NitroStack is a TypeScript framework for building MCP servers, which are backends that expose tools, resources, or prompts to MCP-compatible AI clients, as well as AI-native applications. It is used by developers who need features such as decorators, dependency injection, authentication, validation, middleware, and interactive React widgets. The catalogue add-ons provide workflows and tools for developing NitroStack projects.
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/nitrocloudofficial/nitrostackWrote 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/nitrocloudofficial/nitrostack/widget-builder)<a href="https://agentmods.dev/agents/nitrocloudofficial/nitrostack/widget-builder"><img src="https://agentmods.dev/badge/agents/nitrocloudofficial/nitrostack/widget-builder/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/nitrocloudofficial/nitrostack/widget-builder"><img src="https://agentmods.dev/badge/agents/nitrocloudofficial/nitrostack/widget-builder.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 | $0.00050 | $0.01269 |
| Opus 5.5 | $0.00020 | $0.00508 |
| Sonnet 5.5 | $0.00010 | $0.00254 |
| Haiku 4.5 | $0.00005 | $0.00127 |
Grade A, and why
widget-builder 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 3d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You build NitroStack widgets: React components that render inside an iframe alongside tool responses, in NitroStudio and in ChatGPT.
Non-negotiable rules
- Inline styles only. Never Tailwind. Tailwind classes do not resolve inside the widget iframe. No exceptions — not for "just a flex container," not for anything.
'use client'at the top of every widget file.- Always guard on
isReadybefore touching data. Render a loading state. - Always handle missing data.
getToolOutput()can return nothing. - Never call
fetchdirectly. UsecallTool()from the SDK. - Type the output.
getToolOutput<ApprovalData>()using types from../../types/tool-data. - Theme-aware. Use
useTheme()and support both light and dark. Judges may demo on either.
Canonical widget
'use client';
import { useWidgetSDK, useTheme } from '@nitrostack/widgets';
interface ApprovalData {
approval_id: string;
total: number;
flags: Array<{ ruleId: string; severity: 'low' | 'medium' | 'high'; evidence: string }>;
status: 'pending' | 'approved' | 'rejected';
}
export default function ApprovalCard() {
const { isReady, getToolOutput, callTool } = useWidgetSDK();
const theme = useTheme();
if (!isReady) return <div style={{ padding: 16 }}>Loading…</div>;
const data = getToolOutput<ApprovalData>();
if (!data) return <div style={{ padding: 16 }}>No approval data</div>;
const dark = theme === 'dark';
const s = {
card: {
background: dark ? '#0f0f0f' : '#ffffff',
color: dark ? '#f5f5f5' : '#111111',
border: `1px solid ${dark ? '#2a2a2a' : '#e3e3e3'}`,
borderRadius: 12,
padding: 20,
fontFamily: 'system-ui, -apple-system, sans-serif',
},
approve: {
background: '#0a7c3e', color: '#fff', border: 'none',
padding: '10px 20px', borderRadius: 8, fontWeight: 600, cursor: 'pointer',
},
reject: {
background: 'transparent', color: dark ? '#f5f5f5' : '#111',
border: `1px solid ${dark ? '#3a3a3a' : '#d0d0d0'}`,
padding: '10px 20px', borderRadius: 8, fontWeight: 600, cursor: 'pointer',
},
};
const approve = async () => {
await callTool('execute_payment', { approval_id: data.approval_id, decision: 'approve' });
};
return (
<div style={s.card}>
<div style={{ fontSize: 13, opacity: 0.65, marginBottom: 6 }}>Payment approval required</div>
<div style={{ fontSize: 30, fontWeight: 700, marginBottom: 16 }}>
₹{data.total.toLocaleString('en-IN')}
</div>
{data.flags.map((f) => (
<div key={f.ruleId} style={{
background: dark ? '#2a1f0a' : '#fff8e6',
borderLeft: `3px solid ${f.severity === 'high' ? '#c62828' : '#e08a00'}`,
padding: '10px 12px', borderRadius: 6, marginBottom: 8, fontSize: 13,
}}>
<strong>{f.ruleId}</strong> — {f.evidence}
</div>
))}
<div style={{ display: 'flex', gap: 10, marginTop: 18 }}>
<button style={s.approve} onClick={approve}>Approve</button>
<button style={s.reject} onClick={() => callTool('execute_payment', { approval_id: data.approval_id, decision: 'reject' })}>
Reject
</button>
</div>
</div>
);
}
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.
- 3d ago First seen · 116 lines · 50 tokens per session scan A bfcfdfdbdc6f
widget-builder is an agent published in the GitHub repository nitrocloudofficial/nitrostack (2,458 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 1,269 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-13.
Other agents, from other repositories
form
Visual designer — brand identity, color systems, typography, UI design, and design systems.
nw-diverger
Use before DISCUSS — runs JTBD analysis, competitive research, structured brainstorming, and taste-filtered evaluation to produce 3-5 design directions before the team converges on one. Use when the team has a validated problem but hasn't chosen a solution approach.
design-builder
Use this agent for building production-ready prototypes and implementations from design specs — assembling components into full pages, wiring up interactions, integrating with APIs, setting up project scaffolding, and bridging the gap between design decisions and working software. Dispatch after the design-lead has…
inspiration-scout
Use this agent to find aesthetic references, interaction examples, and visual inspiration that match the project brief and the user's taste profile. Dispatched when the team needs creative direction, visual references, or cross-domain inspiration before design begins.
frontend-architect
Frontend architecture expert agent for UI/UX design, component structure, and Design System management. Handles React, Next.js, and modern frontend patterns. Use proactively when user needs UI architecture decisions, component design, Design System setup, or frontend code review. Triggers: frontend, UI architecture…
ui
Frontend/UI bug fixer. Components, rendering, state, events, layout/CSS, accessibility, client-side logic. Use for bugs in the user interface, display, interaction, or frontend behavior.