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/andr-ca/agentharness/react-best-practicesnpx skills add andr-ca/agentharness --skill react-best-practicesgit clone --depth 1 https://github.com/andr-ca/agentharnessWhat 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 | $0.00044 | $0.01395 |
| Opus 5 | $0.00022 | $0.00698 |
| Sonnet 5 | $0.00009 | $0.00279 |
| Haiku 4.5 | $0.00004 | $0.00139 |
Grade A, and why
react-best-practices 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 2d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
React Best Practices
This skill covers React/JSX-specific conventions. It layers on top of
typescript-conventions — apply that skill first for naming, type safety,
async/await, and module structure; this skill only covers what's
different for components.
Deeper reference: frameworks/react/CONVENTIONS.md (full harness
conventions), languages/typescript/CONVENTIONS.md.
Component naming and file structure
PascalCasefor component names. File name matches the component name.- Use descriptive, specific names:
UserProfileCard, notCard. - One component per file (unless the secondary component is tightly scoped and unexported).
// Good
export function UserProfileCard({ user }: UserCardProps): JSX.Element {
return <div>{user.name}</div>;
}
// File: UserProfileCard.tsx
// Bad — too generic, doesn't match file name
export function Card({ user }: { user: User }): JSX.Element { }
// File: card.tsx
Props typing
Define prop types explicitly with an interface. Destructure in the
signature. Return type annotation (JSX.Element or React.ReactNode)
is recommended.
interface UserCardProps {
user: User;
onSelect?: (user: User) => void;
}
export function UserCard({ user, onSelect }: UserCardProps): JSX.Element {
return (
<button type="button" onClick={() => onSelect?.(user)}>
{user.name}
</button>
);
}
Hooks rules
- Only call hooks at the top level — never inside conditions, loops, or nested functions.
- Only call hooks from React components or custom hooks.
- Prefix custom hooks with
use:useAuth,useDebounce.
// WRONG: conditional hook call
function Component({ isLoggedIn }: Props) {
if (isLoggedIn) {
const user = useUser(); // breaks Rules of Hooks
}
}
// RIGHT: call unconditionally, use the result conditionally
function Component({ isLoggedIn }: Props) {
const user = useUser();
if (!isLoggedIn) return null;
return <div>{user.name}</div>;
}
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.
- 2d ago First seen · 190 lines · 44 tokens per session scan A ed7094eed712
react-best-practices is a skill published in the GitHub repository andr-ca/agentharness (1 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 1,395 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 2026-08-31.
Other skills, from other repositories
react-best-practices
ORGII-specific React 19 performance review and implementation guidance, adapted from Vercel Engineering. Use for React performance, re-render, async waterfall, bundle, heavy dependency, virtualization, high-frequency event, Context/provider, or store-subscription work. Do not trigger for styling, copy changes, or…
ui-library-router
Choose among Kokonut UI, React Bits, daisyUI, Bklit UI, Anime.js, Rive, and Magic UI for frontend work. Use for pages, dashboards, landing pages, animation, data visualization, or interactive graphics; do not use when no UI/library choice is involved.
empty-trigger-short-circuit-before-app-state
Skip nested memory collection when no triggers exist so render-bound getAppState() is never invoked unnecessarily.
review-frontend
Domain review checklist for the trovex web/ surface — the Vite/React/TypeScript landing + savings-calculator app AND the Vercel serverless API functions (web/api/.js) behind it (lead capture, Twenty-CRM mirror, inbound webhook, OG-card/badge generators). Applies to a diff under web/. Ordered highest-weight first: the…
remotion-best-practices
Best practices for Remotion - Video creation in React.
react-doctor
Use when finishing a feature, fixing a bug, before committing React code, or when the user types /doctor, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.