CLI-COVERAGE

A report describing command-line support for multi-agent networks, systems where several software agents can be created and run together. It also documents the corresponding software-development-kit support.

In plain words
What is it for?
Creating and listing agents, running agents and networks, and configuring them with inline options or JSON files.
Why use it?
It shows which agent and network operations are available from the terminal and through code.

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/cli-coverage
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 1,162 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 $0.01162
Opus 5 $0.00000 $0.00581
Sonnet 5 $0.00000 $0.00232
Haiku 4.5 $0.00000 $0.00116

Measured yesterday against content hash 7637b352311c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CLI-COVERAGE 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 yesterday.

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/CLI-COVERAGE.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Agent Networks CLI Coverage Report

Summary

The Multi-Agent Networks feature has full CLI coverage. All agent and network commands are implemented in src/cli/commands/agent.ts via the AgentCommandFactory class.

SDK Coverage

The SDK provides full programmatic access to Multi-Agent Networks:

import { NeuroLink } from "neurolink";

const neurolink = new NeuroLink();

// Create and execute an agent
const agent = neurolink.createAgent(definition);
const result = await agent.execute("Your input here");

// Create and execute a network
const network = neurolink.createNetwork(config);
const result = await neurolink.executeNetwork(network, { message: input });

CLI Coverage

Agent Commands

neurolink agent create

Create a new agent definition from inline flags or a JSON file.

# Inline flags
neurolink agent create \
  --id researcher \
  --name "Research Agent" \
  --description "Searches and analyzes information" \
  --instructions "You are a research assistant..." \
  --provider anthropic \
  --model claude-3-5-sonnet-20241022

# From a JSON file
neurolink agent create --file agent-config.json

Status: Implemented


neurolink agent list

List all agents registered in the current session.

neurolink agent list

neurolink agent list --format json

neurolink agent list --format table --detailed

Status: Implemented


neurolink agent execute / neurolink agent run

Execute a registered agent. run is an alias for execute.

neurolink agent execute researcher "Find information about AI trends"

neurolink agent run writer "Write a blog post" --stream

neurolink agent execute researcher "Analyze this" \
  --context '{"language": "typescript"}' \
  --maxSteps 15

Status: Implemented


Network Commands

neurolink network create

Create an agent network from a JSON configuration file.

neurolink network create \
  --name "Content Team" \
  --file network-config.json

# Override router settings
neurolink network create \
  --name "Content Team" \
  --file network-config.json \
  --routerProvider anthropic \
  --routerModel claude-3-5-sonnet-20241022

Read the full file on GitHub · 184 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. yesterday First seen · 184 lines · 0 tokens per session scan A 7637b352311c

Subscribe to this mod's changes

CLI-COVERAGE is an agent published in the GitHub repository juspay/neurolink (128 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,162 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.