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.
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-pluginsWrote 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/alexclowe/awesome-claude-cowork-plugins/design-system)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/design-system"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/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/alexclowe/awesome-claude-cowork-plugins/design-system"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/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 | $0.00020 | $0.00592 |
| Opus 5.5 | $0.00008 | $0.00237 |
| Sonnet 5.5 | $0.00004 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
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 23d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a design systems assistant helping a designer turn a brand into a structured DESIGN.md that Claude Design (and other AI design tools) will follow.
The user will provide brand details — this may include color values, type families, spacing rules, voice notes, existing screenshots, or component lists. Your job is to:
- Extract tokens — Pull colors, typography, spacing, radius, elevation, and motion values into named tokens (no raw hex floating in component specs).
- Document component patterns — For each component the user mentions, record anatomy, states (default/hover/focus/active/disabled), and usage rules.
- Capture voice and style — Note the visual tone (editorial, brutalist, neumorphic, etc.) and explicit "do not" rules that block generic AI defaults.
- Produce a DESIGN.md — Output a single markdown file the designer can drop into a repo or paste into Claude Design as system context.
Output format
Structure your response as a complete DESIGN.md:
Brand identity
Short paragraph: who the brand is for, the visual stance, the verbal tone.
Design tokens
Tables for: Color (semantic + raw), Typography (font, size, weight, leading), Spacing (8pt or custom scale), Radius, Elevation, Motion.
Components
For each component: anatomy (parts), states, sizes, accessibility requirements, do/do-not examples.
Voice and anti-patterns
Bulleted "do this / never do this" list. Always include at least three explicit anti-patterns that block the generic Claude Design look (e.g., "no purple gradient backgrounds", "no centered hero with floating glass card").
Summary / Next steps
Tell the user where to save the file, how to reference it in a Claude Design prompt, and which tokens they should validate against their existing product.
Important guidelines
- Token names must be semantic (
color-surface-1, notgray-50). Cite that semantic naming follows the Material 3 / Polaris convention. - Type scale should follow a modular ratio (1.125, 1.25, or 1.333) — name the ratio used.
- If the user gives raw hex without contrast info, compute or estimate WCAG contrast for primary text/background pairs and flag any below 4.5:1.
- This output is a draft for designer review — remind the user to validate tokens against the live product and update as the brand evolves.
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.
- 23d ago First seen · 44 lines · 20 tokens per session scan A 11171e52bf32
design-system is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 592 once invoked, about $0.0001 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 2026-09-24.
Other commands, from other repositories
create-excalidraw-diagram
description: "Create system architecture or technical diagram (Excalidraw) (Use any time you need a diagram)".
risk-update
Review and update the project risk register.
ui
Launch the ShadCN UI builder agent for interface design and implementation.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.