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/query-datasourcenpx skills add ccfos/nightingale --skill query-datasourcegit clone --depth 1 https://github.com/ccfos/nightingaleWhat 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 | $0.00077 | $0.01619 |
| Opus 5 | $0.00039 | $0.00809 |
| Sonnet 5 | $0.00015 | $0.00324 |
| Haiku 4.5 | $0.00008 | $0.00162 |
Grade A, and why
query-datasource 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 2d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nightingale (n9e) Query Datasource Data
Query monitoring metrics, logs, and time-series data from various datasources on the Nightingale monitoring platform.
Based on the datasource type the user needs, read the corresponding file under the datasources/ directory to get the query method and parameter format:
- datasources/prometheus.md - Prometheus / VictoriaMetrics metric queries (PromQL)
- datasources/elasticsearch.md - Elasticsearch log queries (ES DSL / Lucene)
- datasources/loki.md - Loki log queries (LogQL)
- datasources/clickhouse.md - ClickHouse metric/log queries (SQL)
- datasources/mysql.md - MySQL metric queries (SQL)
- datasources/pgsql.md - PostgreSQL metric queries (SQL)
- datasources/tdengine.md - TDengine time-series queries (SQL)
- datasources/doris.md - Doris log queries (SQL)
- datasources/opensearch.md - OpenSearch log queries (ES DSL)
- datasources/victorialogs.md - VictoriaLogs log queries (LogsQL)
Prerequisites
The user needs to provide:
- n9e address: e.g.
http://<n9e-host>:<port> - Username/password: e.g.
<username>/<password> - Query requirement description: e.g. "query CPU usage over the last hour", "search logs containing error"
If the user has not provided the above information, use the AskUserQuestion tool to ask.
Execution Steps
Step 1: Log in to obtain a Token
POST /api/n9e/auth/login
Content-Type: application/json
Body: {"username":"<username>","password":"<password>"}
Extract dat.access_token from the response, and include Authorization: Bearer <token> in all subsequent requests.
Step 2: Query available datasources
Retrieve the datasource list to determine the datasource ID and type to query:
POST /api/n9e/datasource/list
Authorization: Bearer <token>
Content-Type: application/json
Body: {}
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- datasources/clickhouse.md 3.5 KB
- datasources/doris.md 2.6 KB
- datasources/elasticsearch.md 3.3 KB
- datasources/loki.md 1.9 KB
- datasources/mysql.md 2.6 KB
- datasources/opensearch.md 1.8 KB
- datasources/pgsql.md 2.6 KB
- datasources/prometheus.md 3.5 KB
- datasources/tdengine.md 3.1 KB
- datasources/victorialogs.md 1.3 KB
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.
- 2d ago First seen · 172 lines · 77 tokens per session scan A 6fc830338abb
query-datasource is a skill published in the GitHub repository ccfos/nightingale (13,271 stars, last pushed today), licensed Apache-2.0. It adds 77 tokens to every session and 1,619 once invoked, about $0.0004 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
Alerting & Monitoring Testing
Testing monitoring and alerting configurations including threshold validation, alert routing, escalation policies, and false-positive rate monitoring.
grafana-expert
Expert-level Grafana dashboards, visualization, data sources, alerting, and production operations.
monitoring
Skill "monitoring" from chaterm/terminal-skills, covering 监控与告警, 概述, prometheus, 基础查询（promql） and 即时向量.
monitoring-expert
Expert-level monitoring and observability with Prometheus, Grafana, logging, and alerting.
prometheus-expert
Expert-level Prometheus monitoring, metrics collection, PromQL queries, alerting, and production operations.
observability
Observability, Monitoring & SRE: Comprehensive guide for implementing observability (logs, metrics, traces), setting up monitoring and alerting, defining SLOs/SLIs/SLAs, creating dashboards, and incident detection. Use whenever the user mentions 'observability', 'monitoring', 'alerting', 'logging', 'metrics'…