Borrowing it
Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.claude/commands/define-design-system.mdgit clone --depth 1 https://github.com/bredmond1019/claude-sdk-rsWrote 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.
[](https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/define-design-system)<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/define-design-system"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/define-design-system/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.
<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/define-design-system"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/define-design-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.03440 |
| Opus 5.5 | $0.00000 | $0.01376 |
| Sonnet 5.5 | $0.00000 | $0.00688 |
| Haiku 4.5 | $0.00000 | $0.00344 |
Grade A, and why
define-design-system 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Define Design System — establish the tokens, components and rules a new UI is built from.
Variables
$ARGUMENTS — what is being built, plus flags. Example: "client booking portal --surface web --slug acme-portal"
| Flag | What it does |
|---|---|
--surface <web|mobile|tui|desktop> |
Repeatable. Each gets its own stack and component inventory |
--slug <name> |
Output to planning/<name>/design-system.md + the artifacts it names |
--from <path> |
A brand guide, a client's existing site, a reference product to derive from |
--house |
Adopt the practice's default stack without re-deciding it (step 2) |
Purpose
For a UI that does not exist yet — a new client project, a new side project, a new app.
Produces the thing the first screen is built from: design tokens, a Tailwind/theme config, a justified component inventory, the icon set, and the rules that keep screen twenty consistent with screen one. Then it proves the system by building one real screen with it, and emits a polish standard so later work can be reviewed.
This is the greenfield twin of
/define-polish-standard. That command reads a running product and writes a rubric to judge it. This one has nothing to read and writes artifacts to build from. Do not merge them: their inputs, outputs, failure modes and proof steps all differ.Escalation trigger — check first. If the product already has a discernible system (a spacing scale in use, components being reused, a theme file), stop and use
/define-polish-standardinstead. Codify what exists; do not impose a second system beside it. Establishing a design system on a product that has one is a rewrite and needs approving as one.A new page or screen in an existing app needs neither command — it inherits the system and is reviewed against the existing polish standard. That is the common case; both commands are for the uncommon one.
Instructions
- If
$ARGUMENTSis empty, stop and ask what is being built and for which surfaces.
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.
- 11d ago First seen · 285 lines · 0 tokens per session scan A 454dcd92f47c
define-design-system is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,440 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 2026-10-26.
define-design-system compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| define-design-systembredmond1019/claude-sdk-rs | Command | 23 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| profilecathrynlavery/diagram-design | Command | 65k | 3d ago | MIT | A | 16 | Claude Code |
| erne-animateJubaKitiashvili/everything-react-native-expo | Command | 50 | 29d ago | MIT | A | 21 | Claude Code |
| ui-flow-reviewMRCalderon3D/everything-game-dev-code | Command | 104 | 28d ago | MIT | A | 15 | Claude Code |
| responsive-design-specialistimsaif/design-with-claude | Command | 11 | yesterday | MIT | A | 36 | Claude Code |
| design-auditw2ur/claude-code-setup | Command | 2 | 3d ago | MIT | A | 30 | Claude Code |
| ppt-image2-editable-rebuildwwe-dog/ppt-image2-editable-rebuild | Command | 204 | 5mo ago | Unlicense | A | 15 | Claude Code |