Agent Skills
› davepoon/buildwithclaude
› ops-monitor
ops-monitor
GitHub统一APM监控技能，轮询Datadog、New Relic和OpenTelemetry后端以获取警报和健康状态。支持配置凭证、实时轮询及多后端并行探测，提供默认健康检查与Agent Teams协作能力。
Trigger Scenarios
用户需要查询系统或服务的实时健康状态
用户请求配置监控后端（如Datadog/New Relic）的API密钥
用户希望开启实时监控模式以持续跟踪警报
Install
npx skills add davepoon/buildwithclaude --skill ops-monitor -g -y
SKILL.md
Frontmatter
{
"name": "ops-monitor",
"effort": "low",
"maxTurns": 20,
"description": "Unified APM and monitoring surface. Polls Datadog, New Relic, and OpenTelemetry backends for active alerts, error traces, and entity health. Use --watch for live polling every 60 seconds. Use --setup to configure monitoring credentials.",
"allowed-tools": [
"Bash",
"Read",
"Agent",
"AskUserQuestion",
"TeamCreate",
"SendMessage"
],
"argument-hint": "[--watch] [--setup] [--backend datadog|newrelic|otel]"
}
Runtime Context
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)
Determine $ARGUMENTS mode:
- Contains
--setup→ run Setup flow - Contains
--watch→ run Watch mode - Otherwise → run Default health check
OPS ► MONITOR
Setup flow (--setup)
Ask which backends to configure:
Which monitoring backends would you like to configure?
[Datadog] [New Relic] [OpenTelemetry] [All three]
For each selected backend, collect credentials via AskUserQuestion free-text input (one at a time, ≤4 options per call):
Datadog:
datadog_api_key— API Key from app.datadoghq.com/organization-settings/api-keysdatadog_app_key— Application Key from app.datadoghq.com/organization-settings/application-keys
New Relic:
newrelic_api_key— User API Key from one.newrelic.com/api-keysnewrelic_account_id— Numeric Account ID from New Relic admin portal
OpenTelemetry:
otel_endpoint— Base URL of your OTEL-compatible backend (e.g., https://otlp.grafana.net)
Write each credential to preferences.json using atomic tmpfile swap:
tmp=$(mktemp)
jq --arg k "$KEY" --arg v "$VALUE" '.[$k] = $v' "$PREFS" > "$tmp" && mv "$tmp" "$PREFS"
Run smoke test after saving:
- Datadog:
curl -sf -H "DD-API-KEY: $DD_API_KEY" -H "DD-APPLICATION-KEY: $DD_APP_KEY" "https://api.datadoghq.com/api/v1/validate"→ expect{"valid": true} - New Relic:
curl -sf -H "Api-Key: $NR_API_KEY" "https://api.newrelic.com/graphql" -d '{"query":"{ actor { user { name } } }"}'→ expectdata.actor.user - OTEL:
curl -sf "$OTEL_ENDPOINT/healthz"→ expect HTTP 200
Report ✅ or ❌ with status for each backend.
Agent Teams support
If CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 is set, use Agent Teams when querying multiple backends simultaneously. This enables:
- Backend probes run in parallel with shared context (e.g., Datadog agent detects latency spike → OTEL agent can correlate with traces)
- You can steer: "focus on Datadog alerts first, then cross-reference with New Relic"
- Real-time progress: agents report per-backend as results arrive
Team setup (only when flag is enabled, multiple backends configured):
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", ...)
If the flag is NOT set or only one backend is configured, use a single monitor-agent subagent.
Default health check (no flags)
Spawn monitor-agent via the Agent tool. Display the result as a formatted dashboard:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
OPS ► MONITOR [<timestamp>]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
DATADOG ✅ healthy (0 alerts)
NEW RELIC 🔴 2 critical entities
OTEL ✅ healthy
──────────────────────────────────────────────────────
Total alerts: 2 Severity: CRITICAL
Status icons:
✅— healthy (0 alerts / configured and reachable)⚠️— warning (warn-level alerts present)🔴— critical (critical alerts or unreachable)⬜— not configured
For each alert or critical entity, display: service name, alert name, and link to the relevant dashboard.
If no backends are configured, show a setup prompt:
No monitoring backends configured. Run /ops:monitor --setup to add Datadog, New Relic, or OTEL.
Watch mode (--watch)
Poll every 60 seconds. On each tick:
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
Exit on Ctrl-C.
--backend filter
If --backend datadog|newrelic|otel is specified, query and display only that backend.
CLI/API Reference
| Backend | Auth header | Base URL | Health endpoint |
|---|---|---|---|
| Datadog | DD-API-KEY: $key + DD-APPLICATION-KEY: $app_key |
https://api.datadoghq.com | /api/v1/validate |
| New Relic | Api-Key: $key |
https://api.newrelic.com/graphql | POST GraphQL query |
| OTEL | varies by backend | $OTEL_ENDPOINT |
/healthz |
# 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"
Version History
- 502fc01 Current 2026-07-05 15:10
