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/notify-rule-copilotnpx skills add ccfos/nightingale --skill notify-rule-copilotgit 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/notify-rule-copilot)<a href="https://agentmods.dev/skills/ccfos/nightingale/notify-rule-copilot"><img src="https://agentmods.dev/badge/skills/ccfos/nightingale/notify-rule-copilot.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 | $0.00172 | $0.03098 |
| Opus 5 | $0.00086 | $0.01549 |
| Sonnet 5 | $0.00034 | $0.00620 |
| Haiku 4.5 | $0.00017 | $0.00310 |
Grade A, and why
notify-rule-copilot scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `http-api.md` | HTTP API paths (for A2A / external agents), the GET→modify→PUT editing pattern, direct DB edits | Only for external A2A scenarios, or when producing curl commands for the user | How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nightingale (n9e) Notify Rule Copilot
A notify rule defines how alert events are delivered: the notification method, recipients, time windows, and filter conditions. It can be referenced by multiple alert rules. This skill covers the full lifecycle of notify rules: creating, editing, copying, routing decomposition, and troubleshooting.
Companion materials (load on demand with read_file; set base to this skill's name)
| File | Contents | When to read |
|---|---|---|
reference.md |
Full table of config fields: notify_configs / the shape of params per channel and the user input each requires / quick lookup of official doc links per medium / time_ranges / label_keys / attributes operators |
When you are unsure about a field while assembling config; when you need to ask the user for channel params (access_token, etc.) and must attach a doc link |
recipes.md |
6 complex routing decomposition templates (tiered / time-windowed / no phone call on recovery / route by business group / label-based canary / catch-all) + 4 complete basic examples | When the requirement is composite routing |
troubleshooting.md |
Quick lookup table of known pitfalls + test/verification (dry-run) checklist | When a rule does not take effect / behaves abnormally after editing |
http-api.md |
HTTP API paths (for A2A / external agents), the GET→modify→PUT editing pattern, direct DB edits | Only for external A2A scenarios, or when producing curl commands for the user |
Scope (first determine which layer the user is changing)
Nightingale's notification pipeline is a three-layer abstraction, with one skill per layer — do not cross wires:
| Layer | Entity | Which skill |
|---|---|---|
| Medium Notify Channel | notify_channel table |
notify-channel-copilot |
| Template Message Template | message_template table |
generate-message-template |
| Rule Notify Rule | notify_rule table |
this skill |
How to judge:
- The wording mentions "URL / Webhook address / request headers / proxy / signature / AppID / AppSecret / how to integrate X" — medium layer, hand off to
notify-channel-copilot. - The wording mentions "template / message body / fields / card color / who to @ /
{{ ... }}variables" — template layer, hand off togenerate-message-template. - The wording mentions "who to send to / which channel for which severity / working hours / route by business group / filter by label / applicable attributes / edit an existing rule" — rule layer, this skill.
- The wording mentions "an event already fired but no notification was received, help me find out why" — post-hoc diagnosis, hand off to
alert-rule-troubleshootflow B. This skill is only responsible for "pulling up the correct rule configuration", not for replaying logs.
What ships with it
4 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.
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 · 119 lines · 172 tokens per session scan A 8741aca2d100
notify-rule-copilot is a skill published in the GitHub repository ccfos/nightingale (13,280 stars, last pushed yesterday), licensed Apache-2.0. It adds 172 tokens to every session and 3,098 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cis-aws-database-10.8
Ensure Monitoring and Alerting is Enabled.
review-pr
Review a GitHub pull request or local Git range against QuestDB coding standards.
fix-ci
Check CI status, analyze test failures, auto-fix obvious issues or discuss with user.
approve-pr
Approve the pull request for the currently checked-out branch. Posts the review from this conversation as an approving review and adds the "QUEUED FOR MERGE" label. Use after review-pr when you decide to approve.
reject-pr
Reject the pull request for the currently checked-out branch. Posts the review from this conversation as a change-request review that tags the PR author, sets the PR to "changes requested", and clears the READY label. Use after review-pr when you decide to reject.
fix-pr
Validate and fix pasted QuestDB pull-request review findings one at a time, with claim verification, a failing regression test where feasible, robust and performant implementation, testing, and an independent review/fix loop. Use when the user pastes Critical, Moderate, or other actionable PR review items.