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/childrentime/reactuse/pr-descriptionnpx skills add childrentime/reactuse --skill pr-descriptiongit clone --depth 1 https://github.com/childrentime/reactuseWhat 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 | $0.00055 | $0.00562 |
| Opus 5 | $0.00028 | $0.00281 |
| Sonnet 5 | $0.00011 | $0.00112 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
pr-description 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.
What it actually says
pr-description — describe a change the ReactUse way
Generate a title + body from the real diff, matching this repo's conventions. Don't invent scope or impact — read what actually changed.
Step 1 — Read the change
git status
git diff --stat
git diff # or: git diff origin/main...HEAD for a branch
git log --oneline -10 # match the prevailing style
Step 2 — Title: conventional commits with a scope
Format: type(scope): summary — imperative, lowercase, no trailing period.
Types seen in this repo: feat, fix, docs, chore, refactor, test.
Common scopes: core (hooks), website, blog, readme, mcp, skill.
Real examples from history:
feat(core): add useMicrophone hook (#198)fix(core): emit default values in generated API docsdocs(website): add useMicrophone hook documentation (#199)docs(blog): add React event hooks post (en, zh-Hans, zh-Hant)chore: release v6.3.3
Pick the type by the dominant change. A new hook is feat(core):; its docs are
docs(website):; they're usually separate commits/PRs.
Step 3 — Body
Keep it tight. Include only sections that apply:
## What
- bullet of each meaningful change
## Why
- the motivation / problem solved
## Test plan
- pnpm --filter @reactuses/core test useX
- pnpm lint
- (for docs) built locally / live demo renders
## AI assistance
- e.g. scaffolded with the new-hook skill (optional, see .claude/ai-policy.md)
Rules
- Verify every hook reference against
scripts/hook-registry.json— never invent a hook name, category, or URL. Links must be the lowercase canonical form. - Multi-locale doc/blog changes: note all three locales like history does
(
(en, zh-Hans, zh-Hant)). - Mention the issue/PR number if one exists.
- Disclosing AI use is recommended (see
ai-policy.md), not required.
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 · 66 lines · 55 tokens per session scan A d463448bd69b
pr-description is a skill published in the GitHub repository childrentime/reactuse (1,047 stars, last pushed 11d ago), licensed Unlicense. It adds 55 tokens to every session and 562 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
react-hooks-composition
Advanced React hooks composition patterns - SWR integration, debounced search, memoized contexts, state machines, and performance optimization.
juniors-best-practice
Juniors-focused React and TypeScript best practices. Use this skill when writing or reviewing code to enforce clear, consistent, and maintainable patterns across common scopes like React, TypeScript, styling, devtools, assets, and Git.
react-hooks-best-practices
React hooks best practices for React application code and custom hook design across DX, optimization, and logic. Use when writing components with hooks, creating or refactoring custom hooks, reviewing hook usage/APIs/internals, checking effects/dependencies/state/refs/callbacks, or improving hook correctness…
reactuse
Practical playbook for React teams to choose and apply reactuse hooks across state, async flows, browser APIs, and UI interactions. Use it when replacing custom hook logic with production-ready patterns that stay compatible with SSR and Next.js.
react-ink
Use this skill when building terminal user interfaces with React Ink - interactive CLI apps, terminal dashboards, progress displays, or keyboard-driven TUI components. Triggers on React Ink, Ink components, terminal UI with React, useInput, useFocus, Box/Text layout, create-ink-app, and any task requiring rich…
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…