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-visual-directiongit 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-visual-direction)<a href="https://agentmods.dev/skills/divyanshu-iitian/agent-website-design-skills/web-visual-direction"><img src="https://agentmods.dev/badge/skills/divyanshu-iitian/agent-website-design-skills/web-visual-direction/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-visual-direction"><img src="https://agentmods.dev/badge/skills/divyanshu-iitian/agent-website-design-skills/web-visual-direction.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 | $0.00052 | $0.00594 |
| Opus 5.5 | $0.00021 | $0.00238 |
| Sonnet 5.5 | $0.00010 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
web-visual-direction 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Visual Direction
Turn an ambiguous brief into one coherent visual system. Make choices that fit the product and can survive implementation; do not produce a mood-board-shaped list of adjectives.
Workflow
- Inspect the product brief and existing code, brand assets, screenshots, content, component library, and constraints. Preserve intentional brand equity.
- State the audience, their immediate task, and the feeling the interface should create in one sentence each.
- Choose one visual thesis with a useful tension, such as "editorial authority with operational speed." Explain why it fits.
- Select two or three relevant references. Extract principles - rhythm, contrast, framing, density - not surface decoration or copyrighted layouts.
- Decide the composition before styling details:
- identify the first viewport's focal point;
- define the grid, content width, density, and section rhythm;
- decide what intentionally breaks the grid, if anything.
- Define implementation-ready rules for typography, color, surfaces, borders, imagery, icons, and motion.
- Express the direction as a small token set and component implications. Reuse the project's existing styling system.
- Implement one representative viewport or component when implementation is in scope.
- Verify the direction at mobile and desktop widths. Remove choices that weaken comprehension, hierarchy, performance, or accessibility.
Decision Rules
- Lead with the real product, work, place, person, object, or outcome.
- Prefer a memorable structural idea over decorative effects.
- Match density to the job: operational interfaces are compact; narrative brand pages can breathe.
- Use typography with a reason. Do not ban or choose a font only because it is fashionable.
- Use cards for meaningful grouping, not as the default container for every sentence.
- Treat gradients, glass, grain, glow, and oversized type as tools, not proof of design quality.
- Keep motion purposeful and respect reduced-motion preferences.
- Do not fabricate brand assets, customer logos, metrics, or product screenshots.
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 · 50 lines · 52 tokens per session scan A 399a4a7813c9
web-visual-direction is a skill published in the GitHub repository divyanshu-iitian/agent-website-design-skills (4 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 594 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
design-md
Author/validate/export Google's DESIGN.md token spec files.
design-dna
Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides…
component-family-consistency
Buttons, inputs, badges and pills share radius, colour logic, shadow, border and spacing. Use when building or reviewing a component library.
extract-design
Extract colours, typography, spacing, components and W3C design tokens from a live website with Dembrandt. Use when you need a site's real tokens or want to seed a design system from it.
modular-scale-typography
Ratio-based type scale where every size relates to the others. Use when defining font sizes or type tokens, or when typography feels arbitrary.
data-display-and-selection
View modes, row selection, mass actions, sorting, filters, search and table patterns. Use when designing data tables, listings, file browsers or any collection.