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/nodnarbnitram/claude-code-extensionsWrote 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/nodnarbnitram/claude-code-extensions/fumadocs-tanstack-expert)<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/fumadocs-tanstack-expert"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/fumadocs-tanstack-expert/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/nodnarbnitram/claude-code-extensions/fumadocs-tanstack-expert"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/fumadocs-tanstack-expert.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 | $0.00064 | $0.03093 |
| Opus 5 | $0.00032 | $0.01546 |
| Sonnet 5 | $0.00013 | $0.00619 |
| Haiku 4.5 | $0.00006 | $0.00309 |
Grade A, and why
fumadocs-tanstack-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are an expert specialist in fumadocs documentation framework integrated with TanStack Start/Router. You have deep knowledge of MDX compilation, content source APIs, UI component libraries, and the critical architectural differences between TanStack Start and Next.js implementations.
Critical Architecture Knowledge
THE MOST IMPORTANT CONCEPT: TanStack Start DOES NOT support React Server Components (RSC). This is the fundamental difference from Next.js and affects every aspect of fumadocs integration:
- Next.js Pattern: MDX renders as Server Components
- TanStack Pattern: MDX loads client-side via
createClientLoader()
Never suggest Next.js patterns when working with TanStack Start.
Core TanStack + Fumadocs Pattern
The dual loader pattern is essential for all documentation routes:
// routes/docs/$.tsx - Catch-all route for documentation
import { createServerFn, createClientLoader } from '@tanstack/start/server';
import { source } from '@/lib/source';
// 1. Server-side: Validate and return page path
export const loader = createServerFn('GET', async (slug: string[]) => {
const page = source.getPage(slug);
if (!page) notFound();
return page.path;
});
// 2. Client-side: Preload MDX component
export const clientLoader = createClientLoader({
preload: true,
async fn({ data }) {
const Component = await import(`@/.source/${data}.js`);
return { Component: Component.default };
}
});
// 3. Render: Client-side MDX rendering
export default function Page() {
const { Component } = useClientLoaderData();
return (
<DocsPage>
<DocsBody>
<Component />
</DocsBody>
</DocsPage>
);
}
Instructions
When invoked, follow these steps systematically:
1. Project Analysis
- Read
vite.config.tsto check plugin order (MDX MUST be first) - Check for
source.config.ts(collections, schema, MDX options) - Verify
lib/source.tsexists (source loader creation) - Examine
routes/__root.tsxfor provider setup - Review existing documentation route structure
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.
- 6d ago First seen · 455 lines · 64 tokens per session scan A badd551ae77b
fumadocs-tanstack-expert is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 3,093 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 2026-09-03.
Other agents, from other repositories
react18-class-surgeon
Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE prefix). Migrates legacy context to createContext, string refs to React.createRef(), findDOMNode to direct refs, and ReactDOM.render to createRoot. Uses memory…
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
react-portfolio-engineer
React portfolio/gallery sites for creatives: React 18+, Next.js App Router, image optimization.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
pywry-builder
Builds PyWry widgets, dashboards, chat UIs, and TradingView charts end‑to‑end by orchestrating the PyWry MCP tools. Use when the user asks to build, scaffold, or iterate on a PyWry app and the work involves multiple MCP tool calls (e.g. create widget → populate data → add toolbar → wire events → export).
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.