Borrowing it
Nothing to install: this file belongs to priyansh-narang2308/TheBlacklisted-NitroStack. 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/priyansh-narang2308/TheBlacklisted-NitroStack/main/.agents/skills/mcp-app-architecture/SKILL.mdgit clone --depth 1 https://github.com/priyansh-narang2308/TheBlacklisted-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/skills/priyansh-narang2308/theblacklisted-nitrostack/mcp-app-architecture)<a href="https://agentmods.dev/skills/priyansh-narang2308/theblacklisted-nitrostack/mcp-app-architecture"><img src="https://agentmods.dev/badge/skills/priyansh-narang2308/theblacklisted-nitrostack/mcp-app-architecture/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/skills/priyansh-narang2308/theblacklisted-nitrostack/mcp-app-architecture"><img src="https://agentmods.dev/badge/skills/priyansh-narang2308/theblacklisted-nitrostack/mcp-app-architecture.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 | $0.00040 | $0.01372 |
| Opus 5.5 | $0.00016 | $0.00549 |
| Sonnet 5.5 | $0.00008 | $0.00274 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
nitrostack-mcp-app-architecture 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 2mo 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.
This is a copy
100% identical to nitrostack-mcp-app-architecture — 0 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
Use this skill whenever you are bootstrapping a new NitroStack MCP server, creating modules, injecting services, or handling application lifecycle events.
Bootstrapping a NitroStack App
A NitroStack application is initialized with the @McpApp decorator on a root class, accompanied by a root @Module.
import { McpApp, Module } from '@nitrostack/core';
import { DatabaseModule } from './database/database.module.js';
import { UsersModule } from './users/users.module.js';
@McpApp({
module: AppModule,
server: {
name: 'user-management-server',
version: '1.0.0',
},
})
@Module({
imports: [DatabaseModule, UsersModule],
})
export class AppModule {}
Modules
Modules organize your application structure. Use the @Module decorator to define imports, exports, and providers.
imports: Other modules whose exported providers should be available in this module.providers: Services, tools, resources, or prompts that should be instantiated and managed by the DI container within this module.exports: Providers defined in this module that should be visible to other modules importing this one.
import { Module } from '@nitrostack/core';
import { UsersService } from './users.service.js';
import { UsersTools } from './users.tools.js';
@Module({
providers: [UsersService, UsersTools],
exports: [UsersService],
})
## Controllers
Use the `@ControllerDecorator` (or alias it as `@Controller`) to group tools, resources, and prompts together. Controllers are automatically registered as singletons in the DI container.
### Key Controller Options:
* **`prefix`**: A string prefix applied to every `@Tool` defined in this controller. For example, `@ControllerDecorator('github')` prefixing a tool named `create_issue` exposes it to MCP clients as `github_create_issue`.
```typescript
import { ControllerDecorator as Controller, Tool, ExecutionContext } from '@nitrostack/core';
@Controller('github')
export class GitHubController {
@Tool({
name: 'create_issue',
description: 'Create an issue in a repository',
inputSchema: z.object({ /* ... */ })
})
async createIssue(input: any, ctx: ExecutionContext) {
// Exposed to clients as "github_create_issue"
}
}
Dependency Injection (DI)
NitroStack uses a robust dependency injection container to manage class instances and lifecycles.
Injection Lifecycles
- Singleton (Default): A single instance is shared across the entire application.
- Transient: A new instance is created every time it is resolved/injected.
- Scoped: A new instance is created per incoming request or context.
import { Injectable, Scope } from '@nitrostack/core';
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.
- 2mo ago First seen · 177 lines · 40 tokens per session scan A 9c6d1a289226
nitrostack-mcp-app-architecture is a skill published in the GitHub repository priyansh-narang2308/TheBlacklisted-NitroStack (5 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 1,372 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to nitrostack-mcp-app-architecture, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
td-api-reference
MUST READ before writing TD Python via executepython, setdatcontent, or editdatcontent, and before any heavy build. Parameters, storage, operators, referencing, threading, cook model, heavy-build safety caps.
manage-annotations
MUST READ before creating, modifying, or querying annotations. Contains parameter names, coordinate model, and API quirks.
pipefy-api-fallback
Use this skill when a toolkit operation fails AND the introspection skill could not resolve the problem. This is the last-resort fallback (Tier 3): call the Pipefy GraphQL API directly using curl or httpx, authenticating with the Service Account (OAuth2) or a Personal Access Token (PAT) available as env var. Follow…
pipefy-ipaas
Use when the user wants to build, test, publish, or manage iPaaS (Advanced Automations) flows: multi-step integrations with external apps (Slack, Gmail, Google Sheets), incoming webhooks, schedules, routers, code steps, or iPaaS data tables. Driven through a per-pipe catalog discovered at runtime. For native if/then…
watch
Watch live IDX turnover and order books for unusual activity — value surges, auto-reject approach, one-sided depth, walls appearing or withdrawn, quiet stocks waking up, UMA flags — plus delayed print-by-print attribution and end-of-day broker context. Use when the user runs /watch, or asks what is trading right now…
pipefy-introspection
Use this skill when you need to discover GraphQL type shapes, mutation signatures, enum values, or execute arbitrary GraphQL as a fallback. This is the first fallback tier (Tier 2) when dedicated operations fail or don't exist for an operation.