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 fusengine/agents --skill react-19git 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/react-19)<a href="https://agentmods.dev/skills/fusengine/agents/react-19"><img src="https://agentmods.dev/badge/skills/fusengine/agents/react-19/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/fusengine/agents/react-19"><img src="https://agentmods.dev/badge/skills/fusengine/agents/react-19.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector 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 | $0.00042 | $0.02429 |
| Opus 5.5 | $0.00017 | $0.00972 |
| Sonnet 5.5 | $0.00008 | $0.00486 |
| Haiku 4.5 | $0.00004 | $0.00243 |
Grade A, and why
react-19 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 22d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Also documents all classic hooks (useState, useEffect, useLayoutEffect, useRef, useImperativeHandle, useMemo, useCallback, useId, useSyncExternalStore) and React 18→19 breaking changes (ref as a prop instead of forwardRef, <Context value={}> instead of <Context.Provider>). This is the core React hooks/features skill — for global state see react-state, for forms see react-forms, and for SOLID architecture rules see solid-react.
React 19.3 Core Features
Agent Workflow (MANDATORY)
Before ANY implementation, spawn 3 agents in parallel, one Agent call each with a name:
- fuse-ai-pilot:explore-codebase - Analyze existing React patterns and component structure
- fuse-ai-pilot:research-expert - Verify latest React 19.3 docs via Context7/Exa
- mcp__context7__query-docs - Check use(), useOptimistic, useActionState, Activity patterns
After implementation, run fuse-ai-pilot:sniper for validation.
What's New in React 19.3
Stable in 19.3 (react/react-dom 19.3.0, 2026-09-09; @types/react 19.3 needs TypeScript ≥ 5.6):
| API | Purpose | Guide |
|---|---|---|
<ViewTransition> |
Animate enter/exit/update/share via the browser View Transition API | references/suspense-patterns.md |
addTransitionType(type) |
Tag a Transition to pick a different animation | references/suspense-patterns.md |
<Fragment ref> |
FragmentInstance (events, focus, observers) without a wrapper <div> |
references/ref-as-prop.md |
use(browser(reason?)) (react-dom) |
Browser-only rendering: suspends on the server, Suspense fallback in HTML | references/new-hooks.md |
What ships with it
44 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/actions-api.md 1.8 KB
- references/activity-component.md 1.9 KB
- references/context-improvements.md 2.3 KB
- references/custom-hooks-patterns.md 2.6 KB
- references/document-metadata.md 1.4 KB
- references/hooks-improved.md 1.8 KB
- references/lazy-loading.md 2.5 KB
- references/migration-18-19.md 3.6 KB
- references/new-hooks.md 4.6 KB
- references/profiling.md 2.9 KB
- references/react-compiler.md 2.6 KB
- references/ref-as-prop.md 1.9 KB
- references/resource-loading.md 1.8 KB
- references/suspense-patterns.md 3.7 KB
- references/templates/action-form.md 4.5 KB
- references/templates/activity-tabs.md 5.4 KB
- references/templates/custom-hooks.md 8.6 KB
- references/templates/document-metadata.md 3.6 KB
- references/templates/effect-patterns.md 16 KB
- references/templates/error-boundary.md 7.2 KB
- references/templates/external-store.md 8.9 KB
- references/templates/lazy-components.md 5.8 KB
- references/templates/optimistic-update.md 4.4 KB
- references/templates/profiling-devtools.md 6.3 KB
- references/templates/ref-as-prop.md 6.6 KB
- references/templates/ref-patterns.md 4.7 KB
- references/templates/resource-loading.md 4.5 KB
- references/templates/state-patterns.md 14 KB
- references/templates/use-context.md 7.4 KB
- references/templates/use-deferred-value.md 5.3 KB
- references/templates/use-effect-event.md 7.0 KB
- references/templates/use-promise.md 4.9 KB
- references/templates/use-transition-async.md 6.4 KB
- references/templates/virtual-list.md 7.4 KB
- references/use-callback.md 2.5 KB
- references/use-effect.md 3.0 KB
- references/use-id.md 1.9 KB
- references/use-imperative-handle.md 1.9 KB
- references/use-layout-effect.md 2.0 KB
- references/use-memo.md 2.4 KB
- references/use-ref.md 1.9 KB
- references/use-state.md 2.4 KB
- references/use-sync-external-store.md 2.0 KB
- references/virtualization.md 2.3 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.
- 22d ago Changed · +13 lines · +8 tokens per session c3331dc7d263
- 1mo ago Changed f27b298edc55
- 1mo ago First seen · 244 lines · 34 tokens per session scan A a7f668f2c03b
react-19 is a skill published in the GitHub repository fusengine/agents (33 stars, last pushed 7d ago), licensed MIT. It adds 42 tokens to every session and 2,429 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 2026-09-03.
Other skills, from other repositories
helius-phantom
Build frontend Solana applications with Phantom Connect SDK and Helius infrastructure. Covers React, React Native, and browser SDK integration, transaction signing via Helius Sender, API key proxying, token gating, NFT minting, crypto payments, real-time updates, and secure frontend architecture.
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-do
Record one ad-hoc prompt as a backlog entry, then execute just that task. Use for /radin-do .
radin-stats
Show the stats/gain output of every companion tool that ships one, side by side.
radin-batch
Work backlog tasks via sub-agents, prioritized, one commit each; plans first the entries radin-record flagged as needing a plan. Use for "work through my backlog", or name an epic or task to run only those.
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.