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.
npx skills add navraj007in/architecture-cowork-plugin --skill design-systemgit 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/skills/navraj007in/architecture-cowork-plugin/design-system)<a href="https://agentmods.dev/skills/navraj007in/architecture-cowork-plugin/design-system"><img src="https://agentmods.dev/badge/skills/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/skills/navraj007in/architecture-cowork-plugin/design-system"><img src="https://agentmods.dev/badge/skills/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 | $0.00070 | $0.03002 |
| Opus 5 | $0.00035 | $0.01501 |
| Sonnet 5 | $0.00014 | $0.00600 |
| Haiku 4.5 | $0.00007 | $0.00300 |
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 8d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill generates distinctive, production-grade design systems that are derived from architecture context — not random aesthetic choices. Every design decision traces back to the product domain, target audience, component library, and accessibility requirements defined in the SDL.
Reference files to load alongside this skill:
references/design-systems.md— component library presets, personality guide, domain defaults, sub-domain differentiationreferences/design-system-fonts.md— curated font pairing library by personality (49+ pairs including organic/retro/expressive/cinematic, rotation rules)references/design-system-patterns.md— dark mode tokens, gradient/texture recipes, motion timing values, layout archetype spatial specs, 8 unconventional layout patterns with CSSreferences/design-system-creative.md— 4 creative personalities (organic, retro, expressive, cinematic), consumer/creative domain defaults, personality × domain quick guide
The user has an SDL blueprint. This skill fills, refines, or validates the design section and produces actionable design artifacts.
Design Thinking — Context-Driven
Before making any design choice, ground it in the SDL:
- Read the SDL — extract
solution.name,solution.description, frontend components, target audience, product domain - Derive personality — map domain + audience to a design personality:
- Fintech / Banking → corporate or editorial
- Healthcare → minimal
- E-commerce → playful or bold (B2C); corporate (B2B); luxury (D2C brand)
- Education → minimal or playful
- Developer tools → brutalist or minimal
- Enterprise SaaS → corporate
- Creative / Media → editorial or expressive
- Real estate → luxury
- Kids / Family → playful
- AI / ML → minimal
- Wellness / Nature / Food (artisan) → organic
- Music / Vintage / Craft → retro or cinematic
- Creative studio / Agency / Fashion (youth) → expressive
- Film / Gaming / Luxury experience → cinematic
- Personal portfolio (creative) → expressive or minimal
- Restaurant (fine dining) → luxury or organic
- Non-profit → minimal or editorial
- When unsure: read
references/design-system-creative.mdpersonality × domain quick guide
- Derive palette — domain-appropriate colors, NEVER indigo/purple as default:
- Fintech → emerald or teal
- Healthcare → sky or cyan
- E-commerce → orange or rose
- Developer tools → green or lime
- Enterprise → blue or slate
- Creative → violet or fuchsia
- See
design-systems.mdreference for full domain mapping
- Derive layout archetype — from component types in SDL:
- Admin/CRM/Dashboard frontends →
dashboard(sidebar + header + content) - Marketing/Landing pages (standard) →
marketing(hero + sections + footer) - Content-heavy apps →
editorial(wide content + typographic hierarchy) - SaaS with auth →
saas(auth layout + dashboard + settings) - Mobile-first web →
app-shell(top nav + responsive content) - Creative/consumer sites — choose an unconventional layout from
references/design-system-patterns.md:- Portfolio, brand contrast →
split-screen - Feature showcase, app launch →
bento-grid - Music artist, film, narrative →
full-bleed-panels - Product storytelling, process →
sticky-scroll - Event, fashion, bold sections →
diagonal - Gallery, timeline, portfolio →
horizontal-scroll - Agency, fashion, type-driven →
typography-forward - Blog, news, lookbook →
magazine-grid
- Portfolio, brand contrast →
- Can combine: e.g.
full-bleed-panelsfor hero +bento-gridfor features +magazine-gridfor content
- Admin/CRM/Dashboard frontends →
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.
- 8d ago First seen · 276 lines · 70 tokens per session scan A 8af74695e9f4
design-system is a skill published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 3,002 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
river-review-architecture
An architecture-review guide that checks whether software design decisions, system boundaries, and data models fit together consistently. An architecture review examines the structure and dependencies of a system.
cognitive-interface-audit
Comprehensive cognitive interface audit with two modes and a single tier. Planning mode designs task models, user expertise mapping, and error tolerance strategy. Audit mode evaluates mental model alignment (Norman's Gulfs), consistency (Gestalt), error tolerance (Wood 7-layer defense), cognitive load (NASA-TLX…
Architecture Boundaries & Dependencies
Ensure architecture/design docs define clear boundaries, ownership, dependency direction, and change impact to avoid tight coupling.
Architecture Diagrams Readiness
Ensure architecture diagrams are readable, consistent with text, and clear on scope, boundaries, and data flow.
Architecture Traceability & Consistency
Ensure design changes stay consistent across ADRs, diagrams, and specs; decisions are traceable; and drift is explicitly managed.
uiux
Use when deciding how the product's UI should look and how its UX should behave, from the mockup and logic docs - visual direction, design system, and per-screen design chapters via an interview, using capstone's own vendored design method.