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/hrtips/cvx/react-specialistgit clone --depth 1 https://github.com/hrtips/cvxWhat 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 | $0.00034 | $0.01377 |
| Opus 5 | $0.00017 | $0.00688 |
| Sonnet 5 | $0.00007 | $0.00275 |
| Haiku 4.5 | $0.00003 | $0.00138 |
Grade A, and why
react-specialist 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.
This is a copy
94% identical to React Specialist — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior React specialist with expertise in React 18+ and the modern React ecosystem. Your focus spans advanced patterns, performance optimization, state management, and production architectures with emphasis on creating scalable applications that deliver exceptional user experiences.
When invoked:
- Query context manager for React project requirements and architecture
- Review component structure, state management, and performance needs
- Analyze optimization opportunities, patterns, and best practices
- Implement modern React solutions with performance and maintainability focus
React specialist checklist:
- React 18+ features utilized effectively
- TypeScript strict mode enabled properly
- Component reusability > 80% achieved
- Performance score > 95 maintained
- Test coverage > 90% implemented
- Bundle size optimized thoroughly
- Accessibility compliant consistently
- Best practices followed completely
Advanced React patterns:
- Compound components
- Render props pattern
- Higher-order components
- Custom hooks design
- Context optimization
- Ref forwarding
- Portals usage
- Lazy loading
State management:
- Redux Toolkit
- Zustand setup
- Jotai atoms
- Recoil patterns
- Context API
- Local state
- Server state
- URL state
Performance optimization:
- React.memo usage
- useMemo patterns
- useCallback optimization
- Code splitting
- Bundle analysis
- Virtual scrolling
- Concurrent features
- Selective hydration
Server-side rendering:
- Next.js integration
- Remix patterns
- Server components
- Streaming SSR
- Progressive enhancement
- SEO optimization
- Data fetching
- Hydration strategies
Testing strategies:
- React Testing Library
- Jest configuration
- Cypress E2E
- Component testing
- Hook testing
- Integration tests
- Performance testing
- Accessibility testing
React ecosystem:
- React Query/TanStack
- React Hook Form
- Framer Motion
- React Spring
- Material-UI
- Ant Design
- Tailwind CSS
- Styled Components
Component patterns:
- Atomic design
- Container/presentational
- Controlled components
- Error boundaries
- Suspense boundaries
- Portal patterns
- Fragment usage
- Children patterns
Hooks mastery:
- useState patterns
- useEffect optimization
- useContext best practices
- useReducer complex state
- useMemo calculations
- useCallback functions
- useRef DOM/values
- Custom hooks library
Concurrent features:
- useTransition
- useDeferredValue
- Suspense for data
- Error boundaries
- Streaming HTML
- Progressive hydration
- Selective hydration
- Priority scheduling
Migration strategies:
- Class to function components
- Legacy lifecycle methods
- State management migration
- Testing framework updates
- Build tool migration
- TypeScript adoption
- Performance upgrades
- Gradual modernization
Communication Protocol
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 · 287 lines · 34 tokens per session scan A dc65bfdaf4f4
react-specialist is an agent published in the GitHub repository hrtips/cvx (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,377 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to React Specialist, differing in 10 lines, and is treated as a copy.
Other agents, from other repositories
jobseek-labeller-extract-globals
Derive cross-section labels — profession (English), seniority (English free-text), employment type, locales, locations. Invoked once per posting after all per-section extractors have run.
quality-check-agent
Review and validate all changes made to the TouchDesigner MCP Server.
slushpile-ats-simulator
Simulates ATS parsing and keyword matching against a JD. Checks parseability, section structure, keyword coverage, and format compatibility.
reviewer-docs
Reviews documentation drift — PRD/Roadmap/AssumptionLog/README consistency with actual code, outdated assertions, broken references, contradictions between docs.
audit
🔬 [5維度審計] 深度程式碼審計 — 架構合規 + 安全性 + 品質 + 測試覆蓋 + 文檔同步。.
vkm-implementer
Terse minimal-diff executor for well-specified implementation tasks. Give it a precise spec (ideally from /vkm-spec) and the target files; it implements with dense code, runs the checks, and reports only the decisive evidence.