New Relic logo

New Relic

CommunityPopular
BagelHole
new-relic

Configure New Relic observability platform for infrastructure and application monitoring. Set up APM agents, create dashboards, configure alerts, and implement distributed tracing. Use when implementing full-stack observability with New Relic One.

Overview

PublisherBagelHole
RepositoryDevOps-Security-Agent-Skills
Skill namenew-relic
Stars
1.1K
Forks
161
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by BagelHole on GitHub. Read the source before you install it.

Installation

Install the New Relic AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/BagelHole/DevOps-Security-Agent-Skills/tree/main/devops/observability/new-relic
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/BagelHole/DevOps-Security-Agent-Skills.git /tmp/DevOps-Security-Agent-Skills
mkdir -p .claude/skills
cp -r /tmp/DevOps-Security-Agent-Skills/devops/observability/new-relic .claude/skills/new-relic
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable New Relic in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads New Relic on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so New Relic is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

New Relic

Monitor applications and infrastructure with New Relic's observability platform.

When to Use This Skill

Use this skill when:

  • Implementing full-stack observability
  • Setting up APM for applications
  • Monitoring infrastructure health
  • Creating custom dashboards and alerts
  • Implementing distributed tracing

Prerequisites

  • New Relic account and license key
  • Application access for APM agents
  • Infrastructure access for host agents

Infrastructure Agent

Linux Installation

bash
# Add repository and install
curl -Ls https://download.newrelic.com/install/newrelic-cli/scripts/install.sh | bash

# Configure license key
sudo NEW_RELIC_API_KEY=<YOUR_API_KEY> NEW_RELIC_ACCOUNT_ID=<ACCOUNT_ID> /usr/local/bin/newrelic install

# Or manual configuration
echo "license_key: YOUR_LICENSE_KEY" | sudo tee -a /etc/newrelic-infra.yml
sudo systemctl start newrelic-infra

Docker

yaml
# docker-compose.yml
version: '3.8'

services:
  newrelic-infra:
    image: newrelic/infrastructure:latest
    cap_add:
      - SYS_PTRACE
    privileged: true
    pid: "host"
    network_mode: "host"
    environment:
      - NRIA_LICENSE_KEY=${NEW_RELIC_LICENSE_KEY}
      - NRIA_DISPLAY_NAME=docker-host
    volumes:
      - /:/host:ro
      - /var/run/docker.sock:/var/run/docker.sock

Kubernetes

bash
# Using Helm
helm repo add newrelic https://helm-charts.newrelic.com

helm install newrelic-bundle newrelic/nri-bundle \
  --namespace newrelic \
  --create-namespace \
  --set global.licenseKey=${NEW_RELIC_LICENSE_KEY} \
  --set global.cluster=my-cluster \
  --set newrelic-infrastructure.privileged=true \
  --set ksm.enabled=true \
  --set kubeEvents.enabled=true \
  --set logging.enabled=true

APM Agents

Node.js

javascript
// At the very start of your application
require('newrelic');

// newrelic.js configuration
exports.config = {
  app_name: ['My Application'],
  license_key: process.env.NEW_RELIC_LICENSE_KEY,
  distributed_tracing: {
    enabled: true
  },
  logging: {
    level: 'info'
  },
  error_collector: {
    enabled: true,
    ignore_status_codes: [404]
  },
  transaction_tracer: {
    enabled: true,
    transaction_threshold: 'apdex_f',
    record_sql: 'obfuscated'
  }
};
bash
# Install agent
npm install newrelic

# Run application
NEW_RELIC_LICENSE_KEY=xxx node -r newrelic app.js

Python

python
# newrelic.ini
[newrelic]
license_key = YOUR_LICENSE_KEY
app_name = My Application
distributed_tracing.enabled = true
transaction_tracer.enabled = true
error_collector.enabled = true
browser_monitoring.auto_instrument = true
bash
# Install agent
pip install newrelic

# Generate config file
newrelic-admin generate-config YOUR_LICENSE_KEY newrelic.ini

# Run application
NEW_RELIC_CONFIG_FILE=newrelic.ini newrelic-admin run-program python app.py

# Or with gunicorn
NEW_RELIC_CONFIG_FILE=newrelic.ini newrelic-admin run-program gunicorn app:app

Java

bash
# Download agent
curl -O https://download.newrelic.com/newrelic/java-agent/newrelic-agent/current/newrelic-java.zip
unzip newrelic-java.zip

# Configure newrelic.yml
# license_key: YOUR_LICENSE_KEY
# app_name: My Application

# Run with agent
java -javaagent:/path/to/newrelic.jar -jar myapp.jar

Go

go
package main

import (
    "github.com/newrelic/go-agent/v3/newrelic"
    "net/http"
)

func main() {
    app, err := newrelic.NewApplication(
        newrelic.ConfigAppName("My Application"),
        newrelic.ConfigLicense("YOUR_LICENSE_KEY"),
        newrelic.ConfigDistributedTracerEnabled(true),
    )
    if err != nil {
        panic(err)
    }

    http.HandleFunc(newrelic.WrapHandleFunc(app, "/", indexHandler))
    http.ListenAndServe(":8080", nil)
}

func indexHandler(w http.ResponseWriter, r *http.Request) {
    txn := newrelic.FromContext(r.Context())
    txn.AddAttribute("user_id", "12345")
    w.Write([]byte("Hello, World!"))
}

Custom Instrumentation

Custom Events

python
import newrelic.agent

# Record custom event
newrelic.agent.record_custom_event('OrderPlaced', {
    'order_id': '12345',
    'amount': 99.99,
    'customer_id': 'cust_001'
})

