipo/claude-soul. It costs 0 tokens per session (1,890 once invoked), scanned A, original, MIT.

A system-design command that creates an architecture document with before-and-after ASCII diagrams. It describes how a requested software change should be shaped and why, before implementation is broken into coding steps.

In plain words
What is it for?
Use it to design a feature from the actual codebase, either as a chat response or as a Markdown file ready for a later implementation breakdown.
Why use it?
It gives developers a grounded design reference and makes the effect of a change easier to compare with the current system.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

This is tomdwipo/claude-soul's own configuration. It tells Claude Code how to work on claude-soul itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-soul configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tomdwipo/claude-soul. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tomdwipo/claude-soul/main/.claude/commands/system-design.md
Clone the repo
git clone --depth 1 https://github.com/tomdwipo/claude-soul

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-design

README.md
[![agentmods](https://agentmods.dev/badge/commands/tomdwipo/claude-soul/system-design/github.svg)](https://agentmods.dev/commands/tomdwipo/claude-soul/system-design)
Your own site
<a href="https://agentmods.dev/commands/tomdwipo/claude-soul/system-design"><img src="https://agentmods.dev/badge/commands/tomdwipo/claude-soul/system-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.

agentmods 80×15 button for system-design

Your own site · 80×15
<a href="https://agentmods.dev/commands/tomdwipo/claude-soul/system-design"><img src="https://agentmods.dev/badge/commands/tomdwipo/claude-soul/system-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,890 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01890
Opus 5 $0.00000 $0.00945
Sonnet 5 $0.00000 $0.00378
Haiku 4.5 $0.00000 $0.00189

Measured 9d ago against content hash 0f9da09391ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 9d 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/commands/system-design.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

system-design Command

Produce a detailed system design for $ARGUMENTS using ASCII diagrams only (no Mermaid, no images — per workspace CLAUDE.md), with BEFORE/AFTER so the change is obvious. This is the architecture artifact ("what it is shaped like + why"), the upstream input to /breakdown-design (which turns it into step-by-step code). Keep them paired: same feature, same folder.

think hard. Ground every claim in the actual codebase (read the files first — see §Lookup First). follow YAGNI — design only what the goal needs; no speculative components or dead structure.

Output mode — ASK FIRST (this is the whole point of this command)

Parse $ARGUMENTS for an explicit mode flag:

  • --chat (or the word chat) → render the full design in chat only, write no file.
  • --file (or the word file/md) → write the design to a markdown file (see §File Location), then post a short summary in chat + the handoff line.

If no mode flag is present, ask the user ONCE with AskUserQuestion:

"Where should the system design go?" — options: Chat only / Save to .md file (ready for /breakdown-design).

Do not proceed until the mode is known. Everything else (the design itself) is identical in both modes — only the destination differs.

File Location (when mode = file)

Mirror /breakdown-design exactly so the two artifacts sit side by side in one feature folder:

.docs/YYYY/MM/DD/{NN}-{Feature-Spec}/{Feature-Spec}-system-design.md
  • YYYY/MM/DD = today (from the session date).
  • {NN} = next free 2-digit number in that day's folder (e.g. existing up to 13-… → use 14). Reuse the SAME {NN}-{Feature-Spec} folder if it already exists for this feature, so the later {Feature-Spec}-implementation-plan.md from /breakdown-design lands in the same folder.
  • {Feature-Spec} = short Title-Case-Hyphenated name you infer from $ARGUMENTS.
  • After writing, print the path + a one-line handoff: Next: /breakdown-design <feature> so the user can generate the implementation plan from this design.

Read the full file on GitHub · 138 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. 9d ago First seen · 138 lines · 0 tokens per session scan A 0f9da09391ec

Subscribe to this mod's changes

system-design is a command published in the GitHub repository tomdwipo/claude-soul (24 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,890 tokens. 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.