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 imsaif/design-with-claude --skill design-with-claudegit clone --depth 1 https://github.com/imsaif/design-with-claudeWrote 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/imsaif/design-with-claude/design-with-claude)<a href="https://agentmods.dev/skills/imsaif/design-with-claude/design-with-claude"><img src="https://agentmods.dev/badge/skills/imsaif/design-with-claude/design-with-claude/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/imsaif/design-with-claude/design-with-claude"><img src="https://agentmods.dev/badge/skills/imsaif/design-with-claude/design-with-claude.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 | $0.00000 | $0.01327 |
| Opus 5 | $0.00000 | $0.00664 |
| Sonnet 5 | $0.00000 | $0.00265 |
| Haiku 4.5 | $0.00000 | $0.00133 |
Grade A, and why
design-with-claude 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 11d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design with claude
A product designer inside your terminal. Start by measuring, then route to the specialist who fixes what you measured.
Start here: measure before you design
npx dwic-audit
Deterministic scan of the current project across 8 categories — color, typography, spacing, accessibility, forms, navigation, motion, copy. WCAG contrast math, token parsing, markup heuristics. Writes .dwic/audit-<date>.md and exits non-zero on errors, so it works in CI. Nothing leaves the machine.
Run this first when the request is vague ("improve our design", "is this any good?"). The findings tell you which specialist to invoke instead of guessing.
Audit finding → specialist:
| Audit category | Invoke |
|---|---|
| Color / contrast AA fails | /color-specialist |
| Typography off-scale | /typography-specialist |
| Spacing inconsistency | /spacing-layout-specialist |
| Accessibility failures | /accessibility-specialist |
| Unlabeled inputs, no fieldset | /form-designer |
| Navigation gaps | /navigation-specialist |
transition: all, no reduced-motion |
/motion-designer |
| Weak CTA, jargon | /content-strategist |
Or hand the whole report to /design-triage — it reads the newest .dwic/audit-*.md, ranks the findings by what costs most to leave broken (not by the audit's own severity order), and works the fix list in order. Use it when the audit returns a pile rather than one obvious problem.
Not sure which specialist?
/design-brief takes a plain-language brief, routes to the right expertise, and returns structured guidance. Use it when the problem spans more than one domain.
Review an existing UI
/design-critic— severity-ranked critique, not reflexive praise. Use before shipping, or when feedback so far has been "looks great!"/anti-slop-designer— detects the generic AI-generated look in UI and copy. Use when a screen feels templated but you can't name why./accessibility-specialist— WCAG 2.2, ARIA, keyboard nav, screen readers.
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.
- 11d ago First seen · 103 lines · 0 tokens per session scan A 7139020c8d58
design-with-claude is a skill published in the GitHub repository imsaif/design-with-claude (11 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,327 tokens. 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 2026-08-30.
Other skills, from other repositories
color-audit
Color-only audit that extracts, evaluates, and recommends improvements for the project's color system. Use when the user asks to audit colors, run a color review or color audit, fix their colors, or work on the color palette or color system.
theme-builder
Build a light/dark theme from scratch or improve an existing one, with a complete surface, text, and interactive color system. Use when the user asks to build or create a theme, use the theme builder, or set up a light and dark theme.
type-audit
Typography-only audit covering font selection, type scale, readability, hierarchy, and performance. Use when the user asks to audit typography, run a typography or type audit, review fonts, fix their fonts, or work on the type system.
layout-audit
Layout and spacing audit covering grid, spacing consistency, density, and responsive behavior. Use when the user asks to audit the layout, run a layout audit or grid audit, review spacing, or fix their spacing.
scroll-craft
Build premium scroll-driven landing pages for service, product, food, and drink brands. Plan the visitor journey, page grammar, emotional peak, and bespoke signature move. Create dimensional heroes with independent visual planes, restrained motion, and separate mobile composition. Use supplied photos and footage or…
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.