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 agentmods add skills/fusengine/agents/nextjs-zustandnpx skills add fusengine/agents --skill nextjs-zustandgit clone --depth 1 https://github.com/fusengine/agentsWrote 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/fusengine/agents/nextjs-zustand)<a href="https://agentmods.dev/skills/fusengine/agents/nextjs-zustand"><img src="https://agentmods.dev/badge/skills/fusengine/agents/nextjs-zustand.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00032 | $0.01480 |
| Opus 5 | $0.00016 | $0.00740 |
| Sonnet 5 | $0.00006 | $0.00296 |
| Haiku 4.5 | $0.00003 | $0.00148 |
Grade A, and why
nextjs-zustand 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.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Covers skipHydration with the persist middleware plus manual rehydration in useEffect to avoid SSR mismatches, useShallow for array/object selectors, and SOLID file organization (store.ts, store-provider.tsx, use-store.ts). States explicitly that Zustand is Client-Components-only — never used in Server Components (fetch data directly there instead) and never used to persist auth tokens (use httpOnly cookies). Does not cover server state caching (see nextjs-tanstack-query for that).
Zustand for Next.js 16
Minimal, scalable state management with React 18+ useSyncExternalStore.
Agent Workflow (MANDATORY)
Before ANY implementation, use TeamCreate to spawn 3 agents:
- fuse-ai-pilot:explore-codebase - Analyze existing stores and state patterns
- fuse-ai-pilot:research-expert - Verify latest Zustand v5 docs via Context7/Exa
- mcp__context7__query-docs - Check middleware and TypeScript patterns
After implementation, run fuse-ai-pilot:sniper for validation.
Overview
When to Use
- Managing client-side state in Next.js App Router applications
- Need global state across Client Components only
- Persisting state to localStorage/sessionStorage
- Building UI state (modals, sidebars, theme, cart)
- Replacing React Context for complex state
Why Zustand v5
| Feature | Benefit |
|---|---|
| Minimal API | Simple create() function, no boilerplate |
| React 18 native | useSyncExternalStore, no shims needed |
| TypeScript first | Full inference with currying pattern |
| Middleware stack | devtools, persist, immer composable |
| Bundle size | ~2KB gzipped, smallest state library |
| No providers | Direct store access, no Context wrapper |
What ships with it
12 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.
- references/auto-selectors.md 4.1 KB
- references/hydration.md 5.4 KB
- references/installation.md 2.3 KB
- references/middleware.md 5.2 KB
- references/migration-v5.md 3.9 KB
- references/nextjs-integration.md 4.8 KB
- references/reset-state.md 4.8 KB
- references/slices.md 5.0 KB
- references/store-patterns.md 5.1 KB
- references/subscribe-api.md 5.3 KB
- references/testing.md 5.1 KB
- references/typescript.md 6.3 KB
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 · 150 lines · 32 tokens per session scan A a0666374d9cb
nextjs-zustand is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,480 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
vibes
Self-contained app generator — invoke this skill directly, do not decompose into sub-steps. Generates React web apps with TinyBase reactive data store. Use when creating new web applications, adding components, or working with real-time data. Ideal for quick prototypes and single-page apps that need real-time data…
radin-record
Log feedback, bugs, follow-ups, or ideas raised mid-session as structured backlog entries, so they survive past the conversation. Use for /radin-record, "log this to the backlog", "add as follow-up/bug/idea", "record what we just found", "note this for later", "add findings to backlog". Triggers even on vague asks…
ink-playing-cards
Use when building terminal card games with ink-playing-cards, working with card components, deck management, zone systems, event systems, effect systems, or any card game logic using Ink and React for CLI rendering.
radin-doctor
Check that radin's own install under /.claude is complete and its optional companion tools are reachable. Use for /radin-doctor, "check my radin install", "is radin installed correctly", "radin doctor", "verify radin install".
designing-interfaces
Creates a design system for software with a UI. Use when a project has a user interface and architecture is confirmed — whether creating from scratch or extracting patterns from existing code.
managing-product
Extracts product requirements and produces a PRD. Use when a user wants to build software and needs to define what to build before architecture or implementation, when scoping an MVP, or when translating a vague idea into a buildable specification.