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-alert-analysisgit 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-alert-analysis)<a href="https://agentmods.dev/skills/stufently/zabbix-ai-cli-mcp/zabbix-alert-analysis"><img src="https://agentmods.dev/badge/skills/stufently/zabbix-ai-cli-mcp/zabbix-alert-analysis/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-alert-analysis"><img src="https://agentmods.dev/badge/skills/stufently/zabbix-ai-cli-mcp/zabbix-alert-analysis.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 | $0.00050 | $0.00585 |
| Opus 5 | $0.00025 | $0.00293 |
| Sonnet 5 | $0.00010 | $0.00117 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
zabbix-alert-analysis 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zabbix: why was there no alert
A notification can be dropped at five different points, and most of them record no error anywhere. Do not reconstruct the chain by hand.
Workflow
-
Get the event identifier. If you have the notification text — pasted from chat, email, or a ticket — hand it over whole:
zabbix-ai-cli-mcp resolve "Problem started at 08:17 ... Host: web01 ... Original problem ID: 757474" --jsonIt extracts the event, host and trigger. Without this step an instruction like "why didn't this one alert?" cannot be acted on, because the identifiers exist only inside the message.
-
Explain the delivery:
zabbix-ai-cli-mcp alert why 757474 --json -
Read
findingsfirst. They are ordered facts, not conclusions. The supporting detail sits insuppressed_by,delivery_attempts,actions,media_typesandrecipients.
What each link means
- Suppressed — the event fell inside a maintenance window. Nothing else matters;
suppressed_bynames the window and its end. - Delivery attempts exist and failed — Zabbix tried.
errorcarries the transport's own message: a rejected token, a refused connection, a bad address. - No delivery attempts at all — nothing was ever queued, so the cause is configuration. Work down: is any trigger action enabled; is the media type enabled; does any recipient have media for it.
- Recipients listed but
severity_accepted: false— the user's media filters this severity out. This drops notifications silently and is the single easiest cause to miss. media_enabled: false— that contact is switched off.
Reading the result
meta.partial: true means one leg of the chain could not be read; say which.
A finding of "no obstacle was found in the configuration" means the chain is intact
and the cause lies outside Zabbix — at the transport or the recipient's client.
Do not
- Do not answer from
problem.getoralert.getalone. Delivery attempts only exist once an action fired; their absence is the interesting case, and it needs the action, media type and recipient checks to interpret.
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 · 56 lines · 50 tokens per session scan A 93ca831b5c05
zabbix-alert-analysis 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 50 tokens to every session and 585 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
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_files
A set of tools for investigating a device’s file system, including finding large files, checking directory disk usage, and inspecting individual files.
code_explorer
Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.
alert-rule-troubleshoot
This skill should be used when the user reports that an alert rule is "not firing", "no alert was sent", "the rule didn't trigger", "the rule isn't working", "it should have alerted but didn't", "why didn't I get an alert", "alert rule not firing", or wants to diagnose why a specific alert rule failed to produce an…
ops-troubleshooting
This skill should be used when the user asks to "troubleshoot", "diagnose", "debug alert", "investigate incident", "locate a fault", "investigate an alert", "diagnose a problem", "fix an issue", "check alerts", "analyze alerts", "root cause analysis", "check metrics", "check logs", or discusses…
operating-github-ci-fixer
Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.