Borrowing it
Nothing to install: this file belongs to Dynokostya/just-works. 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/Dynokostya/just-works/main/.claude/skills/react-coding/SKILL.mdgit clone --depth 1 https://github.com/Dynokostya/just-worksWrote 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/dynokostya/just-works/react-coding)<a href="https://agentmods.dev/skills/dynokostya/just-works/react-coding"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/react-coding/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/dynokostya/just-works/react-coding"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/react-coding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 127 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- high Memory Poisoning · line 130 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- high Memory Poisoning · line 210 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00039 | $0.01258 |
| Opus 5.5 | $0.00016 | $0.00503 |
| Sonnet 5.5 | $0.00008 | $0.00252 |
| Haiku 4.5 | $0.00004 | $0.00126 |
Grade A, and why
react-coding scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 17d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
React Coding
Project conventions override these defaults. Read 2-3 nearby components, package.json (React version, compiler), tsconfig.json, and the framework config (Next.js, Remix, Vite) before writing.
Never rules
- Never use
useEffectfor derived state. Compute the value during render; effect plussetStateadds a render cycle. This is the most common React mistake.
// Wrong
const [fullName, setFullName] = useState("");
useEffect(() => setFullName(`${first} ${last}`), [first, last]);
// Correct
const fullName = `${first} ${last}`;
- Never mutate state. React compares by reference. Use spread,
structuredClone, or non-mutating methods such as.toSorted()(not.sort()). - Never use an array index as
keyin dynamic lists. Reordering or removal reuses DOM nodes and corrupts component state. Use stable IDs. - Never add
"use client"by default. In the Next.js App Router, components are Server Components unless marked. Add it only for hooks, event handlers, or browser APIs, and place the boundary as low in the tree as possible. - Never use
forwardRefin React 19+ code.refis a regular prop. React 18 still requiresforwardRef. - Never define a component inside another component. It gets a new identity every render and loses all state.
- Never suppress
react-hooks/exhaustive-deps. It hides stale closures. Fix the code: extract functions, use updater functions, or move objects inside the effect. - Never mirror props in state.
useState(prop)ignores later prop changes. Use the prop directly, or name itinitialXto signal intent. - Never generate class components. The exception is error boundaries (or use
react-error-boundary). - Never use
dangerouslySetInnerHTMLwithout sanitizing (DOMPurify or similar). - Never render
React.lazycomponents without<Suspense>and an error boundary.
Effects
Before writing useEffect, walk this list:
- Can the value be computed from props or state? Compute it during render.
- Is it a response to a user event? Put it in the event handler, not in an effect keyed to a state flag.
- Does state need to reset when a prop changes? Use
keyon the component (<Profile key={userId} />), not an effect. - Is it synchronization with an external system (DOM, network subscription, third-party widget)? That is a valid effect; return cleanup.
- Is it data fetching? Prefer framework data fetching or TanStack Query. In a raw effect, abort on cleanup and capture errors in state (a rethrow inside
.catchbecomes an unhandled rejection).
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.
- 17d ago Changed · -197 lines · -7 tokens per session 3273356361e3
- 2mo ago First seen · 286 lines · 46 tokens per session scan A e9f3a9549fa1
react-coding is a skill published in the GitHub repository Dynokostya/just-works (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,258 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 2026-09-04.
react-coding compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| react-codingDynokostya/just-works | Skill | 14 | 10d ago | Apache-2.0 | A | 39 | Claude Code |
| build-ghost-appTryGhost/Ghost | Skill | 56k | yesterday | MIT | A | 44 | Claude Code, Codex |
| chakra-ui-builderchakra-ui/chakra-ui | Skill | 41k | yesterday | MIT | A | 214 | Claude Code, Codex |
| material-ui-tailwindmui/material-ui | Skill | 99k | yesterday | MIT | A | 67 | Claude Code, Codex |
| fuzzy-rankingTanStack/table | Skill | 29k | 4d ago | MIT | A | 62 | Claude Code, Codex |
| r3f-best-practiceszebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 74 | Claude Code, Codex |
| git-safetytamagui/tamagui | Skill | 14k | today | MIT | A | 0 | Claude Code |