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 magarcia/skills --skill designgit clone --depth 1 https://github.com/magarcia/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/magarcia/skills/design)<a href="https://agentmods.dev/skills/magarcia/skills/design"><img src="https://agentmods.dev/badge/skills/magarcia/skills/design/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/magarcia/skills/design"><img src="https://agentmods.dev/badge/skills/magarcia/skills/design.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 | $0.00046 | $0.00340 |
| Opus 5.5 | $0.00018 | $0.00136 |
| Sonnet 5.5 | $0.00009 | $0.00068 |
| Haiku 4.5 | $0.00005 | $0.00034 |
Grade A, and why
design 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.
What it actually says
Design
Gate on the diff: if it does not touch components, styles, tokens, templates, markup, copy, or layout, report "no UI changes in diff" and stop.
- Load context — Read the applicable
AGENTS.mdfiles and the design-system documentation they identify, including the component library, tokens, spacing, typography, breakpoints, and themes. - Inspect statically — Find hand-written values where tokens exist, reimplemented component variants, placeholder copy, and accessibility defects in semantics, labels, alt text, focus states, contrast, or keyboard access.
- Look at the UI — Start the documented development environment or Storybook. Use
$agent-browserfor real interaction and screenshots unless the repository explicitly requires another tool; load its current core workflow before issuing browser commands. Check empty, loading, error, and populated states; hover, focus, active, and disabled states; long and minimal content; project breakpoints; and supported themes. Support every "looks correct" claim with a screenshot. - Fix or flag — Fix mechanical defects within scope, such as a wrong token, missing focus style, or broken breakpoint. Present tradeoffs before changes that involve visual judgment, intentional-looking behavior, or other screens.
Check at least one additional consumer when the diff changes a shared component. Preserve consistency rather than redesigning or adding unrequested aesthetic changes.
What ships with it
1 file 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 · 16 lines · 46 tokens per session scan A 4101249118af
design is a skill published in the GitHub repository magarcia/skills (4 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 340 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
cognitive-walkthrough
Deep-dive usability evaluation of specific user tasks. Simulates novice user cognition step-by-step to identify learnability issues, unclear actions, and points of confusion.
don-norman-principles-audit
Evaluate UX/UI using Don Norman's 7 fundamental design principles from The Design of Everyday Things. Audit discoverability, affordances, signifiers, feedback, mapping, constraints and conceptual models.
wcag-accessibility-audit
Comprehensive web accessibility audit using WCAG 2.1/2.2 guidelines. Evaluate compliance across 4 POUR principles (Perceivable, Operable, Understandable, Robust) with A, AA, AAA conformance levels.
nielsen-heuristics-audit
Evaluate UX/UI using Jakob Nielsen's 10 usability heuristics. Comprehensive audit of visibility, control, consistency, error prevention, recognition, flexibility, aesthetics, error recovery, and documentation.
ui-design-review
Comprehensive visual design and aesthetics evaluation. Analyzes typography, color, spacing, hierarchy, consistency, branding, and current product-category conventions for polished, professional interfaces.
information-architecture-audit
Audit or design the information architecture of a site/app — organization, labeling, navigation, search, content inventory, sitemaps, card sorting and tree testing, with prioritized findings.