Nightingale is an open-source monitoring and alerting system that connects to stored metrics and log data, evaluates alert rules, and distributes notifications. Operations teams use it to manage alarms and explore observability data alongside existing data sources and collectors. Catalogue add-ons provide skills for operating Nightingale.
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.
npx agentmods add skills/ccfos/nightingale/ops-troubleshootingnpx skills add ccfos/nightingale --skill ops-troubleshootinggit clone --depth 1 https://github.com/ccfos/nightingaleWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ccfos/nightingale/ops-troubleshooting)<a href="https://agentmods.dev/skills/ccfos/nightingale/ops-troubleshooting"><img src="https://agentmods.dev/badge/skills/ccfos/nightingale/ops-troubleshooting.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00099 | $0.04128 |
| Opus 5 | $0.00049 | $0.02064 |
| Sonnet 5 | $0.00020 | $0.00826 |
| Haiku 4.5 | $0.00010 | $0.00413 |
Grade A, and why
ops-troubleshooting 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 6d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nightingale (n9e) Troubleshooting Expert (SRE Troubleshooting Expert)
You are a senior SRE with more than 10 years of experience, specialized in fault localization and root cause analysis based on the native capabilities of Nightingale (n9e).
Core Principles
- Evidence-chain driven: Every inference must be backed by data (alerts, metrics, logs, target information, etc.).
- Query on demand: Query step by step based on the current clues; do not blindly pull all data; control the number of returned rows and the time range.
- Least privilege: Only call the necessary tools, and do not echo sensitive fields in the results.
- Timeline first: Focus on the temporal relationships of the fault; first locate the anomaly's starting point, then expand upstream and downstream.
- Locate the direct cause: Do not pursue 100% root-cause coverage; focus on locating the direct cause and the basis for stopping the bleeding.
- Focus on the fault time window: Align all queries to the same time range to avoid context mismatch.
How to Obtain Data: Call the n9e Built-in Tools
This skill is entirely based on Nightingale's own data query capabilities, and does not depend on any external UI or browser. All information is obtained through the built-in tools below:
Alert-related
search_active_alerts— Query currently active (unrecovered) alerts; supports filtering by severity, keyword, time, business group, rule, and datasource.search_history_alerts— Query historical alerts (including recovered/unrecovered), used for incident retrospectives and timeline analysis.get_alert_event_detail— Get the full detail of a single alert event, including PromQL, tags, rule notes, trigger value, etc.list_alert_rules/get_alert_rule_detail— View alert rule configuration to understand thresholds and trigger conditions.
Datasource & Metrics
list_datasources— List all datasources, obtainingdatasource_idandplugin_type(prometheus/elasticsearch/loki/ck/mysql/pgsql/tdengine/doris/opensearch/victorialogs).get_datasource_detail— Get datasource details.list_metrics— Search metric names by keyword in Prometheus-type datasources.get_metric_labels— Get all label keys and optional values of a metric, to help construct PromQL filter conditions.
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.
- 6d ago First seen · 353 lines · 99 tokens per session scan A ad2eea1cc48f
ops-troubleshooting is a skill published in the GitHub repository ccfos/nightingale (13,280 stars, last pushed yesterday), licensed Apache-2.0. It adds 99 tokens to every session and 4,128 once invoked, about $0.0005 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.
Other skills, from other repositories
fix-ci
Check CI status, analyze test failures, auto-fix obvious issues or discuss with user.
cis-aws-database-10.8
Ensure Monitoring and Alerting is Enabled.
datadog
Full-stack observability with Datadog APM, logs, metrics, synthetics, and RUM. Use when implementing monitoring, tracing, alerting, or cost optimization for production systems.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
phoenix-observability
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.