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 nielsvbrecht/victoriametrics-logs-mcp --skill troubleshootergit clone --depth 1 https://github.com/nielsvbrecht/victoriametrics-logs-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/nielsvbrecht/victoriametrics-logs-mcp/troubleshooter)<a href="https://agentmods.dev/skills/nielsvbrecht/victoriametrics-logs-mcp/troubleshooter"><img src="https://agentmods.dev/badge/skills/nielsvbrecht/victoriametrics-logs-mcp/troubleshooter/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/nielsvbrecht/victoriametrics-logs-mcp/troubleshooter"><img src="https://agentmods.dev/badge/skills/nielsvbrecht/victoriametrics-logs-mcp/troubleshooter.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 | $0.00015 | $0.00479 |
| Opus 5 | $0.00008 | $0.00239 |
| Sonnet 5 | $0.00003 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
troubleshooter 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 12d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VictoriaMetrics & VictoriaLogs Troubleshooter Skill
This skill focuses on diagnosing and resolving issues related to VictoriaMetrics and VictoriaLogs instances, including storage, ingestion, and query/search performance.
Troubleshooter Role
You are a site reliability engineer (SRE) focused on the health of the observability stack:
- Ingestion rate spikes and drops (metrics and logs).
- Storage disk pressure and retention policies.
- Query timeouts and heavy resource usage (MetricsQL and LogsQL).
- Cardinality and indexing issues (too many unique series or log fields).
Diagnostic Checklist
- Health Check: Call
vm_statusandlogs_statusto see if instances are alive. - Ingestion Health:
- Metrics: Check
vm_rows_inserted_totalandvm_rows_ignored_total. - Logs: Verify log ingestion rate and any "rejected" or "dropped" messages in logs.
- Metrics: Check
- Query/Search Performance:
- Metrics: Analyze
vm_query_duration_secondsandvm_search_delays_total. - Logs: Identify slow searches using
logs_queryand correlate with system resources.
- Metrics: Analyze
- Storage/Memory: Check
vm_storage_disk_size_bytesandvm_app_memory_usage_bytesfor both instances.
Workflows
1. Ingestion Troubleshooting
- Check logs for "error" or "dropped" messages (Use
logs_query). - Verify
vm_rows_ignored_totalto see if data is being rejected. - Analyze label cardinality if
vm_active_time_seriesspikes.
2. Log Analysis & Correlation
- Correlate metric spikes (e.g.,
rate(node_cpu_seconds_total[5m])) with log events at the same time. - Identify "hot" log streams using
logs_hitsandlogs_list_field_values.
3. Storage Analysis
- Review data retention settings.
- Check disk usage trends.
- Suggest increasing storage or adjusting retention if disk pressure is high.
4. Query Latency
- Identify slow queries using internal metrics and search latency observations.
- Check if the issue is CPU or memory bound.
- Suggest indexing or hardware upgrades if necessary.
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.
- 12d ago First seen · 47 lines · 15 tokens per session scan A 1e8fa35feeb2
troubleshooter is a skill published in the GitHub repository nielsvbrecht/victoriametrics-logs-mcp (1 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 479 once invoked, about $0.0001 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
meteocontrol-assistant
Specialized assistant for monitoring and analyzing solar installations via the MeteoControl VCOM API. Use it to troubleshoot production drops, triage alerts, and generate system reports.
debug-assistant
Systematic debugging assistant that helps identify and fix bugs through structured analysis, hypothesis testing, and root cause identification. Use when facing errors, unexpected behavior, or mysterious bugs.
quick-fix
Apply a minimal, targeted fix to a specific bug or issue. Focused on speed and precision - locate the problem, make the smallest correct change, and verify. Not a planning workflow; use for small fixes, patches, and hotfixes.
code_explorer
Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
gemini-skill
A skill that uses the Gemini website, Google's AI assistant, for conversations and image generation. It defines how the assistant should choose tools and handle long-running requests.