ReactUse is a TypeScript library of reusable React Hooks for browser APIs, state, sensors, animations, and DOM interactions. React developers use it when building React applications that need these common behaviors. The catalogue skills and commands help coding agents discover or work with ReactUse hooks.
Borrowing it
Nothing to install: this file belongs to childrentime/reactuse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/childrentime/reactuse/main/.claude/commands/new-hook.mdgit clone --depth 1 https://github.com/childrentime/reactuseWrote 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/commands/childrentime/reactuse/new-hook)<a href="https://agentmods.dev/commands/childrentime/reactuse/new-hook"><img src="https://agentmods.dev/badge/commands/childrentime/reactuse/new-hook/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/commands/childrentime/reactuse/new-hook"><img src="https://agentmods.dev/badge/commands/childrentime/reactuse/new-hook.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00019 | $0.00392 |
| Opus 5.5 | $0.00008 | $0.00157 |
| Sonnet 5.5 | $0.00004 | $0.00078 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
new-hook 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 2mo 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.
What it actually says
Add a new hook to @reactuses/core, running the full pipeline. Arguments: $ARGUMENTS
(hook name starting with use, a one-line description in quotes, and a category — one of
browser / effect / element / state / integrations).
Do it in this order, using the dedicated skills and stopping to confirm understanding before writing code:
-
Sanity check. Confirm the hook name starts with
use, the category is valid, andpackages/core/src/<useName>does not already exist. If the category wasn't given, ask. -
Scaffold — use the new-hook skill. Create
packages/core/src/<useName>/{index.ts, interface.ts}with SSR-safe, util-reusing code and multilingual JSDoc, then wire all three parts intopackages/core/src/index.ts. -
Test — use the hook-test skill. Add
packages/core/src/<useName>/index.spec.tsand runpnpm --filter @reactuses/core test <useName>until green. -
Docs — use the hook-docs skill. Create the
.mdxfor all three locales under the chosen{category}folder, then runbash scripts/generate-hook-registry.sh. -
Verify — run
pnpm lintand the hook's test once more. Report the files created/edited and the test result. Do not commit unless asked.
Follow .claude/knowledge-base.md for conventions and .claude/ai-policy.md for the
self-review bar.
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.
- 2mo ago First seen · 31 lines · 19 tokens per session scan A 531d9e21d35d
new-hook is a command published in the GitHub repository childrentime/reactuse (1,068 stars, last pushed 8d ago), licensed Unlicense. It adds 19 tokens to every session and 392 once invoked, about $0.0001 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.
new-hook compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| new-hookchildrentime/reactuse | Command | 1.1k | 8d ago | Unlicense | A | 19 | Claude Code |
| plan-featureHoangNguyen0403/agent-skills-standard | Command | 583 | today | MIT | A | 0 | Claude Code |
| retro-learnHoangNguyen0403/agent-skills-standard | Command | 583 | today | MIT | A | 0 | Claude Code |
| prototype-loopGenerous-Corp/pulp | Command | 22 | today | MIT | A | 31 | Claude Code |
| react-buildDekaPrayoga/AurixAgent | Command | 62 | 3mo ago | none | A | 59 | Claude Code |
| web-designlukaskellerstein/claude-my-marketplace | Command | 3 | 1mo ago | none | A | 26 | Claude Code |
| nextjs-routeshoruz-ai/claude-plugins | Command | 5 | 9mo ago | none | A | 8 | Claude Code |