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.
git clone --depth 1 https://github.com/fellipeutaka/leonWrote 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/plugins/fellipeutaka/leon/frontend)<a href="https://agentmods.dev/plugins/fellipeutaka/leon/frontend"><img src="https://agentmods.dev/badge/plugins/fellipeutaka/leon/frontend/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/plugins/fellipeutaka/leon/frontend"><img src="https://agentmods.dev/badge/plugins/fellipeutaka/leon/frontend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
frontend 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 yesterday.
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
{
"name": "frontend",
"description": "Skills for building, reviewing, and optimizing frontend interfaces.",
"source": "./",
"strict": false,
"skills": [
"./skills/ai-sdk",
"./skills/baseline-ui",
"./skills/canvas-design",
"./skills/composition-patterns",
"./skills/denji",
"./skills/design-lab",
"./skills/fixing-accessibility",
"./skills/fixing-metadata",
"./skills/fixing-motion-performance",
"./skills/frontend-design",
"./skills/figma-raw-geometry",
"./skills/interface-design",
"./skills/interaction-design",
"./skills/kanpeki",
"./skills/motion",
"./skills/nuqs",
"./skills/paraglide-js",
"./skills/react-best-practices",
"./skills/react-hook-form-zod",
"./skills/react-native-skills",
"./skills/shadcn",
"./skills/shadcn-dream",
"./skills/tanstack-ai",
"./skills/tanstack-db",
"./skills/tanstack-form",
"./skills/tanstack-hotkeys",
"./skills/tanstack-query",
"./skills/tanstack-react-store",
"./skills/tanstack-router",
"./skills/tanstack-virtual",
"./skills/tanstack-pacer",
"./skills/tanstack-table",
"./skills/ui-ux-pro-max",
"./skills/web-design-guidelines",
"./skills/zustand"
]
}What it installs
The manifest is a name and a version. 35 skills travel with it, and installing the plugin installs all of them — 2,722 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill motion A 89 tokens
- Skill shadcn-dream A 110 tokens
- Skill react-hook-form-zod A 69 tokens
- Skill denji A 106 tokens
- Skill figma-raw-geometry A 66 tokens
- Skill nuqs A 79 tokens
- Skill tanstack-query A 67 tokens
- Skill tanstack-ai A 122 tokens
- Skill tanstack-form A 76 tokens
- Skill tanstack-pacer A 62 tokens
- Skill tanstack-router A 65 tokens
- Skill tanstack-table A 64 tokens
- Skill kanpeki A 104 tokens
- Skill paraglide-js A 141 tokens
- Skill tanstack-hotkeys A 55 tokens
- Skill tanstack-virtual A 80 tokens
- Skill tanstack-react-store A 71 tokens
- Skill zustand A 75 tokens
- Skill tanstack-db A 50 tokens
- Skill vercel-composition-patterns A 58 tokens
- Skill shadcn A 94 tokens
- Skill design-lab A 52 tokens
- Skill react-native-skills A 55 tokens
- Skill interface-design A 78 tokens
- Skill react-best-practices A 65 tokens
- Skill interaction-design A 38 tokens
- Skill ai-sdk A 155 tokens
- Skill fixing-accessibility A 45 tokens
- Skill fixing-motion-performance A 45 tokens
- Skill web-design-guidelines A 44 tokens
- Skill canvas-design A 59 tokens
- Skill frontend-design A 40 tokens
- Skill baseline-ui A 34 tokens
- Skill fixing-metadata A 71 tokens
- Skill ui-ux-pro-max B 238 tokens
What ships with it
1 file beside marketplace.json#frontend 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.
- yesterday First seen · 43 lines scan A 2b84b4f072e0
frontend is a plugin published in the GitHub repository fellipeutaka/leon (5 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-11-05.
frontend compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| frontendfellipeutaka/leon | Plugin | 5 | yesterday | MIT | A | — | Claude Code |
| shadcnshadcn-ui/ui | Plugin | 127k | yesterday | MIT | A | — | Cursor |
| frontendjezweb/claude-skills | Plugin | 1.1k | 28d ago | MIT | A | — | Claude Code |
| ui-polishopkod-france/opkod-claude-code-plugins | Plugin | 10 | 1mo ago | MIT | A | — | Claude Code |
| frontend-developerarmanzeroeight/fastagent-plugins | Plugin | 29 | 3mo ago | MIT | A | — | Claude Code |
| uiforgeTaewoooPark/UIForge | Plugin | 10 | 3mo ago | MIT | A | — | Claude Code |
| ui-ux-design-proca-who-codes/ultimate.UIUX.design.skills | Plugin | 6 | 3mo ago | MIT | A | — | Claude Code |