Custom Metrics

python
import newrelic.agent

# Record custom metric
newrelic.agent.record_custom_metric('Custom/OrderValue', 99.99)

# With attributes
newrelic.agent.record_custom_metric('Custom/ProcessingTime', 
    processing_time, 
    {'unit': 'milliseconds'}
)

Custom Spans

python
import newrelic.agent

@newrelic.agent.function_trace(name='process_payment')
def process_payment(order_id, amount):
    # This creates a custom span in the trace
    pass

# Manual span creation
with newrelic.agent.FunctionTrace(name='custom_operation'):
    # Traced code
    pass

NRQL Queries

Basic Queries

sql
-- Transaction throughput
SELECT rate(count(*), 1 minute) FROM Transaction 
WHERE appName = 'My Application' 
SINCE 1 hour ago

-- Average response time
SELECT average(duration) FROM Transaction 
WHERE appName = 'My Application' 
SINCE 1 hour ago

-- Error rate
SELECT percentage(count(*), WHERE error IS true) FROM Transaction 
WHERE appName = 'My Application' 
SINCE 1 hour ago

-- Apdex score
SELECT apdex(duration, t: 0.5) FROM Transaction 
WHERE appName = 'My Application' 
SINCE 1 hour ago

Advanced Queries

sql
-- Slowest transactions
SELECT average(duration) FROM Transaction 
WHERE appName = 'My Application' 
FACET name 
SINCE 1 hour ago 
ORDER BY average(duration) DESC 
LIMIT 10

-- Error breakdown
SELECT count(*) FROM TransactionError 
WHERE appName = 'My Application' 
FACET error.class 
SINCE 1 hour ago

-- Percentile response times
SELECT percentile(duration, 50, 90, 95, 99) FROM Transaction 
WHERE appName = 'My Application' 
SINCE 1 hour ago TIMESERIES

-- Custom event analysis
SELECT average(amount), count(*) FROM OrderPlaced 
FACET customer_id 
SINCE 1 day ago

Dashboards

Dashboard JSON

json
{
  "name": "Application Dashboard",
  "pages": [
    {
      "name": "Overview",
      "widgets": [
        {
          "title": "Throughput",
          "visualization": {"id": "viz.line"},
          "configuration": {
            "nrqlQueries": [
              {
                "accountId": 12345,
                "query": "SELECT rate(count(*), 1 minute) FROM Transaction WHERE appName = 'My Application' SINCE 1 hour ago TIMESERIES"
              }
            ]
          }
        },
        {
          "title": "Error Rate",
          "visualization": {"id": "viz.billboard"},
          "configuration": {
            "nrqlQueries": [
              {
                "accountId": 12345,
                "query": "SELECT percentage(count(*), WHERE error IS true) FROM Transaction WHERE appName = 'My Application' SINCE 1 hour ago"
              }
            ]
          }
        }
      ]
    }
  ]
}

Alerts

Alert Condition (NRQL)

json
{
  "name": "High Error Rate",
  "type": "static",
  "nrql": {
    "query": "SELECT percentage(count(*), WHERE error IS true) FROM Transaction WHERE appName = 'My Application'"
  },
  "valueFunction": "single_value",
  "terms": [
    {
      "threshold": 5,
      "thresholdOccurrences": "all",
      "thresholdDuration": 300,
      "operator": "above",
      "priority": "critical"
    },
    {
      "threshold": 2,
      "thresholdOccurrences": "all",
      "thresholdDuration": 300,
      "operator": "above",
      "priority": "warning"
    }
  ]
}

Alert Policy

json
{
  "name": "Application Alerts",
  "incident_preference": "PER_CONDITION_AND_TARGET",
  "conditions": [
    {
      "name": "High Response Time",
      "type": "apm_app_metric",
      "entities": ["My Application"],
      "metric": "response_time_web",
      "condition_scope": "application",
      "terms": [
        {
          "duration": "5",
          "operator": "above",
          "threshold": "1",
          "priority": "critical"
        }
      ]
    }
  ]
}

Logs in Context

Python Configuration

python
# newrelic.ini
[newrelic]
application_logging.enabled = true
application_logging.forwarding.enabled = true
application_logging.metrics.enabled = true
application_logging.local_decorating.enabled = true

Log Forwarding

yaml
# newrelic-infra.yml
log:
  - name: application-logs
    file: /var/log/myapp/*.log
    attributes:
      service: myapp
      environment: production

Common Issues

Issue: No Data Appearing

Problem: Agent not reporting to New Relic Solution: Verify license key, check network connectivity, review agent logs

Issue: Missing Transactions

Problem: Some transactions not captured Solution: Check instrumentation coverage, verify framework support

Issue: High Overhead

Problem: APM agent impacting performance Solution: Adjust sampling rate, disable unnecessary features

Best Practices

  • Use meaningful application names
  • Implement distributed tracing across services
  • Set up service maps for dependency visualization
  • Configure appropriate alert thresholds
  • Use custom attributes for business context
  • Implement logs in context for correlation
  • Set up workloads for service grouping
  • Regular review of unused dashboards and alerts

Related Skills

Frequently asked questions

What does the New Relic AI skill do?

Configure New Relic observability platform for infrastructure and application monitoring. Set up APM agents, create dashboards, configure alerts, and implement distributed tracing. Use when implementing full-stack observability with New Relic One.

Why use New Relic on TypingMind?

Because you install it once and use it with any model. New Relic is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install New Relic in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/BagelHole/DevOps-Security-Agent-Skills/tree/main/devops/observability/new-relic. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use New Relic?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with New Relic?

As many as you like. As long as a model supports skills, you can use New Relic with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the New Relic AI skill free?

Yes. It is published on GitHub by BagelHole under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