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-windows-sysmongit 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-windows-sysmon)<a href="https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/wazuh-windows-sysmon"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/wazuh-windows-sysmon/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-windows-sysmon"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/wazuh-windows-sysmon.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 | $0.00067 | $0.01623 |
| Opus 5.5 | $0.00027 | $0.00649 |
| Sonnet 5.5 | $0.00013 | $0.00325 |
| Haiku 4.5 | $0.00007 | $0.00162 |
Grade A, and why
wazuh-windows-sysmon 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 1mo 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wazuh Windows and Sysmon
Windows logs reach Wazuh through the EventChannel collector and are decoded as JSON under data.win.*.
Security-log rules live in the windows_security group; Sysmon rules in the sysmon group.
Field paths
| Field | Content |
|---|---|
data.win.system.eventID |
Windows Event ID |
data.win.system.channel |
Security, System, Microsoft-Windows-Sysmon/Operational, … |
data.win.system.computer |
Host name as Windows reports it |
data.win.eventdata.targetUserName / subjectUserName |
Account acted on / acting account |
data.win.eventdata.logonType |
Logon type (below) |
data.win.eventdata.ipAddress / workstationName |
Source of a network logon |
data.win.eventdata.status / subStatus |
Failure reason codes |
data.win.eventdata.image, parentImage, commandLine, hashes |
Sysmon process fields |
data.win.eventdata.destinationIp, destinationPort |
Sysmon network fields |
data.win.eventdata.targetObject |
Sysmon registry target |
Security log: Event ID → Wazuh rule
| Windows event | Wazuh rule (level) | Notes |
|---|---|---|
| Event ID 4624 logon success | rule 60106 (level 3) | Workstation variant: rule 60118 (level 3) |
| Event ID 4625 logon failure | rule 60122 (level 5) | Parent: rule 60105 (level 5) |
| Repeated Event ID 4625 | rule 60204 (level 10) | Correlation: multiple Windows logon failures within 240s |
| Event ID 4740 account locked out | rule 60115 (level 9) | |
| Event ID 4720 / Event ID 4722 account created / enabled | rule 60109 (level 8) | |
| Event ID 4738 account changed | rule 60110 (level 8) | |
| Administrators group changed | rule 60154 (level 12) | Privilege escalation / persistence |
| Event ID 4672 special privileges assigned | rule 67028 (level 3) | In the WEF baseline ruleset; noisy on its own — join with 4624 for the same logon |
| Event ID 1102 audit log cleared | rule 60117 (level 9) | Also rule 593 (level 9, "Microsoft Event log cleared") — defence evasion, always investigate |
| Audit policy changed | rule 60112 (level 8) | |
| Event ID 7045 new service installed (System log) | rule 61138 (level 5) | Persistence / lateral movement (PsExec creates a service) |
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.
- 1mo ago First seen · 95 lines · 67 tokens per session scan A 474f8aa04774
wazuh-windows-sysmon is a skill published in the GitHub repository gensecaihq/Wazuh-Autopilot (63 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,623 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.
wazuh-windows-sysmon compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wazuh-windows-sysmongensecaihq/Wazuh-Autopilot | Skill | 63 | 1mo ago | MIT | A | 67 | Claude Code |
| paperclip-create-agentpaperclipai/paperclip | Skill | 113k | today | MIT | A | 44 | Claude Code, Codex |
| agent-crdt-synchronizerruvnet/ruflo | Skill | 81k | today | MIT | A | 25 | Claude Code |
| ramppaperclipai/paperclip | Skill | 113k | today | MIT | A | 35 | Claude Code, Codex |
| agent-topology-optimizerruvnet/ruflo | Skill | 81k | today | MIT | A | 21 | Claude Code |
| suggestion-boxpaperclipai/paperclip | Skill | 113k | today | MIT | A | 37 | Claude Code, Codex |
| agent-release-swarmruvnet/ruflo | Skill | 81k | today | MIT | A | 19 | Claude Code |