zabbix-status

zabbix-status is a skill for Claude Code, Codex from stufently/zabbix-ai-cli-mcp. It costs 66 tokens per session (470 once invoked), scanned A, original, Apache-2.0.

A guide for answering what is currently wrong in Zabbix, a system-monitoring tool. It covers active alerts, host health, and monitoring overviews, including problems hidden by maintenance windows.

In plain words
What is it for?
Use it to list current problems, check a host, find hosts by name, and report whether alerts are acknowledged, suppressed, old, or truncated.
Why use it?
It provides a consistent way to check current system state and prevents suppressed or incomplete results from being mistaken for healthy, fully monitored systems.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to list current problems, check a host, find hosts by name, and report whether alerts are acknowledged, suppressed, old, or truncated.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stufently/zabbix-ai-cli-mcp/zabbix-status
Install

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.

Any agent
npx skills add stufently/zabbix-ai-cli-mcp --skill zabbix-status
Clone the repo
git clone --depth 1 https://github.com/stufently/zabbix-ai-cli-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for zabbix-status

README.md
[![agentmods](https://agentmods.dev/badge/skills/stufently/zabbix-ai-cli-mcp/zabbix-status/github.svg)](https://agentmods.dev/skills/stufently/zabbix-ai-cli-mcp/zabbix-status)
Your own site
<a href="https://agentmods.dev/skills/stufently/zabbix-ai-cli-mcp/zabbix-status"><img src="https://agentmods.dev/badge/skills/stufently/zabbix-ai-cli-mcp/zabbix-status/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.

agentmods 80×15 button for zabbix-status

Your own site · 80×15
<a href="https://agentmods.dev/skills/stufently/zabbix-ai-cli-mcp/zabbix-status"><img src="https://agentmods.dev/badge/skills/stufently/zabbix-ai-cli-mcp/zabbix-status.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 470 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.00470
Opus 5 $0.00033 $0.00235
Sonnet 5 $0.00013 $0.00094
Haiku 4.5 $0.00007 $0.00047

Measured 10d ago against content hash c77cc1c81ec1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

zabbix-status 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.

internal/skills/files/zabbix-status/SKILL.md · 47 lines

What it actually says

Zabbix: current state

Answer questions about what is wrong now, using zabbix-ai-cli-mcp.

Workflow

  1. Broad question ("what's broken?", "any alerts?"):

    zabbix-ai-cli-mcp problems list --json
    

    Add --severity high to cut noise, --limit N to bound the answer.

  2. About one host: pass it through. Matching is fuzzy, so a fragment works.

    zabbix-ai-cli-mcp problems list --host web01 --json
    zabbix-ai-cli-mcp host status web01 --json
    
  3. Nothing came back: the host name may not be what you assumed.

    zabbix-ai-cli-mcp host list --search web --json
    

Reading the result

  • suppressed: true means the problem raises no alert. suppressed_by names the maintenance window responsible and when it ends. Say so explicitly — a suppressed problem looks identical to a healthy host from the outside, and an outage can sit inside one for weeks unnoticed.
  • acknowledged: false means nobody has picked it up yet.
  • meta.truncated: true means there is more; say so rather than implying the list is complete, and offer to raise --limit.
  • age is how long the problem has been open. A problem hours old that nobody acknowledged is worth mentioning on its own.

Do not

  • Do not use zabbix_api_call for these questions. The high-level commands resolve host names and bound their output; a raw problem.get returns neither the host nor the suppression reason.
  • Do not report a count without saying whether the result was truncated.
Changes

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.

  1. 10d ago First seen · 47 lines · 66 tokens per session scan A c77cc1c81ec1

Subscribe to this mod's changes

zabbix-status 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 66 tokens to every session and 470 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.