Ops Monitor

What it does

When your agent uses it

• Asks to datadog
• Tasks that involve Monitoring and alerting

Example prompts

• “datadog”
• “APM alerts”
• “/ops-monitor”

Requirements

• A credential in DD_API_KEY
• A credential in NR_API_KEY
• Pre-approved tools (allowed-tools): Bash, Read, Agent, AskUserQuestion, TeamCreate, SendMessage

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

1. 1datadog_api_key — API Key from app.datadoghq.com/organization-settings/api-keys
2. 2datadog_app_key — Application Key from app.datadoghq.com/organization-settings/application-keys

What it can do on your machine

Read from SKILL.md and the folder at commit 996d61a. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read
  • Agent
  • AskUserQuestion
  • TeamCreate
  • SendMessage

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • curl
  • jq

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • api.datadoghq.com
  • api.newrelic.com

  Also links to:

  • otlp.grafana.net

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • DD_API_KEY
  • NR_API_KEY
  • DD_APP_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ops Monitor loads about 1.5k tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 384 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~26

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read, Agent, AskUserQuestion, TeamCreate, SendMessage

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Lifecycle-Innovations-Limited/claude-ops at commit 996d61a, republished under its MIT licence (© Lifecycle-Innovations-Limited). 384 words, ~1,533 tokens.

name

ops-monitor

description

OPS on-demand: This skill should be used when the user asks to "datadog", "APM alerts", or…

allowed-tools

Bash, Read, Agent, AskUserQuestion, TeamCreate, SendMessage

argument-hint

[--watch] [--setup] [--backend datadog|newrelic|otel]

effort

low

maxTurns

20

PREFS="${CLAUDE_PLUGIN_DATA_DIR:-$HOME/.claude/plugins/data/ops-ops-marketplace}/preferences.json"
DD_API_KEY=$(jq -r '.datadog_api_key // empty' "$PREFS" 2>/dev/null)
NR_API_KEY=$(jq -r '.newrelic_api_key // empty' "$PREFS" 2>/dev/null)
OTEL_ENDPOINT=$(jq -r '.otel_endpoint // empty' "$PREFS" 2>/dev/null)

Which monitoring backends would you like to configure?
[Datadog]  [New Relic]  [OpenTelemetry]  [All three]

tmp=$(mktemp)
jq --arg k "$KEY" --arg v "$VALUE" '.[$k] = $v' "$PREFS" > "$tmp" && mv "$tmp" "$PREFS"

TeamCreate("monitor-probes")
Agent(team_name="monitor-probes", name="datadog-probe", subagent_type="ops:monitor-agent", ...)
Agent(team_name="monitor-probes", name="newrelic-probe", subagent_type="ops:monitor-agent", ...)
Agent(team_name="monitor-probes", name="otel-probe", subagent_type="ops:monitor-agent", ...)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 OPS ► MONITOR                       [<timestamp>]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 DATADOG      ✅ healthy (0 alerts)
 NEW RELIC    🔴 2 critical entities
 OTEL         ✅ healthy
──────────────────────────────────────────────────────
 Total alerts: 2   Severity: CRITICAL

No monitoring backends configured. Run /ops:monitor --setup to add Datadog, New Relic, or OTEL.

while true; do
  RESULT=$(# spawn monitor-agent and capture JSON output)
  # Diff against previous tick
  # Print: timestamp, changed items only
  # 🆕 new alert: <name>
  # ✅ resolved: <name>
  sleep 60
done

# Datadog — active alerts
curl -sf \
  -H "DD-API-KEY: ${DD_API_KEY}" \
  -H "DD-APPLICATION-KEY: ${DD_APP_KEY}" \
  "https://api.datadoghq.com/api/v1/monitor?monitor_tags=*&with_downtimes=false" \
  | jq '[.[] | select(.overall_state == "Alert" or .overall_state == "Warn")]'

# New Relic — critical entities (GraphQL)
curl -sf \
  -H "Api-Key: ${NR_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{"query":"{ actor { entitySearch(queryBuilder: {alertSeverity: CRITICAL}) { results { entities { name alertSeverity entityType } } } } }"}' \
  "https://api.newrelic.com/graphql"

# OTEL — health check
curl -sf "${OTEL_ENDPOINT}/healthz"

© Lifecycle-Innovations-Limited, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in claude-ops/skills/ops-monitor of Lifecycle-Innovations-Limited/claude-ops.

Open the folder on GitHubat commit 996d61a

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in Lifecycle-Innovations-Limited/claude-ops, which our catalogue first saw on October 7, 2026.

• davepoon/buildwithclaudeplugins/claude-ops/skills/ops-monitor