Borrowing it
Nothing to install: this file belongs to lennix1337/Genexus18MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lennix1337/Genexus18MCP/main/.gemini/skills/frontend/mercury-design-system/SKILL.mdgit clone --depth 1 https://github.com/lennix1337/Genexus18MCPWrote 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/lennix1337/genexus18mcp/mercury-design-system)<a href="https://agentmods.dev/skills/lennix1337/genexus18mcp/mercury-design-system"><img src="https://agentmods.dev/badge/skills/lennix1337/genexus18mcp/mercury-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/lennix1337/genexus18mcp/mercury-design-system"><img src="https://agentmods.dev/badge/skills/lennix1337/genexus18mcp/mercury-design-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 11 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 Memory Poisoning · line 145 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 147 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 148 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 150 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Prompt Injection · line 145 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 147 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 148 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 150 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 151 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 152 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 299 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00060 | $0.06298 |
| Opus 5 | $0.00030 | $0.03149 |
| Sonnet 5 | $0.00012 | $0.01260 |
| Haiku 4.5 | $0.00006 | $0.00630 |
Grade A, and why
mercury-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 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 — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mercury Design System
Apply Mercury Design System styling to UIs built with Chameleon web components. This skill covers Mercury-specific usage: ch-theme, getBundles, CSS bundles, CSS classes, design tokens, typography, color, spacing, and design patterns. Use the Chameleon skill to build the component tree; then use this skill to add Mercury styling
Workflow
CRITICAL — Chameleon skill required: Before writing any component code, you MUST invoke the chameleon-controls-library skill (via the
Skilltool). Mercury only handles styling (CSS bundles, classes, tokens) — component APIs (properties, events, slots, model shapes) are documented exclusively in the Chameleon skill. Skipping it leads to wrong prop names, missing events, and broken component wiring
Choose the path that matches the user's request:
Path A: Implement from a Figma design (image or frame provided)
- Detect the theme variant (FIRST) — Look at the primary action color in the design (buttons, links, focus indicators). Blue → Mercury (default). Green → Globant (
theme: "globant"). See How to detect the variant. This determines thethemevalue invite-plugin-mercuryand must be resolved before writing any code - Set up the project with the correct theme — If scaffolding a new project or the project doesn't exist yet, configure
vite-plugin-mercurywith the detected theme:mercury({ theme: "mercury" })ormercury({ theme: "globant" }). If the project already exists, verify the theme invite.config.tsmatches the design - Analyze the design — Identify components, layout structure, colors, typography, spacing, and interaction states
- Map Figma values to Mercury tokens — Use Figma token mapping to translate Figma variables, hex values, and font specs into Mercury tokens and classes. Critical: Figma font-weights are +100 higher than real — always subtract 100
What ships with it
60 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.
- evals.json 8.6 KB
- references/api/assets-manager.md 3.3 KB
- references/api/bundles.md 1.7 KB
- references/api/chat-message-metadata.md 293 B
- references/api/chat-render.md 1.0 KB
- references/api/index.md 372 B
- references/api/mercury-assets.md 603 B
- references/api/mercury-config.md 774 B
- references/api/README.md 1.0 KB
- references/api/register-mercury.md 263 B
- references/api/vite-plugin-options.md 3.1 KB
- references/bundles-index.md 4.1 KB
- references/bundles/base/base-globant.css 42 KB
- references/bundles/base/base.css 41 KB
- references/bundles/base/base.md 1.8 KB
- references/bundles/base/icons.css 2979 KB
- references/bundles/chameleon/scrollbar.css 910 B
- references/bundles/chameleon/scrollbar.md 265 B
- references/bundles/components/accordion.css 5.0 KB
- references/bundles/components/accordion.md 1.0 KB
- references/bundles/components/button.css 4.3 KB
- references/bundles/components/button.md 2.2 KB
- references/bundles/components/chat.css 19 KB
- references/bundles/components/chat.md 2.5 KB
- references/bundles/components/checkbox.css 1.6 KB
- references/bundles/components/checkbox.md 641 B
- references/bundles/components/code.css 2.4 KB
- references/bundles/components/code.md 162 B
- references/bundles/components/combo-box.css 4.7 KB
- references/bundles/components/combo-box.md 754 B
- references/bundles/components/dialog.css 4.4 KB
- references/bundles/components/dialog.md 1.2 KB
- references/bundles/components/dropdown.css 6.2 KB
- references/bundles/components/dropdown.md 1.6 KB
- references/bundles/components/edit.css 1.5 KB
- references/bundles/components/edit.md 616 B
- references/bundles/components/flexible-layout.css 8.1 KB
- references/bundles/components/flexible-layout.md 285 B
- references/bundles/components/icon.css 1.4 KB
- references/bundles/components/icon.md 3.0 KB
- references/bundles/components/layout-splitter.css 231 B
- references/bundles/components/layout-splitter.md 217 B
- references/bundles/components/list-box.css 3.7 KB
- references/bundles/components/list-box.md 535 B
- references/bundles/components/markdown-viewer.css 8.2 KB
- references/bundles/components/markdown-viewer.md 373 B
- references/bundles/components/navigation-list.css 2.9 KB
- references/bundles/components/navigation-list.md 217 B
- references/bundles/components/paginator.css 8.9 KB
- references/bundles/components/paginator.md 341 B
- references/bundles/components/pills.css 5.4 KB
- references/bundles/components/pills.md 935 B
- references/bundles/components/radio-group.css 1.4 KB
- references/bundles/components/radio-group.md 590 B
- references/bundles/components/segmented-control.css 2.3 KB
- references/bundles/components/segmented-control.md 820 B
- references/bundles/components/sidebar.css 2.0 KB
- references/bundles/components/sidebar.md 807 B
- references/bundles/components/slider.css 1.5 KB
- references/bundles/components/slider.md 507 B
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 · 377 lines · 60 tokens per session scan A 0a2ab7a93873
mercury-design-system is a skill published in the GitHub repository lennix1337/Genexus18MCP (30 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 6,298 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
animation-patterns
SwiftUI animation patterns including springs, transitions, PhaseAnimator, KeyframeAnimator, SF Symbol effects, scroll-driven effects, mesh gradients, text renderers, and shader effects. Use when implementing, reviewing, or fixing animation or visual-effect code on iOS/macOS.
frontend-enhancer
This skill should be used when enhancing the visual design and aesthetics of web applications. It provides modern UI components, design patterns, color palettes, animations, and layout templates. REQUIRES ui-research skill first. Use this skill for tasks like improving styling, creating responsive designs…
generic-design-system
Complete design system reference for any project - colors, typography, spacing, components, animations. Adapts to project theme and tech stack. Use when implementing UI, choosing colors, creating animations, or ensuring brand consistency. For new design systems, use ui-research skill first.
static-page-stack
SOTA stack recommendations for elegant, controlled, semantic static HTML pages — dashboards, post-mortems, technical-investigation reports.
generic-react-design-system
Complete design system reference for React applications. Covers colors, typography, spacing, component patterns, glassmorphism effects, GPU-accelerated animations, and WCAG AA accessibility. Use when implementing UI, choosing colors, applying spacing, creating components, or ensuring brand consistency.
generic-static-design-system
Complete design system reference for static HTML/CSS/JS sites. Covers colors, typography, component patterns, animations, and accessibility. Use when implementing UI, choosing colors, or ensuring brand consistency.