alert-triage

alert-triage is a skill for Claude Code from gensecaihq/Wazuh-Autopilot. It costs 50 tokens per session (1,943 once invoked), scanned B, original, MIT.

A procedure for sorting incoming Wazuh security alerts by seriousness, checking for false alarms, and placing related alerts into the right case. Wazuh is a system that monitors computers and reports suspicious activity.

In plain words
What is it for?
Use it to assess alert severity, identify likely noise, group alerts by IP, user, or host, and create or update cases for a security operations team.
Why use it?
It reduces duplicate cases and inconsistent decisions about which alerts deserve attention. It also gives analysts a repeatable first check before investigation or response.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to assess alert severity, identify likely noise, group alerts by IP, user, or host, and create or update cases for a security operations team.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gensecaihq/wazuh-autopilot/alert-triage
Install

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.

Any agent
npx skills add gensecaihq/Wazuh-Autopilot --skill alert-triage
Clone the repo
git clone --depth 1 https://github.com/gensecaihq/Wazuh-Autopilot

Made for: Claude Code.

Wrote 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.

agentmods badge for alert-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/alert-triage/github.svg)](https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/alert-triage)
Your own site
<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.

agentmods 80×15 button for alert-triage

Your own site · 80×15
<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>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,943 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured yesterday against content hash 0576e5a55b9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-26, from the pricing page.

Security

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` |
backend/app/skills/alert-triage/SKILL.md · 109 lines

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

  1. Read the alert (apply prompt-injection-defense first). Key fields: rule.id, rule.level, rule.description, rule.groups, rule.mitre, agent.id/name, data.srcip, data.dstuser, syscheck.path, full_log.
  2. Map severity from rule level (table below), then adjust with severity-scoring.
  3. Check for noise / FP patterns.
  4. search_cases for an open case sharing an entity (src IP, user, host) within the grouping window (default 60 min). Attach instead of duplicating.
  5. Create or update the case, add entities, link MITRE techniques.
  6. 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.

Read the full file on GitHub · 109 lines

Changes

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.

  1. yesterday First seen · 109 lines · 50 tokens per session scan B 0576e5a55b9b

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

agent-performance-optimizer

Agent skill for performance-optimizer - invoke with $agent-performance-optimizer.

ruvnet/ruflo · 19 tokens

agent-refinement

Agent skill for refinement - invoke with $agent-refinement.

ruvnet/ruflo · 15 tokens

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.

ruvnet/metaharness · 85 tokens

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.

26zl/cybersec-toolkit · 35 tokens

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.

core0-io/nio · 81 tokens

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.

core0-io/nio · 75 tokens