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 gensecaihq/Wazuh-Autopilot --skill alert-correlationgit clone --depth 1 https://github.com/gensecaihq/Wazuh-AutopilotWrote 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/gensecaihq/wazuh-autopilot/alert-correlation)<a href="https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/alert-correlation"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/alert-correlation/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/gensecaihq/wazuh-autopilot/alert-correlation"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/alert-correlation.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 | $0.00042 | $0.01073 |
| Opus 5.5 | $0.00017 | $0.00429 |
| Sonnet 5 | $0.00008 | $0.00215 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
alert-correlation 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 yesterday.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alert Correlation
Goal: answer "is this isolated, or part of something bigger?" NIST CSF 2.0 DE.AE — correlating adverse events from multiple sources.
Procedure
get_case— collect entities (IPs, users, hosts, hashes) and first/last alert time.- Pick a window: default ±24h around the case; widen to 7d for slow activity (password spraying, beaconing) or narrow to ±1h for bursts.
- Pivot on each attacker/victim entity (max 10 pivots per run — prioritize attacker IPs, then targeted users, then hosts).
- Aggregate to find patterns rather than reading raw alerts one by one.
- Classify the result (table below) and record it.
Query patterns
| Question | Tool and arguments |
|---|---|
| Everything this IP did | search_security_events(query="<ip>", srcip="<ip>", time_range="24h") (time_range is one of 1h, 6h, 12h, 1d, 24h, 7d, 30d) |
| Alerts on the same host | get_wazuh_alerts(agent_id="<id>", timestamp_start="now-24h", level="5") (level means "this or higher"; "10+" also works) |
| Which rules and agents dominate | get_alerts_aggregated(timestamp_start="now-24h", top_rules=20, top_agents=20). It aggregates by rule and agent, not by source IP; for per-IP counts use search_security_events with srcip |
| Rules or groups over a period | get_wazuh_alert_summary(time_range="24h", group_by="rule.id") (group_by: rule.level, rule.id, rule.groups, agent.id, agent.name) |
| Burst / trend / anomaly | analyze_alert_patterns(time_range="24h", min_frequency=5) |
| Group-wide auth failures | get_wazuh_alerts(rule_groups=["authentication_failed", "authentication_failures"], timestamp_start="now-24h") (single-failure and composite brute-force groups) |
| What a rule id means | get_wazuh_rules_summary, or load wazuh-rules-and-decoders |
Results come back as "<Label>:\n{json}" with items under data.affected_items. Keep
compact=true (the default), keep limit ≤ 500 per query, and narrow by time or agent
rather than paging through thousands of alerts. Load wazuh-mcp-querying for more.
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.
- yesterday First seen · 71 lines · 42 tokens per session scan A a83cf1acee64
alert-correlation is a skill published in the GitHub repository gensecaihq/Wazuh-Autopilot (57 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 1,073 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-25.
Other skills, from other repositories
agent-crdt-synchronizer
Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer.
agent-topology-optimizer
Agent skill for topology-optimizer - invoke with $agent-topology-optimizer.
agent-benchmark-suite
Agent skill for benchmark-suite - invoke with $agent-benchmark-suite.
agent-performance-monitor
Agent skill for performance-monitor - invoke with $agent-performance-monitor.
agent-resource-allocator
Agent skill for resource-allocator - invoke with $agent-resource-allocator.
agentic-jujutsu
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination.