🎩 You're Invited:Meet the Socket team at Black Hat in Las Vegas, August 3-6.RSVP
Sign In

@nanomind/router

Package Overview
Dependencies
Maintainers
1
Versions
4
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

@nanomind/router

Intent classification and command mapping for CLI tools

latest
Source
npmnpm
Version
0.1.3
Version published
Maintainers
1
Created
Source

@nanomind/router

Intent classification and command mapping for CLI security tools. Classifies natural language into 17 intent types including 6 security scanning intents.

Install

npm install @nanomind/router

Usage

import { classifyIntent, mapToCommand, isScanIntent } from '@nanomind/router';

const result = classifyIntent('scan this project for vulnerabilities');
// { intent: 'SCAN', confidence: 0.85, entities: {} }

const cmd = mapToCommand(result, 'hma');
// { command: 'hma secure', args: ['.'], description: 'Run security scan' }

// Check if an intent is a security scan (needs full model inference)
isScanIntent('SCAN_SKILL'); // true
isScanIntent('EXPLAIN');     // false

Intent Types

General Intents

IntentExampleMaps To
SCAN"scan this project"hma secure
FIX"fix the credential issue"hma secure --fix
EXPLAIN"what does CRED-001 mean"hma explain CRED-001
TRUST_QUERY"what's the trust level"hma trust
ATC_STATUS"why is my agent level 2"opena2a identity status
ATTEST"add trust to my CI"opena2a identity attest
PROTECT"protect my credentials"secretless-ai init
REVIEW"review my project security"opena2a review
HELP"how do I use this"--help
CONFIG"set my API key"opena2a config
UNKNOWN(low confidence)Show suggestions

Security Scanning Intents (SCAN_*)

These intents require full NanoMind model inference via the daemon. Used by HackMyAgent's Semantic Compiler.

IntentPurposeUsed By
SCAN_SKILLClassify skill artifacts for attack patternsSemanticCompiler
SCAN_MCPAnalyze MCP server configurationsSemanticCompiler
SCAN_SOULEvaluate governance document completenessSemanticCompiler
SCAN_CREDENTIALDetect credential exposure in contextSemanticCompiler
SCAN_CODEIdentify code injection patternsSemanticCompiler
COMPILE_ASTFull AST compilation (all analyzers)SemanticCompiler

Confidence Scoring

The classifier returns a confidence score between 0 and 1:

RangeMeaning
0.8-1.0High confidence, route directly
0.5-0.8Medium confidence, may prompt for clarification
0.0-0.5Low confidence, show suggestions

License

MIT

Keywords

nanomind

FAQs

Package last updated on 28 Apr 2026

Did you know?

Socket

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Install

Related posts