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 agents/franzos/claude-plugins/engineer-reactgit clone --depth 1 https://github.com/franzos/claude-pluginsWhat 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 | $0.00065 | $0.02150 |
| Opus 5 | $0.00032 | $0.01075 |
| Sonnet 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 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.
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.
- yesterday 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 20d ago), licensed MIT. It adds 65 tokens to every session and 2,150 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.