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 skills add stufently/zabbix-ai-cli-mcp --skill zabbix-maintenancegit clone --depth 1 https://github.com/stufently/zabbix-ai-cli-mcpWrote 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/stufently/zabbix-ai-cli-mcp/zabbix-maintenance)<a href="https://agentmods.dev/skills/stufently/zabbix-ai-cli-mcp/zabbix-maintenance"><img src="https://agentmods.dev/badge/skills/stufently/zabbix-ai-cli-mcp/zabbix-maintenance/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/stufently/zabbix-ai-cli-mcp/zabbix-maintenance"><img src="https://agentmods.dev/badge/skills/stufently/zabbix-ai-cli-mcp/zabbix-maintenance.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00053 | $0.00563 |
| Opus 5 | $0.00026 | $0.00282 |
| Sonnet 5 | $0.00011 | $0.00113 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
zabbix-maintenance 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 10d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zabbix: maintenance windows
Check first
zabbix-ai-cli-mcp maintenance list --json
Expired windows are shown deliberately: "that one already ended, remove it" is a
routine follow-up and cannot be done if the window is invisible. ends_in tells you
how long an active window has left.
Opening a window
Host names may be patterns, so a fleet can be silenced the way it is described:
zabbix-ai-cli-mcp maintenance create "ms*,massivegrid*" --for 7d
zabbix-ai-cli-mcp maintenance create db1,db2 --for 2h --description "index rebuild"
Durations are written the way people say them: 30m, 2h, 7d, 2w.
Nothing happens yet. The command prints a plan showing exactly which hosts matched, and stops. A pattern that matches nothing is an error, not a quietly smaller window — read the host count in the plan before going further.
Whether you may apply it depends on the installation. Where zabbix_write
is offered, the change is yours to make: check the matched hosts first, make it,
and say plainly what you did. Where it is not, zabbix_plan_create is the only
route — relay the approve_command verbatim and let the operator run it.
Data collection
By default Zabbix keeps collecting during the window and only suppresses alerts.
--no-data-collection stops collection entirely — which also means a real outage
starting inside the window leaves no trace. Prefer the default unless asked.
Ending a window
zabbix-ai-cli-mcp maintenance expire 42 # ends now, keeps the record
zabbix-ai-cli-mcp maintenance delete 42 # removes it entirely
Prefer expire. delete is destructive: it removes the record of the window
along with the window, so nothing later explains why alerts were quiet.
Do not
- Do not open an indefinite window "to stop the noise". Give it the shortest duration that covers the work; a forgotten window is how an outage hides.
- Do not report a window as created while it is only planned. A plan is a description; until it is applied, nothing has changed.
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.
- 10d ago First seen · 60 lines · 53 tokens per session scan A e42a4547bf28
zabbix-maintenance is a skill published in the GitHub repository stufently/zabbix-ai-cli-mcp (0 stars, last pushed 12d ago), licensed Apache-2.0. It adds 53 tokens to every session and 563 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
monitoring
Use when setting up uptime and health monitoring, alerts, or on-call basics for a service already in production, so you learn it is down before customers do — health and readiness probes, alerting on SLO error-budget burn rather than raw counts, curing alert fatigue, on-call rotation with escalation, and a status…
host_bash
A read-only shell skill for examining files and running diagnostic commands in a restricted environment. A shell is a text interface for operating-system commands.
host_restart_service
A tool for restarting approved systemd services, which are background programs managed by Linux's service manager.
setup-environment-profile
Point the ilert CLI at a staging, preview or self-hosted ilert environment by giving it its own profile.
ilert-essentials
Core ilert concepts and CLI behaviour: the object model and the rules behind the field names.
migrate-from-opsgenie
Map Opsgenie resources onto ilert equivalents.