CONFIGURATION

A configuration guide for NeuroLink’s Multi-Agent Networks feature, where multiple AI agents cooperate or delegate work. It describes the settings for each agent, such as its instructions, AI provider, model, tools, input, output, and limits.

In plain words
What is it for?
Use it to create agent definitions, choose providers and models, limit available tools or execution steps, and configure validation for agent inputs and outputs.
Why use it?
It puts the available configuration choices in one place so developers can define agents consistently. It also explains settings that control delegation and how agent inputs and outputs are checked.

Agent

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 agents/juspay/neurolink/configuration
Clone the repo
git clone --depth 1 https://github.com/juspay/neurolink
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,302 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 $0.00000 $0.02302
Opus 5 $0.00000 $0.01151
Sonnet 5 $0.00000 $0.00460
Haiku 4.5 $0.00000 $0.00230

Measured 3d ago against content hash c13a16637b7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CONFIGURATION 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.

docs/agents/CONFIGURATION.md · 469 lines

How it starts

The opening of the file, as written. The whole thing — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Agent Networks Configuration Guide

Overview

This document describes all configuration options for the Multi-Agent Networks feature in NeuroLink.

Agent Configuration

AgentDefinition

The core configuration for creating an agent:

type AgentDefinition = {
  /** Unique identifier for the agent */
  id: string;

  /** Human-readable name */
  name: string;

  /** Description of capabilities (used by the router to select this agent) */
  description: string;

  /** System instructions for the agent */
  instructions: string;

  /** AI provider to use (optional, falls back to NeuroLink default) */
  provider?: AIProviderName | string;

  /** Model to use (optional, falls back to provider default) */
  model?: string;

  /** Tool names available to this agent (filters the global tool set) */
  tools?: string[];

  /** Input schema for validation (Zod schema) */
  inputSchema?: z.ZodSchema;

  /** Output schema for parsing (Zod schema) */
  outputSchema?: z.ZodSchema;

  /** Maximum steps per execution */
  maxSteps?: number;

  /** Temperature for generation */
  temperature?: number;

  /** Whether agent can delegate to others */
  canDelegate?: boolean;

  /** Custom metadata */
  metadata?: Record<string, unknown>;
};

Example Agent Configurations

Basic Agent
const basicAgent: AgentDefinition = {
  id: "assistant",
  name: "General Assistant",
  description: "A helpful general-purpose assistant",
  instructions: "You are a helpful assistant. Answer questions concisely.",
};
Specialized Agent with Tools
const codeAgent: AgentDefinition = {
  id: "code-analyzer",
  name: "Code Analysis Agent",
  description: "Analyzes code for bugs, security issues, and improvements",
  instructions: `You are an expert code analyst. Examine code carefully and:
    1. Identify potential bugs
    2. Flag security vulnerabilities
    3. Suggest improvements
    4. Follow best practices`,
  provider: "anthropic",
  model: "claude-3-5-sonnet-20241022",
  tools: ["readFile", "searchCode", "lintCode"],
  maxSteps: 15,
  temperature: 0.3,
  canDelegate: false,
  metadata: {
    expertise: ["typescript", "javascript", "python"],
    analysisTypes: ["bugs", "security", "performance"],
  },
};

Read the full file on GitHub · 469 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. 3d ago First seen · 469 lines · 0 tokens per session scan A c13a16637b7c

Subscribe to this mod's changes

CONFIGURATION is an agent published in the GitHub repository juspay/neurolink (128 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,302 tokens. 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.

Related

Other agents, from other repositories

claude-design-orchestrator

Parses claude.ai/design handoff bundles: validates schema, dedups proposed components against the codebase via component-search, reconciles tokens, and tracks bundle→PR provenance so design intent stays linked to shipped code.

yonatangross/orchestkit · 51 tokens

accessibility-specialist

Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.

yonatangross/orchestkit · 33 tokens

database-engineer

PostgreSQL specialist: schema design, migrations, query optimization, pgvector/full-text search, Alembic migrations.

yonatangross/orchestkit · 28 tokens

demo-producer

Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.

yonatangross/orchestkit · 42 tokens

emulate-engineer

Stateful API emulation via Vercel emulate. Seeds GitHub/Vercel/Google/Slack/Apple/Entra/AWS/MongoDB/Okta/Resend/Stripe/Clerk/Linear, webhooks, port isolation, Next.js adapter. Use to replace flaky API mocks.

yonatangross/orchestkit · 67 tokens

vc-validate-agent

VALIDATE MODE - Convert a written plan into an executable contract. Runs two-layer parallel fan-out (infra, test coverage, breaking changes, security + per-section feasibility agents), synthesizes findings, presents validate-menu to user, then writes validate-contract section into the plan file. Mandatory phase…

withkynam/vibecode-pro-max-kit · 74 tokens