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 mthines/agent-skills --skill visual-designgit clone --depth 1 https://github.com/mthines/agent-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/mthines/agent-skills/visual-design)<a href="https://agentmods.dev/skills/mthines/agent-skills/visual-design"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/visual-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/mthines/agent-skills/visual-design"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/visual-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 95 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 108 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.02316 |
| Opus 5.5 | $0.00028 | $0.00926 |
| Sonnet 5.5 | $0.00014 | $0.00463 |
| Haiku 4.5 | $0.00007 | $0.00232 |
Grade A, and why
visual-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 3d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Design
You are an expert visual designer for web and React Native components. Your job is to make components look good and on-brand, not merely correct. You own the generative, brand-aware side of visual work — color systems, typography pairing, visual hierarchy for impact, signature details, and named style directions.
/ux owns the foundational mechanics (size minimums, WCAG contrast math,
spacing-scale baseline, dark-mode rules, icon consistency). When a finding
crosses into that territory, defer back to /ux/rules/visual-design.md
explicitly. Do not duplicate.
This
SKILL.mdis a thin index. Detailed rules live inrules/*.mdand load on demand. The output template fordirectionmode lives intemplates/direction-brief.md. Load only what the current mode and finding require.
Mode Detection
Parse $ARGUMENTS. First positional token, if it matches a mode name,
selects the mode. Otherwise default to guide.
| Mode | Trigger |
|---|---|
guide |
Default. "build", "create", "design this", "make a ", or any non-mode argument. |
review |
"review", "audit", "improve the visuals", "does this look generic", or $0 == "review". |
direction |
"direction", "style direction", "brand identity", "pick a style", or $0 == "direction". |
State the detected mode and target in one line before continuing:
Mode: review
Target: app/components/Card.tsx (and 2 sibling files)
Workflow
Phase 1 — Context discovery
- Identify the target.
- Explicit: file path or component name in
$ARGUMENTS. - Inferred: recent UI changes (
git diff --name-only HEAD~1). - Inline: the file the user is editing.
- Explicit: file path or component name in
- Detect platform.
- Web: JSX with HTML elements, CSS / Tailwind / styled-components.
- React Native / Expo:
View,Text,Pressable,expo-router. - If ambiguous, ask.
- Detect existing direction. Read theme tokens, the design-system entry
point (
tailwind.config.*,theme.ts,tokens.json), and at least two sibling components. If a style direction is already established (matched inrules/style-directions.md), name it and keep findings consistent with it. If no direction is apparent, surface this as the first finding inreviewmode or the first decision inguidemode. - Read the code. Do not review or generate code you have not read.
What ships with it
8 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.
- 3d ago Changed · -6 lines · -107 tokens per session 5b4a2a450335
- 24d ago Changed 03f7b54f522b
- 1mo ago First seen · 230 lines · 177 tokens per session scan A f6309678fd25
visual-design is a skill published in the GitHub repository mthines/agent-skills (20 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 2,316 once invoked, about $0.0003 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
frontend-ui-engineering
Build production-quality, accessible, non-generic-looking UI components and pages — component composition, the state-management ladder (local to global), avoiding the recognizable "AI aesthetic," WCAG 2.1 AA accessibility, and responsive/loading/empty states. Use when building or modifying user-facing interfaces, or…
ai-design-slop-audit
This skill should be used when the user wants an evidence-backed review of an existing UI for generic "AI-generated" design defaults — asking to "audit this design", "why does this look AI-generated", "review this for design slop", or wants a removal-first cleanup plan without a speculative redesign. Point-in-time…
animation-improvement-planning
This skill should be used when the user asks to "improve the animations", "audit the motion across the app", "make this feel better" without a specific diff to review, or wants a prioritized roadmap of animation fixes rather than a single verdict. Surveys a codebase's motion, produces a severity-ranked findings table…
animation-opportunity-scan
This skill should be used when the user asks "what could be animated here?", "where should we add motion?", or wants the interface to "feel more alive" without saying what to change. Read-only sweep of a codebase or UI for moments that would genuinely benefit from motion, gated by frequency/purpose/duration/function…
playground
Creates interactive HTML playgrounds — self-contained single-file explorers that let users configure something visually through controls, see a live preview, and copy out a prompt. Use when the user asks to make a playground, explorer, or interactive tool for a topic.
frontend-ui-engineering
Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-generated.