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/navraj007in/architecture-cowork-pluginWrote 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/navraj007in/architecture-cowork-plugin/design-system)<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/design-system"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/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/navraj007in/architecture-cowork-plugin/design-system"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-plugin/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 | $0.00015 | $0.05712 |
| Opus 5 | $0.00008 | $0.02856 |
| Sonnet 5 | $0.00003 | $0.01142 |
| Haiku 4.5 | $0.00002 | $0.00571 |
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 12d 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 — 516 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect:design-system
Trigger
/architect:design-system
Purpose
Creates a complete, context-aware design system — palette, typography, motion language, component inventory, and design tokens — grounded in the product domain and target audience. Works at any stage: after wireframes (pre-blueprint), after blueprint, or as a standalone command. The scaffold phase consumes the output.
Workflow
Quick Navigation
| Phase | Steps |
|---|---|
| Setup | Step 1 · Step 1.5 |
| Analysis | Step 2 · Step 3 |
| Generation | Step 4 · Step 5 · Step 6 |
| Updates | Step 7 · Step 7.5 |
| Completion | Step 7.6 · Step 8 · Step 9 · Step 9.5 |
Step 1: Read Context
First, check for architecture-output/_state.json. If it exists, read it in full and extract:
project.nameandproject.description→ product name and domain contexttech_stack→ framework and component library choices already made (optional — may not exist yet)design→ if present and fully populated (personality + full palette + fonts), the design system was already set — use these values as the starting point rather than re-deriving from scratchpersonas→ target audience context; use instead of readinguser-personas.mdmvp_scope→ feature scope; informs which UI components are needed
Then, scan for wireframe output in architecture-output/wireframes/. If JSON wireframe files exist, read them to extract:
- Screen inventory (all screen names and layouts)
- Component patterns already decided (navbars, sidebars, modals, cards, forms)
- Application type hint (sidebar navigation → likely dashboard web app; bottom tabs → mobile; etc.)
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.
- 12d ago First seen · 516 lines · 15 tokens per session scan A 427856df7d4b
design-system is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 5,712 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.
Other commands, from other repositories
verify
Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.
anti-slop-designer
Use when a UI looks machine-made rather than decided. Violet gradients, glassmorphism everywhere, identical cards in a grid, untouched shadcn or Material defaults, emoji bullets, or copy stuffed with seamless and unlock.
theme
Switch between visual theme skins — OLED Black, Matrix, Claude Anthropic, Surprise Me.
stark-director
Use this command when the user asks Stark to go all out, raise design quality broadly, use libraries well, make a UI feel actually designed, or coordinate research, typography, motion, usability, implementation, and QA in one pass.
data-visualization-specialist
Use when a chart misleads or confuses. Wrong chart type for the data, a truncated axis, colour that encodes nothing, unreadable labels on mobile, or charts no screen reader can use.
motion-designer
Use when animation feels wrong. Transitions too slow or too bouncy, motion with no purpose, blanket transitions on every property, no reduced-motion support, or animation that drops frames.