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 ir-playbook-vulnerability-spikegit 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/ir-playbook-vulnerability-spike)<a href="https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/ir-playbook-vulnerability-spike"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/ir-playbook-vulnerability-spike/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/ir-playbook-vulnerability-spike"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/ir-playbook-vulnerability-spike.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 | $0.00106 | $0.01961 |
| Opus 5.5 | $0.00042 | $0.00784 |
| Sonnet 5 | $0.00021 | $0.00392 |
| Haiku 4.5 | $0.00011 | $0.00196 |
Grade A, and why
ir-playbook-vulnerability-spike 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IR Playbook — Vulnerability Spike (PB-005)
Owned by the vuln-management agent; escalates to the incident swarm when exploitation is observed. Severity
varies with CVSS, KEV status, exposure and asset criticality. MITRE ATT&CK (exploitation): T1190, T1203, T1210,
T1068. Rule IDs are from the stock Wazuh 4.14 ruleset (levels official). Full procedure: references/playbook.md.
1. Detection signals
| Signal | Wazuh rules (level) | Trigger |
|---|---|---|
New active vulnerabilities by severity (group vulnerability-detector) |
rule 23506 (L13, Critical), rule 23505 (L10, High), rule 23504 (L7, Medium), rule 23503 (L5, Low) | spike > 3σ above the 7-day average and ≥ 10 findings |
| Vulnerability fixed / cleared | rule 23502 (L3, CVE solved by an update), rule 23507 (L3, vulnerabilities cleared) | use for remediation tracking, not as new findings |
| CVE without severity yet | rule 23508 (L3, awaiting analysis) | re-check once NVD scores it |
| Same CVE on many hosts | vulnerability inventory (get_wazuh_vulnerabilities) |
CVE on ≥ 20 % of hosts and ≥ 5 hosts |
| Web exploitation attempts | rules 31103 (L7, SQL injection), 31104 (L6, common web attack), 31106 (L6, web attack returned HTTP 200), 31152 (L10, multiple SQLi from one source), 31153 (L10, multiple web attacks from one source), 31115 (L13, over-long URL) | against a vulnerable asset |
| IDS / exploit attempts | rule 86601 (L3, Suricata alert — severity comes from the signature), rule 40104 (L13, possible buffer overflow) | ≥ 5 attempts or 5× daily average |
| Hardening regression (SCA) | rule 19011 (L9, check passed → failed), rule 19014 (L9, not applicable → failed), rule 19004 (L7, policy score < 50 %), rule 19005 (L9, score < 30 %) | clusters on the same benchmark control |
| KEV match | CISA KEV catalog (external) | any KEV-listed CVE present → auto-escalate |
Note: the detector's levels follow the CVE severity label (Low/Medium/High/Critical), not a CVSS threshold you set.
2. Assessment (vuln-management agent)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 100 lines · 106 tokens per session scan A b548570c967a
ir-playbook-vulnerability-spike is a skill published in the GitHub repository gensecaihq/Wazuh-Autopilot (57 stars, last pushed 2d ago), licensed MIT. It adds 106 tokens to every session and 1,961 once invoked, about $0.0004 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.