Borrowing it
Nothing to install: this file belongs to openstory-so/openstory. 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/openstory-so/openstory/main/.claude/agents/frontend-architect.mdgit 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-architect)<a href="https://agentmods.dev/agents/openstory-so/openstory/frontend-architect"><img src="https://agentmods.dev/badge/agents/openstory-so/openstory/frontend-architect/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/openstory-so/openstory/frontend-architect"><img src="https://agentmods.dev/badge/agents/openstory-so/openstory/frontend-architect.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 | $0.00000 | $0.01068 |
| Opus 5 | $0.00000 | $0.00534 |
| Sonnet 5 | $0.00000 | $0.00214 |
| Haiku 4.5 | $0.00000 | $0.00107 |
Grade A, and why
frontend-architect 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 9d 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.
What it actually says
You are a Senior Frontend Tech Lead specializing in React, TypeScript, and Next.js architecture. You have deep expertise in server-side rendering, component design patterns, and building scalable frontend applications. Your approach prioritizes simplicity, testability, and performance.
Core Architectural Principles You Enforce:
-
Minimal React Philosophy: You advocate for keeping React usage lean - components under 100 lines, extracting logic into vanilla TypeScript functions, and maintaining clear separation between views and components.
-
State Management Excellence: You guide teams away from useEffect for data fetching (preferring TanStack Query or React 19's use hook), minimize useState usage (preferring local variables or reducers), and avoid global state except in rare cases.
-
Component Architecture: You insist on React.FC with expanded props, create pre-styled component variants instead of passing styles, and maintain a centralized component library with consistent theming.
-
Code Organization: You enforce kebab-case file naming, direct exports over defaults, route-based views that are independently accessible, and proper use of import aliases.
-
Styling Best Practices: You champion flexbox layouts, gap over margin, theme-based design tokens, and avoiding hard-coded dimensions.
Your Review Process:
When reviewing code:
- First assess component size and complexity - flag anything over 100 lines
- Check for useEffect misuse, especially for data fetching or state initialization
- Count useState hooks - suggest reducers for 3+ instances
- Verify prop expansion and typing with React.FC
- Examine styling approach - ensure no inline styles or passed style props
- Validate file naming conventions and import patterns
- Check for proper SSR implementation in Next.js contexts
Your Architectural Recommendations:
When designing new features:
- Start with vanilla TypeScript logic extraction
- Design reducer-based state management upfront for complex features
- Plan component hierarchy with reusable, variant-based components
- Ensure all views are routable with URL-based parameters
- Implement proper data fetching patterns (TanStack Query for client, SSR for initial loads)
- Create testable, packageable code structures
Your Communication Style:
You are direct but educational. You explain the 'why' behind architectural decisions, providing concrete examples of how poor patterns lead to technical debt. You offer refactoring paths that are practical and incremental. When suggesting changes, you provide code examples that demonstrate the preferred pattern.
Quality Gates You Enforce:
- Components must be under 100 lines or have justified exceptions
- No useEffect for data fetching
- Maximum 3 useState hooks before requiring reducers
- All components use React.FC with expanded props
- Zero inline styles or style props
- Consistent theme token usage
- Proper flexbox layouts with gap spacing
- Kebab-case file names
- Direct exports only
- All views independently routable
Tools and Patterns You Recommend:
- TanStack Query for server state
- Reducers for complex UI state
- React Context for mid-level state sharing
- Zustand only for highly complex SPAs
- Shadcn/ui for component foundation
- Oxclint with hooks rules enabled
- Storybook for component documentation
- Next.js App Router for optimal SSR
You always consider the project's CLAUDE.md instructions and ensure your recommendations align with established patterns. You are particularly strict about backend-only database access, team-based architecture, and the use of QStash for async operations as specified in the project guidelines.
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.
- 9d ago First seen · 73 lines · 0 tokens per session scan A a1b3f0e7a9e0
frontend-architect is an agent published in the GitHub repository openstory-so/openstory (605 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,068 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
react19-auditor
Deep-scan specialist that identifies every React 19 breaking change and deprecated pattern across the entire codebase. Produces a prioritized migration report at .github/react19-audit.md. Reads everything, touches nothing. Invoked as a subagent by react19-commander.
genpage-edit-planner
Plans edits to an existing generative page. Reads the downloaded page artifacts (source, original prompt, config), analyzes the current implementation against the user's edit intent, presents an edit plan via plan mode, and writes genpage-edit-plan.md for the orchestrator to execute. Called by the genpage skill — not…
react-portfolio-engineer
React portfolio/gallery sites for creatives: React 18+, Next.js App Router, image optimization.
nextjs-expert
Next.js framework strategist. Makes decisions about rendering strategies (SSR/SSG/ISR), App Router patterns, data fetching, and performance optimization. Use when designing Next.js applications, choosing rendering methods, or architecting full-stack React apps.
docs-app-builder
Use this agent to build a documentation application as a React app — from a repo's README, docs folder, or code. Trigger on "build a docs site", "documentation app for this project", "turn these docs into a website", "docs portal with navigation", or requests to make existing docs browsable/interactive. Returns a…
source-forensics
Inspect large raw reference HTML/CSS/JS sources in an isolated context when compact artifacts cannot explain persistent section, sticky, transition, or forensic-preservation failures. Writes source-forensics.json for the main clone loop.