devops/observability/new-relic/SKILL.md
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.
npx skillsauth add bagelhole/devops-security-agent-skills new-relicInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Monitor applications and infrastructure with New Relic's observability platform.
Use this skill when:
# 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-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=${NEW_RELIC_LICENSE_KEY}
- NRIA_DISPLAY_NAME=docker-host
volumes:
- /:/host:ro
- /var/run/docker.sock:/var/run/docker.sock
# Using Helm
helm repo add newrelic https://helm-charts.newrelic.com
helm install newrelic-bundle newrelic/nri-bundle \
--namespace newrelic \
--create-namespace \
--set global.licenseKey=${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
// 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'
}
};
# Install agent
npm install newrelic
# Run application
NEW_RELIC_LICENSE_KEY=xxx node -r newrelic app.js
# 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
# 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
# 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
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!"))
}
import newrelic.agent
# Record custom event
newrelic.agent.record_custom_event('OrderPlaced', {
'order_id': '12345',
'amount': 99.99,
'customer_id': 'cust_001'
})
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'}
)
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
-- 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
-- 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
{
"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"
}
]
}
}
]
}
]
}
{
"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"
}
]
}
{
"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"
}
]
}
]
}
# newrelic.ini
[newrelic]
application_logging.enabled = true
application_logging.forwarding.enabled = true
application_logging.metrics.enabled = true
application_logging.local_decorating.enabled = true
# newrelic-infra.yml
log:
- name: application-logs
file: /var/log/myapp/*.log
attributes:
service: myapp
environment: production
Problem: Agent not reporting to New Relic Solution: Verify license key, check network connectivity, review agent logs
Problem: Some transactions not captured Solution: Check instrumentation coverage, verify framework support
Problem: APM agent impacting performance Solution: Adjust sampling rate, disable unnecessary features
development
Design and operationalize SRE dashboards that surface reliability, latency, error, saturation, and capacity signals across services. Use when building observability views for SLOs, incident response, and executive reliability reporting.
testing
Harden OpenClaw self-hosted environments with baseline host controls, auth tightening, secret handling, network segmentation, and safe update/rollback workflows. Use when deploying OpenClaw in home labs, startups, or production-like local AI infrastructure.
devops
Deploy, manage, and optimize vector databases for AI applications. Covers Qdrant, Weaviate, pgvector, and Pinecone — collection management, indexing strategies, backup, and performance tuning for production RAG and semantic search workloads.
testing
Deploy ML models on Kubernetes with KServe (formerly KFServing) and NVIDIA Triton Inference Server. Includes canary deployments, autoscaling, model versioning, A/B testing, and GPU resource management for production model serving.