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 wazuh-platform-healthgit 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/wazuh-platform-health)<a href="https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/wazuh-platform-health"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/wazuh-platform-health/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/wazuh-platform-health"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/wazuh-platform-health.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 | $0.00066 | $0.01443 |
| Opus 5.5 | $0.00026 | $0.00577 |
| Sonnet 5 | $0.00013 | $0.00289 |
| Haiku 4.5 | $0.00007 | $0.00144 |
Grade A, and why
wazuh-platform-health 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wazuh Platform Health
A SOC is blind where Wazuh is blind. An attacker who stops an agent, floods its queue or clears a log produces less telemetry, not more — so absence of alerts is not evidence of safety. This skill finds the gaps.
Check sequence (scheduled run)
- Connectivity to Wazuh:
validate_wazuh_connection. If it fails, stop and open a critical case — nothing else is trustworthy. - Manager / cluster:
get_wazuh_cluster_health,get_wazuh_cluster_nodes,list_wazuh_clusters. Any node disconnected or out of sync → high. - Agent fleet:
get_wazuh_agents status="disconnected",status="never_connected",status="pending";get_wazuh_running_agentsfor the active count. Compare with the previous run (from the last report) — sudden drops matter more than a steady handful. - Throughput:
get_wazuh_statistics,get_wazuh_remoted_stats(agent communication: received vs discarded messages, queue usage) andget_wazuh_log_collector_stats— note this tool returns analysisd statistics (events decoded, events dropped, EPS), despite its name. - Errors:
get_wazuh_manager_error_logs, thensearch_wazuh_manager_logswith targeted patterns ("ERROR","Invalid","decoder","rules","queue","disk"). - Platform alerts in the window:
get_wazuh_alerts rule_groups=["agent_flooding","agent_restarting","upgrade","fim_db_state","logs_cleared","low_diskspace"] timestamp_start="now-4h"and agent status rules below. - Silent sources: for crown-jewel agents, compare alert volume now vs the same window yesterday
(
get_wazuh_alerts agent_id="<id>"withtotal_affected_itemsas the count); a normally chatty agent going quiet while connected suggests a stopped log source or tampering. Confirm what should be collected withget_agent_configuration.
Platform rules (stock ruleset)
| Rule | Level | Meaning | Severity for us |
|---|---|---|---|
| rule 504 | 3 | Wazuh agent disconnected | Level 3 by design — high if a server/crown jewel, or several at once |
| rule 506 | 3 | Wazuh agent stopped | High on servers (possible tampering, T1562.001) |
| rule 505 | 3 | Wazuh agent removed | High unless a change ticket exists |
| rule 202 | 7 | Agent event queue is partially full | Medium |
| rule 203 | 9 | Agent event queue is full. Events may be lost | High — detection gap |
| rule 204 | 12 | Agent event queue is flooded | High — also a possible deliberate flood to hide activity |
| rule 205 | 3 | Agent event queue back to normal load | Closes the gap window; record duration |
| rule 220 | 7 | Agent could not restart due to a remote configuration failure | Medium — module may be off |
| rule 216 | 7 | Remote upgrade failed, agent disconnected | High |
| rule 560 | 7 | FIM real-time queue is full, events may be lost | Medium |
| rule 233 | 12 | Maximum limit of files monitored has been reached | High — new files unmonitored |
| rule 531 | 7 | Partition usage reached 100% | High on the manager/indexer |
| rule 592 | 8 | Log file size reduced | Investigate (possible log tampering) |
| rule 593 | 9 | Microsoft Event log cleared | Security incident — hand to triage |
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 · 91 lines · 66 tokens per session scan A 218b20d2b337
wazuh-platform-health is a skill published in the GitHub repository gensecaihq/Wazuh-Autopilot (57 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 1,443 once invoked, about $0.0003 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.