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 mantinedev/skills --skill mantine-comboboxgit clone --depth 1 https://github.com/mantinedev/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/mantinedev/skills/mantine-combobox)<a href="https://agentmods.dev/skills/mantinedev/skills/mantine-combobox"><img src="https://agentmods.dev/badge/skills/mantinedev/skills/mantine-combobox/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/mantinedev/skills/mantine-combobox"><img src="https://agentmods.dev/badge/skills/mantinedev/skills/mantine-combobox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00104 | $0.01831 |
| Opus 5.5 | $0.00042 | $0.00732 |
| Sonnet 5.5 | $0.00021 | $0.00366 |
| Haiku 4.5 | $0.00010 | $0.00183 |
Grade A, and why
mantine-combobox 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 27d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- mantine-combobox — 100% identical, 88 lines differ
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mantine Combobox Skill
Written for Mantine 9.x.
Overview
Combobox provides low-level primitives for building any select-like UI. The built-in
Select, MultiSelect, Autocomplete, and TagsInput components are all built on top of it.
Check for a ready-made component first
Build with Combobox primitives only when none of these fit:
| Need | Use |
|---|---|
| Standard select, multi-select, autocomplete or tags input | Select, MultiSelect, Autocomplete, TagsInput (all support renderOption) |
| Options dropdown attached to a button or any other element, no input | ComboboxPopover (data-driven: data, value, onChange, searchable, multiple) |
| Hierarchical options | TreeSelect (see below) |
| More than a few hundred options | Combobox with useVirtualizedCombobox, see the virtualized pattern |
<ComboboxPopover data={['React', 'Angular', 'Vue']} value={value} onChange={setValue}>
<ComboboxPopover.Target>
<Button variant="default">{value || 'Select framework'}</Button>
</ComboboxPopover.Target>
</ComboboxPopover>
ComboboxPopover opens on target click by itself, marks the selected option with a check icon and
handles keyboard navigation. Useful props: searchable, multiple (value becomes string[], the
dropdown stays open while picking), allowDeselect={false} (one option is always selected),
nothingFoundMessage, renderOption, limit, maxDropdownHeight, name (hidden input for forms),
comboboxProps={{ width: 220, position: 'bottom-start' }}. data supports disabled items and groups
like Select: [{ group: 'Size', items: [{ value: 'xs', label: 'XS' }] }]. It cannot render custom dropdown content (tabs, header, footer, create actions): use
Combobox primitives for that.
TreeSelect takes nested data ({ value, label, children? }[], unique values) and renders an
input with an expandable tree in the dropdown. Props include mode (single, multiple, or checkbox
with parent-child cascade), searchable, clearable, renderNode. Build the tree from Combobox
primitives instead when you need a different layout: only leaves selectable, a flat list of search
results with full paths, or a button trigger. In that case render every visible row as a
Combobox.Option and decide in onOptionSubmit whether the row selects or expands.
What ships with it
2 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.
- 27d ago Changed · +80 lines 8d69cdf10716
- 2mo ago First seen · 74 lines · 104 tokens per session scan A ba9897d1d114
mantine-combobox is a skill published in the GitHub repository mantinedev/skills (65 stars, last pushed 16d ago), licensed MIT. It adds 104 tokens to every session and 1,831 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
build-ghost-app
Connect a Ghost app to Ghost Admin with the app SDK, and serve its manifest and install link. Use when building a Ghost app, connecting it to Admin, writing its manifest or installing it.
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
material-ui-tailwind
Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.
fuzzy-ranking
Rank fuzzy matches with rankItem, filter with RankingInfo.passed, compare saved ranking metadata with compareItems, and configure rankings, thresholds, accessors, min/max bounds, or diacritics. Load for @tanstack/match-sorter-utils itself or fuzzy Table filterMeta wiring.
r3f-best-practices
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
git-safety
Git safety rules. INVOKE WHEN: git push, force push, git reset, git clean, destructive git, push force, reset hard. NEVER force push or do destructive git operations.