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 incident-timelinegit 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/incident-timeline)<a href="https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/incident-timeline"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/incident-timeline/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/incident-timeline"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/incident-timeline.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 | $0.00041 | $0.01026 |
| Opus 5.5 | $0.00016 | $0.00410 |
| Sonnet 5 | $0.00008 | $0.00205 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
incident-timeline 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incident Timeline
A timeline turns a pile of alerts into a story a responder or executive can act on. NIST SP 800-61r3 expects incident documentation of what happened, when, and how it was detected; the timeline is the backbone of that record.
Procedure
get_case— gather attached alerts, entities, findings, actions.- Pull supporting events for the key entities over the incident window
(
search_security_events,get_wazuh_alertsfiltered by agent/user/ip). - Normalize every timestamp to UTC ISO 8601. A Wazuh alert's
timestampis when the manager processed the event. The original event time is in the log itself (predecoder.timestamp, or the time at the start offull_log, ordata.win.system.systemTimefor Windows). Use the event time when they differ by more than a few seconds, and note clock skew or delayed delivery (e.g. an agent reconnecting and flushing its buffer). - Order events; collapse repetitive ones ("38 sshd failures 09:02–09:12"). Wazuh composite rules summarize bursts: one rule 5763 or rule 5712 alert stands for several single failures (rules 5716, 5760, 5710), so count the underlying failures, not the composites.
- Label each event with an ATT&CK tactic where possible.
- Identify the key milestones and gaps.
Milestones to identify
| Milestone | Definition |
|---|---|
| First malicious activity | Earliest event attributable to the attacker (may predate the first alert) |
| Initial access | First successful foothold (login success, exploit, execution) |
| First detection | Timestamp of the first Wazuh alert on this activity |
| Escalation / spread | Privilege gain, new host touched |
| Containment | Time an approved action was executed and verified |
| Last activity | Latest attacker event |
Derived metrics:
- Dwell time = first detection − first malicious activity.
- Time to contain = containment − first detection.
- Active duration = last activity − first malicious activity.
Pivot points
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 · 83 lines · 41 tokens per session scan A 8afb3a9e6485
incident-timeline is a skill published in the GitHub repository gensecaihq/Wazuh-Autopilot (57 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 1,026 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.