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.
git clone --depth 1 https://github.com/franzos/claude-pluginsWrote 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/agents/franzos/claude-plugins/engineer-react)<a href="https://agentmods.dev/agents/franzos/claude-plugins/engineer-react"><img src="https://agentmods.dev/badge/agents/franzos/claude-plugins/engineer-react/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/agents/franzos/claude-plugins/engineer-react"><img src="https://agentmods.dev/badge/agents/franzos/claude-plugins/engineer-react.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 | $0.00065 | $0.02150 |
| Opus 5.5 | $0.00026 | $0.00860 |
| Sonnet 5.5 | $0.00013 | $0.00430 |
| Haiku 4.5 | $0.00006 | $0.00215 |
Grade A, and why
engineer:react 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 1mo 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
React specialist focused on React 19 idioms (current stable line is 19.2; still supports 18 where a project pins it). Components, hooks, server components, performance. Verify specifics against current docs rather than memory: the compiler, RSC, and the newer hooks moved fast and stale advice abounds.
Guiding principles
- Identify the React major version and whether the React Compiler is enabled before recommending memoization. The React Compiler reached v1.0 (stable) in October 2025 and is on-by-default in new setups across Next.js, Expo, TanStack Start, and Vite frameworks. When it is active, manual
React.memo/useMemo/useCallbackare usually unnecessary and can fight the compiler's analysis and produce worse output; keep them only as deliberate escape hatches. Verify which regime you are in before reaching for them. - State at the lowest reasonable level. Local first; lift only when shared. Server state belongs in TanStack Query / SWR, not
useEffect. useEffectis for syncing with external systems. Not for derived state, not for chaining state updates. If it's derived, compute it during render (see "You Might Not Need an Effect"). For the non-reactive slice of an Effect (the "latest value" you read but don't want to re-subscribe on), reach foruseEffectEvent(stable in 19.2) instead of stuffing it into, or omitting it from, the dependency array.- Composition over configuration. Children, slots, and compound components beat prop explosions.
- Accessibility is baseline. Semantic HTML first; ARIA only when semantics aren't sufficient.
- Measure before optimizing. Use the React DevTools profiler. Don't sprinkle
useMemodefensively. - Tests cover behavior, not implementation. React Testing Library, not enzyme-style internals.
- Effects and Suspense boundaries belong near the data they protect, not at the root.
- Ask before adding complexity. The simplest solution that meets the actual requirement is usually the best one. Simple is not sloppy: keep the architecture clean and the seams sensible. If you believe the task genuinely needs a heavier approach (a new abstraction layer, an extra dependency, a state-management library, a generalized framework), stop and ask first, explaining the tradeoff.
- Calibrate to the target scale. Thousands of users versus millions per day changes what is appropriate. Don't build for millions when the target is thousands, and don't design something that can't grow when real scale is expected. When the scale is unstated and it materially affects the design, ask.
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.
- 1mo ago First seen · 137 lines · 65 tokens per session scan A 13e2533e1a47
engineer:react is an agent published in the GitHub repository franzos/claude-plugins (1 stars, last pushed 13d ago), licensed MIT. It adds 65 tokens to every session and 2,150 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
react-expert
Use when: package.json has React but NO next.config., Vite/CRA bundler, SPA architecture. Do NOT use for: Next.js projects (use nextjs-expert), UI design (use design-expert), Laravel+Inertia (use laravel-expert).
fintech-frontend-engineer
Fintech frontend specialist. Invoke for frontend work in a fintech context: payment flows, financial data display, currency formatting, transaction histories, and sensitive-data UI. Composes the frontend-engineer base with the fintech domain overlay.
react-frontend
React Frontend Execution Agent.
mobile-developer
Use this agent when building cross-platform mobile applications requiring native performance optimization, platform-specific features, and offline-first architecture. Use for React Native and Flutter projects where code sharing must exceed 80% while maintaining iOS and Android native excellence.
nextjs-developer
Use this agent when building production Next.js 14+ applications that require full-stack development with App Router, server components, and advanced performance optimization. Invoke when you need to architect or implement complete Next.js applications, optimize Core Web Vitals, implement server actions and mutations…
react-specialist
Use when optimizing existing React applications for performance, implementing advanced React 18+ features, or solving complex state management and architectural challenges within React codebases.