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 siberiacancode/agent-skills --skill reactusegit clone --depth 1 https://github.com/siberiacancode/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/siberiacancode/agent-skills/reactuse)<a href="https://agentmods.dev/skills/siberiacancode/agent-skills/reactuse"><img src="https://agentmods.dev/badge/skills/siberiacancode/agent-skills/reactuse/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/siberiacancode/agent-skills/reactuse"><img src="https://agentmods.dev/badge/skills/siberiacancode/agent-skills/reactuse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Memory Poisoning · line 240 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00050 | $0.04137 |
| Opus 5.5 | $0.00020 | $0.01655 |
| Sonnet 5.5 | $0.00010 | $0.00827 |
| Haiku 4.5 | $0.00005 | $0.00414 |
Grade A, and why
reactuse 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.
How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reactuse
This skill is a decision-and-implementation guide for reactuse library for react.js / next.js projects. It maps requirements to the most suitable reactuse hook, applies the correct usage pattern, and prefers hook-based solutions over bespoke code to keep implementations concise, maintainable, and performant.
When to Apply
- Apply this skill whenever assisting development work in React.js / Next.js.
- Always check first whether a reactuse hook can implement the requirement.
- Prefer reactuse hooks over custom code to improve readability, maintainability, and performance.
- Map requirements to the most appropriate hook and follow the hook’s invocation rule.
- Please refer to the
Invocationfield in the hooks table. For example:AUTO: Use automatically when applicable.EXTERNAL: Use only if the user already installed the required external dependency; otherwise reconsider, and ask to install only if truly needed.EXPLICIT_ONLY: Use only when explicitly requested by the user.NOTE User instructions in the prompt or
AGENTS.mdmay override a hook’s defaultInvocationrule.
Hooks
All hooks listed below are part of the reactuse library. Each section categorizes hooks based on their functionality.
IMPORTANT: Each hook entry includes a short Description and a detailed Reference. When using any hook, always consult the corresponding document in ./references for usage details and type declarations.
Blocked upstream category: Reactuse also exports Humor hooks (useFul, useLess, useOnce) in recent releases. This skill intentionally does not support or recommend them because upstream marks them as jokes or non-production utilities.
Helpers
| Hook | Description | Invocation |
|---|---|---|
| cn | Normalizes conditional class names for React className. |
HIGH |
| createContext | Creates a typed context with provider and selector hook. | HIGH |
| createContextHook | Scopes one hook result to a React subtree. | LOW |
| createEventEmitter | Creates a type-safe event emitter with a subscription hook. | LOW |
| createReactiveContext | Creates a typed context selector with optimized updates. | LOW |
| createSharedHook | Shares one hook instance across consumers. | LOW |
| createStore | Creates a external store with state, subscriptions, and a hook. | MEDIUM |
| makeDestructurable | Supports object and tuple consumption from one value. | LOW |
| target | Wraps DOM targets in the shape Reactuse hooks expect. | MEDIUM |
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.
- AGENTS.md 257 KB
- metadata.json 483 B
- README.md 3.3 KB
- rules/_sections.md 1.9 KB
- rules/_template.md 1.1 KB
- rules/cn.md 1.2 KB
- rules/createContext.md 1.8 KB
- rules/createContextHook.md 1.3 KB
- rules/createEventEmitter.md 1.2 KB
- rules/createReactiveContext.md 1.9 KB
- rules/createSharedHook.md 1.1 KB
- rules/createStore.md 1.8 KB
- rules/makeDestructurable.md 985 B
- rules/target.md 1.4 KB
- rules/useActiveElement.md 1.3 KB
- rules/useAsync.md 917 B
- rules/useAsyncEffect.md 630 B
- rules/useAudio.md 2.2 KB
- rules/useAutoScroll.md 1.1 KB
- rules/useBatchedCallback.md 1.2 KB
- rules/useBattery.md 1.4 KB
- rules/useBluetooth.md 3.8 KB
- rules/useBoolean.md 723 B
- rules/useBreakpoints.md 2.4 KB
- rules/useBroadcastChannel.md 1000 B
- rules/useBrowserLanguage.md 560 B
- rules/useBrowserLocation.md 1.7 KB
- rules/useClickOutside.md 1.0 KB
- rules/useClipboard.md 966 B
- rules/useConst.md 523 B
- rules/useContextMenu.md 3.0 KB
- rules/useControllableState.md 1.6 KB
- rules/useCookie.md 2.8 KB
- rules/useCookies.md 1.2 KB
- rules/useCopy.md 815 B
- rules/useCounter.md 1.2 KB
- rules/useCssVar.md 1.3 KB
- rules/useCycleList.md 1.3 KB
- rules/useDebounceCallback.md 891 B
- rules/useDebounceEffect.md 788 B
- rules/useDebounceState.md 949 B
- rules/useDebounceValue.md 783 B
- rules/useDefault.md 875 B
- rules/useDeviceList.md 2.0 KB
- rules/useDeviceMotion.md 1.8 KB
- rules/useDeviceOrientation.md 990 B
- rules/useDevicePixelRatio.md 882 B
- rules/useDidUpdate.md 737 B
- rules/useDisclosure.md 1.2 KB
- rules/useDisplayMedia.md 2.6 KB
- rules/useDocumentEvent.md 774 B
- rules/useDocumentTitle.md 1.1 KB
- rules/useDocumentVisibility.md 732 B
- rules/useDoubleClick.md 1.7 KB
- rules/useDraggable.md 2.7 KB
- rules/useDropZone.md 2.6 KB
- rules/useEvent.md 745 B
- rules/useEventListener.md 2.4 KB
- rules/useEventSource.md 2.3 KB
- rules/useEyeDropper.md 974 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.
- 1mo ago Changed · +2 lines 00c997e6b20a
- 1mo ago First seen · 263 lines · 50 tokens per session scan A 27c5c99c47e2
reactuse is a skill published in the GitHub repository siberiacancode/agent-skills (23 stars, last pushed 8d ago), licensed MIT. It adds 50 tokens to every session and 4,137 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 2026-08-30.
Other skills, from other repositories
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
next-bundle-optimizer
Audit and reduce Next.js browser initial-load work. Use for slow route startup, oversized client bundles, duplicate browser dependencies, or features that can wait for interaction.
next-dev-loop
Verify Next.js runtime behavior after editing app code. Use this skill to confirm a change actually works in a running app — not just that it compiles or type-checks. Combines /next/mcp (Next.js's view) with agent-browser (the browser's view). Requires a running next dev.
next-partial-prefetching-optimizer
Optimize what selected Next.js client navigations include before the click under Partial Prefetching. Use after Cache Components and Partial Prefetching are adopted when the user wants selected URL-specific UI to be instant, wants reusable content to wait for navigation, or needs to choose between default, viewport…