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 divyanshu-iitian/agent-website-design-skills --skill web-design-systemgit clone --depth 1 https://github.com/divyanshu-iitian/agent-website-design-skillsWrote 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/divyanshu-iitian/agent-website-design-skills/web-design-system)<a href="https://agentmods.dev/skills/divyanshu-iitian/agent-website-design-skills/web-design-system"><img src="https://agentmods.dev/badge/skills/divyanshu-iitian/agent-website-design-skills/web-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/divyanshu-iitian/agent-website-design-skills/web-design-system"><img src="https://agentmods.dev/badge/skills/divyanshu-iitian/agent-website-design-skills/web-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 | $0.00055 | $0.00612 |
| Opus 5.5 | $0.00022 | $0.00245 |
| Sonnet 5.5 | $0.00011 | $0.00122 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
web-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 1mo 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Design System
Build the smallest system that makes the product more coherent. Favor semantic contracts that components can use over a large inventory of decorative values.
Choose the Mode
- Extract when the product is visually coherent but undocumented.
- Reconcile when multiple patterns conflict.
- Create when a new product has no established UI language.
- Extend when a feature needs states or components the system lacks.
Workflow
- Inspect the framework, CSS strategy, theme files, primitives, component library, icon set, and representative screens.
- Inventory repeated values and patterns. Separate intentional variation from accidental drift.
- Map raw values to semantic roles before changing code. Example:
blue-600->action-primary, not "replace every blue." - Define the minimum token layers:
- foundations: color, type, spacing, radius, border, shadow, motion;
- semantic tokens: background, surface, text, border, action, focus, and status;
- component tokens only where a component genuinely needs them.
- Specify component anatomy, variants, sizes, and state behavior. Include content constraints, not only appearance.
- Define responsive behavior and density rules without inventing device-specific duplicates.
- Encode accessibility defaults: semantic elements, names, labels, focus-visible, keyboard behavior, contrast, errors, target size, and reduced motion.
- Implement inside the existing styling mechanism. Avoid parallel token systems.
- Migrate one representative component or screen and remove superseded values when safe.
- Verify light/dark themes, core states, narrow/wide layouts, and at least one realistic content stress case.
System Rules
- Name tokens by purpose, not by current appearance.
- Keep primitive escape hatches available, but make the correct path easier.
- Do not force every region into a card.
- Do not encode status through color alone.
- Keep component APIs small; prefer composition over variant explosions.
- Preserve established patterns unless they harm usability, accessibility, or maintainability.
- Document decisions where future contributors would otherwise recreate the inconsistency.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 56 lines · 55 tokens per session scan A d0ca7aed0027
web-design-system is a skill published in the GitHub repository divyanshu-iitian/agent-website-design-skills (4 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 612 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
brand-visual-language
Shape language across type, radius and icons carries brand personality. Use when starting a design system, picking icons or radius tokens, or reviewing visual consistency.
loading-states-and-perceived-performance
Spinners, skeletons and staggered reveals that manage wait times. Use when designing loading states, async data or the feel of a slow interface.
micro-interactions
Small purposeful animations — toggles, animated icons, success moments. Use when designing interactive feedback, success states or loaders.
elevation-and-depth
Shadows and layering that lift elements above the surface. Use when designing cards, dropdowns, modals, tooltips or any floating element.
motion-and-storytelling
Disney's animation principles and cinematic technique applied to UI motion. Use when designing transitions, scroll animations or onboarding motion.
responsive-paradigms
Mobile, tablet and desktop are different paradigms, not one layout scaled. Use when designing responsive layouts or deciding what each breakpoint shows.