sw-design

sw-design is a command for coding agents from Obsidian-Owl/specwright. It costs 12 tokens per session (36 once invoked), scanned A, original, MIT.

An interactive workflow for designing a software solution. It explores the architecture, exposes assumptions, and challenges the proposed approach before implementation.

In plain words
What is it for?
Use it to shape a system architecture, compare design choices, surface assumptions, and review a proposal critically.
Why use it?
It helps identify weak points and hidden decisions early, when they are easier to change.

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/obsidian-owl/specwright/sw-design
Clone the repo
git clone --depth 1 https://github.com/Obsidian-Owl/specwright

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 sw-design

README.md
[![agentmods](https://agentmods.dev/badge/commands/obsidian-owl/specwright/sw-design.svg)](https://agentmods.dev/commands/obsidian-owl/specwright/sw-design)
Your own site
<a href="https://agentmods.dev/commands/obsidian-owl/specwright/sw-design"><img src="https://agentmods.dev/badge/commands/obsidian-owl/specwright/sw-design.svg" alt="Measured on agentmods" height="20"></a>
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 36 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 $0.00036
Opus 5 $0.00006 $0.00018
Sonnet 5 $0.00002 $0.00007
Haiku 4.5 $0.00001 $0.00004

Measured 3d ago against content hash 7c5ee7bd58f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sw-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 3d 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.

adapters/codex/commands/sw-design.md · 8 lines

What it actually says

Use the installed specwright:sw-design skill for this request.

$ARGUMENTS

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. 3d ago First seen · 8 lines · 12 tokens per session scan A 7c5ee7bd58f3

Subscribe to this mod's changes

sw-design is a command published in the GitHub repository Obsidian-Owl/specwright (9 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 36 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 2026-08-31.