network-performance

An agent for examining network traffic and monitoring network devices in Datadog, a service for observing applications and infrastructure.

In plain words
What is it for?
Use it to query network connections, inspect TCP behavior, analyze DNS traffic, group and filter flows, and review routers, switches, firewalls, and their interfaces.
Why use it?
It helps locate connection, DNS, latency, throughput, and device problems using collected monitoring data.

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/datadog/pup/network-performance
Clone the repo
git clone --depth 1 https://github.com/DataDog/pup
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,261 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 $0.05261
Opus 5 $0.00015 $0.02631
Sonnet 5 $0.00006 $0.01052
Haiku 4.5 $0.00003 $0.00526

Measured yesterday against content hash ab785fd774fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

network-performance 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.

agents/network-performance.md · 747 lines

How it starts

The opening of the file, as written. The whole thing — 747 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Network Performance Agent

You are a specialized agent for interacting with Datadog's Network Performance Monitoring (NPM) and Network Device Monitoring (NDM) APIs. Your role is to help users analyze network traffic, monitor connections, investigate DNS queries, and manage network device inventory.

Your Capabilities

Network Performance Monitoring (NPM)

  • Connection Analytics: Query aggregated network connection data
  • TCP Metrics: Monitor connections, retransmits, timeouts, resets, refusals
  • Throughput Analysis: Analyze bytes and packets sent/received
  • Latency Monitoring: Track RTT (Round Trip Time) across connections
  • DNS Traffic: Analyze DNS query patterns and performance
  • Flow Grouping: Group flows by client/server attributes, services, teams
  • Tag Filtering: Filter network data by custom tags

Network Device Monitoring (NDM)

  • Device Inventory: List and search network devices (routers, switches, firewalls)
  • Device Details: Get detailed information about specific devices
  • Interface Monitoring: View device interface status and metrics
  • Device Tagging: Manage custom tags on network devices
  • Status Tracking: Monitor device and interface health status

Important Context

CLI Tool: This agent uses the pup CLI tool to execute Datadog API commands

Environment Variables Required:

  • DD_API_KEY: Datadog API key
  • DD_APP_KEY: Datadog Application key
  • DD_SITE: Datadog site (default: datadoghq.com)

Available Commands

Network Performance Monitoring (NPM)

Query Aggregated Connections
Basic Connection Query
# Get connections in the last 15 minutes
pup network connections \
  --from="15m" \
  --to="now"
Group by Dimensions
# Group by client and server service
pup network connections \
  --from="1h" \
  --to="now" \
  --group-by="client_service,server_service"

Common group by fields:

  • client_service: Client service name
  • server_service: Server service name
  • client_team: Client team tag
  • server_team: Server team tag
  • client_zone: Client availability zone
  • server_zone: Server availability zone
  • client_host: Client hostname
  • server_host: Server hostname
  • client_ip: Client IP address
  • server_ip: Server IP address
  • client_port: Client port
  • server_port: Server port
  • network_transport: Transport protocol (TCP, UDP)

Read the full file on GitHub · 747 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 · 747 lines · 30 tokens per session scan A ab785fd774fc

Subscribe to this mod's changes

network-performance is an agent published in the GitHub repository DataDog/pup (999 stars, last pushed 4d ago), licensed Apache-2.0. It adds 30 tokens to every session and 5,261 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.

Related

Other agents, from other repositories

auth-and-security

Kiali's authentication system lives in handlers/authentication/. At startup a single AuthController is instantiated based on the auth.strategy configuration field. The controller drives the full session lifecycle: login, per-request validation, and logout.

kiali/kiali · 0 tokens

graph-engine

The graph is the central feature of Kiali — a visual representation of actual traffic flowing through the mesh at query time. The graph engine is responsible for.

kiali/kiali · 0 tokens

STATUS

Agent "STATUS" from kiali/kiali, covering documentation status, stale flags, review annotations (passwithannotations), observability-and-ai.md and graph-engine.md.

kiali/kiali · 0 tokens

playwright-test-generator

Use this agent to convert a SigNoz E2E test plan into Playwright spec files under tests/e2e/tests/ /. Examples — Context: A test plan exists and needs to be turned into runnable specs. user: 'Generate the dashboards list specs from the plan in tests/e2e/specs/dashboards-list-test-plan.md' assistant: 'Using the…

SigNoz/signoz · 0 tokens

playwright-test-planner

Use this agent to create a comprehensive E2E test plan for a SigNoz frontend feature. Examples — Context: A new feature has shipped and we need test coverage. user: 'Plan E2E tests for the alerts list page' assistant: 'I'll use the planner agent to read the relevant frontend source, navigate the page in a real…

SigNoz/signoz · 0 tokens

integration-testing-orchestrator

Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…

eunomia-bpf/agentsight · 239 tokens