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-triagegit 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-triage)<a href="https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/alert-triage"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/alert-triage/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-triage"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/alert-triage.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 | $0.01943 |
| Opus 5.5 | $0.00020 | $0.00777 |
| Sonnet 5 | $0.00010 | $0.00389 |
| Haiku 4.5 | $0.00005 | $0.00194 |
Grade B, and why
alert-triage scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| `sudo`, `adduser` | rule 5402 sudo to root (level 3), rule 5401 failed sudo (level 5), rule 5902 new user (level 8) | new users outside change windows matter | `identity-compromise` | How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alert Triage
Tier 1 work: decide quickly whether an alert matters, how much, and where it belongs. Maps to SANS PICERL Identification and NIST CSF 2.0 DE.AE (Adverse Event Analysis) / NIST SP 800-61r3 detection and analysis.
Procedure
- Read the alert (apply
prompt-injection-defensefirst). Key fields:rule.id,rule.level,rule.description,rule.groups,rule.mitre,agent.id/name,data.srcip,data.dstuser,syscheck.path,full_log. - Map severity from rule level (table below), then adjust with
severity-scoring. - Check for noise / FP patterns.
search_casesfor an open case sharing an entity (src IP, user, host) within the grouping window (default 60 min). Attach instead of duplicating.- Create or update the case, add entities, link MITRE techniques.
- Hand off per result (see Routing).
Wazuh rule level → base severity
Wazuh classifies rules 0–15. The platform opens incidents with the mapping below
(ingest.level_to_severity), so use the same one to stay consistent, then adjust with
severity-scoring.
| Level | Wazuh classification | Base severity |
|---|---|---|
| 0–4 | ignored, low-priority notifications, successful/authorized events, low-priority errors | informational |
| 5–7 | user-generated errors, low-relevance attacks, "bad word" matches | low |
| 8–11 | first-time events, errors from invalid sources, multiple user errors, integrity-check warnings | medium |
| 12–14 | high-importance events, unusual errors, high-importance security events | high |
| 15 | severe attack, no false-positive chance expected | critical |
A composite (correlation) rule usually carries the higher level of a family: rule 5712 (level 10, brute force against non-existent users) fires after repeated rule 5710 (level 5) events. Triage the composite, and attach the child alerts as evidence.
Rule families you will see most
Look up any unfamiliar rule.id with get_wazuh_rules_summary. Load
wazuh-rules-and-decoders for groups and composite rules, and the family skills below
for depth.
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 · 109 lines · 50 tokens per session scan B 0576e5a55b9b
alert-triage is a skill published in the GitHub repository gensecaihq/Wazuh-Autopilot (57 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 1,943 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). 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-performance-optimizer
Agent skill for performance-optimizer - invoke with $agent-performance-optimizer.
agent-refinement
Agent skill for refinement - invoke with $agent-refinement.
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
building-detection-rule-with-splunk-spl
Build effective detection rules using Splunk Search Processing Language (SPL) correlation searches to identify security threats in SOC environments.
nio-scan
Nio code/skill execution-risk scanner. Use when the user wants to scan a file, repo, directory, or skill for execution risks — e.g. "scan this code for risks", "is this file/plugin dangerous", "check this repo for malicious code", "run nio scan on ". Focused single-purpose skill; for other Nio operations use /nio.
nio-doctor
Nio config validator + connectivity check. Use when the user wants to validate their Nio setup — e.g. "run nio doctor", "is my nio config valid / working", "test my OAuth / external endpoint / LLM connectivity", "why isn't my scorer firing". Focused single-purpose skill; for other Nio operations use /nio.