ir-playbook-ransomware

ir-playbook-ransomware is a skill for Claude Code from gensecaihq/Wazuh-Autopilot. It costs 90 tokens per session (1,975 once invoked), scanned A, original, MIT.

An incident-response guide for investigating ransomware, where attackers encrypt or alter many files and may delete backups, stop services, or erase logs. It covers signs from file monitoring, antivirus, Windows events, and dropped malware files.

In plain words
What is it for?
Use it when monitored files change in bulk, ransom notes appear, antivirus detects malware, backups or shadow copies are removed, services stop, or audit logs are cleared. It helps assess affected hosts and related activity before containment and recovery.
Why use it?
It gives responders a focused process for confirming a fast-moving attack, preserving evidence, and checking whether recovery options were deliberately disabled. This reduces the risk of treating widespread file changes as ordinary activity.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it when monitored files change in bulk, ransom notes appear, antivirus detects malware, backups or shadow copies are removed, services stop, or audit logs are cleared. It helps assess affected hosts and related activity before containment and recovery.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gensecaihq/wazuh-autopilot/ir-playbook-ransomware
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 ir-playbook-ransomware
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 ir-playbook-ransomware

README.md
[![agentmods](https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/ir-playbook-ransomware/github.svg)](https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/ir-playbook-ransomware)
Your own site
<a href="https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/ir-playbook-ransomware"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/ir-playbook-ransomware/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 ir-playbook-ransomware

Your own site · 80×15
<a href="https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/ir-playbook-ransomware"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/ir-playbook-ransomware.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,975 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00090 $0.01975
Opus 5.5 $0.00036 $0.00790
Sonnet 5 $0.00018 $0.00395
Haiku 4.5 $0.00009 $0.00198

Measured yesterday against content hash eba636fb293e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-26, from the pricing page.

Security

Grade A, and why

ir-playbook-ransomware 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.

backend/app/skills/ir-playbook-ransomware/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IR Playbook — Ransomware

Severity critical. Speed matters more than completeness: isolate within 5 minutes of confirmation, scope within 30 minutes. MITRE ATT&CK: T1486 (encrypted for impact), T1490 (inhibit recovery), T1489 (service stop), T1070.001 (log clearing), T1567 (pre-encryption exfil). Rule IDs are from the stock Wazuh 4.14 ruleset (levels official). Full procedure and family indicators: references/playbook.md.

1. Detection signals

Source Signal Wazuh rules (level)
FIM Bulk changes / deletions / additions on monitored paths rules 550 (L7, checksum changed), 553 (L7, file deleted), 554 (L5, file added); group syscheck
FIM (Windows registry) Run keys / services changed rules 594 (L5), 750 (L5), 752 (L5)
Antimalware Defender detection / suspicious behaviour rules 62113 (L14), 62122 (L12), 62123 (L12); Defender protection disabled: rules 92008 (L12), 92009 (L13), 92012 (L13, controlled folder access disabled)
VirusTotal integration Dropped file flagged rule 87105 (L12)
Sysmon file drops Executable in malware-typical folders, Users\Public, Office-created payloads rules 92213 (L15), 92207 (L12), 92214 (L15)
Sysmon network Suspicious binary opened a network connection rule 92104 (L15)
Log tampering Security log cleared (Event ID 1102) rule 60117 (L9); rule 63103 (L5)
Credential theft before encryption LSASS / SAM access rules 92900 (L12), 92024 (L14), 92026 (L14)
Rootkit / host anomaly Rootcheck rules 510 (L7), 521 (L11, possible kernel-level rootkit)
Microsoft Graph (if integrated) Defender for Endpoint ransomware alert rules 99535 (L12), 99594 (L15)

Stock gaps — the org must create these (range 100000–120000, validate with wazuh-logtest):

  • Mass FIM burst: custom rule 100401 — frequency ≥ 100 over group syscheck in 60 s, <same_field>agent.id</same_field>.
  • Ransom-note / encrypted-extension creation: custom rule 100402 — syscheck.path matching note names (README*.txt, *DECRYPT*, *RESTORE*) or known extensions.
  • Recovery inhibition: custom rule 100403 — Sysmon Event ID 1 commandLine matching vssadmin.*delete shadows, wmic shadowcopy delete, bcdedit.*recoveryenabled no, wbadmin delete catalog. The stock ruleset has no rule for these commands; treat them as critical.
  • Backup / VSS service stopped: custom rule 100404 on System-log Event ID 7036/7040 for VSS and backup agents.

Read the full file on GitHub · 103 lines

Files

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.

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 · 103 lines · 90 tokens per session scan A eba636fb293e

Subscribe to this mod's changes

ir-playbook-ransomware is a skill published in the GitHub repository gensecaihq/Wazuh-Autopilot (57 stars, last pushed 2d ago), licensed MIT. It adds 90 tokens to every session and 1,975 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.