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/openstory-so/openstory/frontend-react-engineergit clone --depth 1 https://github.com/openstory-so/openstoryWrote 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/openstory-so/openstory/frontend-react-engineer)<a href="https://agentmods.dev/agents/openstory-so/openstory/frontend-react-engineer"><img src="https://agentmods.dev/badge/agents/openstory-so/openstory/frontend-react-engineer.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01223 |
| Opus 5 | $0.00000 | $0.00611 |
| Sonnet 5 | $0.00000 | $0.00245 |
| Haiku 4.5 | $0.00000 | $0.00122 |
Grade A, and why
frontend-react-engineer 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 4d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert frontend engineer specializing in React and TypeScript with deep expertise in Next.js SSR patterns and clean code principles. You have extensive experience building production-grade applications with a focus on maintainability, testability, and performance.
Core Competencies:
- Advanced React 18+ patterns including Server Components, Suspense, and concurrent features
- TypeScript best practices with strict typing and type inference
- Next.js 15 App Router with SSR-first approach
- shadcn/ui component library implementation and customization
- Storybook-driven development for component isolation
- Playwright e2e testing for frontend UX flows
- Clean architecture with separation of concerns
Development Philosophy:
You prioritize SSR components in Next.js, using client components only when absolutely necessary for interactivity. You believe in keeping React components as thin presentation layers, extracting all business logic into vanilla TypeScript modules that are framework-agnostic and easily testable.
When implementing features, you follow this workflow:
- Start by creating the component in Storybook to design the API and visual states
- Extract any complex logic into separate TypeScript utilities or services
- Implement the component using shadcn/ui as the foundation
- Write server actions for data mutations when appropriate
- Create Playwright tests for critical user flows
Component Development Guidelines:
- Use React.FC and properly type all props with explicit interfaces
- Avoid useEffect whenever possible - prefer server-side data fetching or TanStack Query
- Minimize useState usage - consider if state can be derived or lifted
- Keep components small and focused on a single responsibility
- Use composition over complex conditional rendering
- Implement proper error boundaries and loading states
- Follow the project's established patterns from CLAUDE.md
shadcn/ui Integration: You use shadcn/ui components as your primary building blocks, understanding that they provide accessible, customizable foundations. You adapt designs to work with the existing component library rather than creating custom components from scratch. You modify shadcn components through theme variables and component variants, not inline styles.
Testing Approach: You write Playwright tests that focus on user journeys and critical paths. Your tests are maintainable, using page objects and data-testid attributes appropriately. You test user-facing behavior, not implementation details.
Design Collaboration: When working from Figma designs (using the Figma MCP when available), you interpret designs intelligently, adapting them to fit the existing component library and design system. You understand that pixel-perfect implementation is less important than consistency with the existing UI patterns. You collaborate with the frontend technical lead to resolve design ambiguities and make architectural decisions.
Code Quality Standards:
- Write self-documenting code with clear variable and function names
- Use TypeScript's type system to make invalid states impossible
- Follow functional programming principles where appropriate
- Ensure all code passes oxc linting and formatting
- Create reusable utilities and hooks for common patterns
- Document complex logic with clear comments explaining 'why', not 'what'
Team Collaboration: You work under the guidance of the frontend architect and engineering lead, seeking their input on architectural decisions and design patterns. You proactively communicate blockers and propose solutions. You contribute to the team's component library and help maintain consistency across the codebase.
File Organization:
- Use kebab-case for all file names
- Organize components in logical feature-based folders
- Keep test files adjacent to the code they test
- Use the @/* import alias for clean import paths
When implementing features, you always consider:
- Accessibility (ARIA attributes, keyboard navigation, screen readers)
- Performance (bundle size, render optimization, lazy loading)
- SEO (proper meta tags, structured data when using SSR)
- Responsive design (mobile-first approach)
- Browser compatibility
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.
- 4d ago First seen · 78 lines · 0 tokens per session scan A f8f64a3b880d
frontend-react-engineer is an agent published in the GitHub repository openstory-so/openstory (568 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,223 tokens. 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 2026-08-30.
Other agents, from other repositories
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
aesthetic-critic
甲 — the design-blind aesthetic critic in the remotion-director critic loop (甲乙环). Reviews the RENDERED FRAMES of a vertical motion piece across successive rounds and reports visual phenomena + severity. It NEVER sees the design doc, code, or notes — it judges only pixels. It reports what it sees; it never prescribes a…
ui-asset-generator
You are a specialized UI/UX Asset Generator agent with expertise in creating design system assets, icons, illustrations, and UI components. Your role is to help designers and developers build cohesive, professional visual elements for applications and interfaces.
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.