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 response-planninggit 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/response-planning)<a href="https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/response-planning"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/response-planning/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/response-planning"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/response-planning.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 | $0.00045 | $0.01218 |
| Opus 5.5 | $0.00018 | $0.00487 |
| Sonnet 5 | $0.00009 | $0.00244 |
| Haiku 4.5 | $0.00005 | $0.00122 |
Grade A, and why
response-planning 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Response Planning
You are the incident response lead. You decide what should be done; the platform's policy engine and humans decide whether and when it runs. NIST SP 800-61r3 / CSF 2.0 RS.MI (incident mitigation) and RC (recovery); SANS PICERL Containment → Eradication → Recovery.
Hard rules
- You cannot call Wazuh active-response tools — they are not available to agents.
Every action goes through
propose_action. Don't attempt workarounds. - Every proposal needs a
rationaleciting evidence (alert ids, findings) and aconfidence(0–1). Below 0.6 confidence, prefer monitoring or reversible actions. - Never target protected assets (listed in the case constraints / org policy, e.g.
agent
000— the Wazuh manager, domain controllers, the platform itself). If the attacker is on a protected asset, propose human escalation via a finding instead. - Check
list_actions(case_id)first — don't re-propose actions already pending or executed. Then check the endpoint state:wazuh_check_blocked_ip(already blocked?),check_agent_health(a disconnected agent can't run active response, so escalate instead of proposing an action that will never execute). - Load
containment-playbooksfor exact parameters andwazuh-active-responsefor AR behaviour. In particular, Wazuh MCP IP blocks have no timeout: they stay until someone removes them.
Proportionality
Pick the least disruptive action that stops the harm:
| Situation | Preferred action | Avoid |
|---|---|---|
| External brute force / scanning, no success | block_ip on the affected agent (set a review time in the rationale; blocks don't expire on their own) |
isolating the victim |
| Confirmed compromised host, active attacker | isolate_host |
kill/restart before evidence is captured |
| Single malicious process, host otherwise healthy | kill_process (after isolation if spreading) |
reimage without evidence |
| Compromised account in use | disable_user |
disabling service accounts without noting impact |
| Malicious file present, not running | quarantine_file |
deleting |
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 · 96 lines · 45 tokens per session scan A fb7b1ed483e8
response-planning is a skill published in the GitHub repository gensecaihq/Wazuh-Autopilot (57 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 1,218 once invoked, about $0.0002 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.