nitrostack-auth-security

Security guidance for NitroStack applications, covering ways to verify users and control access to tools. It includes JSON Web Tokens (signed data used to identify a user), API keys, OAuth 2.1, and role-based access control.

In plain words
What is it for?
Use it to add login checks, configure JWT or API-key authentication, connect OAuth 2.1, restrict tools with guards, and enforce permissions based on user roles.
Why use it?
It helps prevent unauthorised users from calling protected tools or accessing sensitive data. It also provides patterns for checking tokens and assigning user roles.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/nitrocloudofficial/nitrostack/auth-security
Any agent
npx skills add nitrocloudofficial/nitrostack --skill auth-security
Clone the repo
git clone --depth 1 https://github.com/nitrocloudofficial/nitrostack

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 828 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.00828
Opus 5 $0.00015 $0.00414
Sonnet 5 $0.00006 $0.00166
Haiku 4.5 $0.00003 $0.00083

Measured 2d ago against content hash 5408d8946e47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nitrostack-auth-security 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 2d 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.

Origin

Copies of this mod

6 near-identical copies found in the catalogue:

sample-apps/AI-Scheduler-NitroStack-Hackathon/.agents/skills/auth-security/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to Use

Use this skill when configuring security modules, implementing user authentication, restricting tool access via guards, or handling sensitive tokens.


1. JSON Web Tokens (JWT)

To secure tools with JWT authentication:

Register JWTModule:

import { JWTModule, Module, McpApp } from '@nitrostack/core';

@McpApp({
  server: { name: 'my-server', version: '1.0.0' }
})
@Module({
  imports: [
    JWTModule.forRoot({
      secret: process.env.JWT_SECRET!,
      expiresIn: '7d',
    }),
  ]
})
export class AppModule {}

Write a JWTGuard:

import { Guard, ExecutionContext, Injectable, ConfigService } from '@nitrostack/core';
import * as jwt from 'jsonwebtoken';

@Injectable()
export class JWTGuard implements Guard {
  constructor(private config: ConfigService) {}

  async canActivate(context: ExecutionContext): Promise<boolean> {
    const token = this.extractToken(context);
    if (!token) return false;

    try {
      const secret = this.config.get('JWT_SECRET');
      const payload = jwt.verify(token, secret) as any;
      context.auth = {
        subject: payload.sub,
        role: payload.role,
        token,
      };
      return true;
    } catch {
      return false;
    }
  }

  private extractToken(context: ExecutionContext): string | null {
    const auth = context.metadata?.authorization;
    if (auth?.startsWith('Bearer ')) {
      return auth.substring(7);
    }
    return null;
  }
}

2. API Key Authentication

Use ApiKeyModule for service-to-service validation.

Register ApiKeyModule:

import { ApiKeyModule, Module } from '@nitrostack/core';

@Module({
  imports: [
    ApiKeyModule.forRoot({
      keysEnvPrefix: 'API_KEY', // Reads API_KEY_1, API_KEY_2, etc.
      headerName: 'x-api-key',
      hashed: false,
    }),
  ]
})
export class AppModule {}

API Key Guard:

import { Guard, ExecutionContext, ApiKeyModule } from '@nitrostack/core';

export class ApiKeyGuard implements Guard {
  async canActivate(context: ExecutionContext): Promise<boolean> {
    const apiKey = context.metadata?.['x-api-key'] || context.metadata?.apiKey;
    if (!apiKey) return false;

    const isValid = await ApiKeyModule.validate(apiKey as string);
    if (isValid) {
      context.auth = {
        subject: `apikey_${(apiKey as string).substring(0, 10)}`,
        scopes: ['*'],
      };
      return true;
    }
    return false;
  }
}

Read the full file on GitHub · 142 lines

Changes

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.

  1. 2d ago First seen · 142 lines · 30 tokens per session scan A 5408d8946e47

Subscribe to this mod's changes

nitrostack-auth-security is a skill published in the GitHub repository nitrocloudofficial/nitrostack (2,505 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 828 once invoked, about $0.0002 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 2026-08-30.