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 meltedinhex/analyst-ai-pack --skill hunting-ransomware-precursor-behaviorgit clone --depth 1 https://github.com/meltedinhex/analyst-ai-packWrote 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/meltedinhex/analyst-ai-pack/hunting-ransomware-precursor-behavior)<a href="https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/hunting-ransomware-precursor-behavior"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/hunting-ransomware-precursor-behavior/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/meltedinhex/analyst-ai-pack/hunting-ransomware-precursor-behavior"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/hunting-ransomware-precursor-behavior.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 | $0.00076 | $0.00749 |
| Opus 5 | $0.00038 | $0.00375 |
| Sonnet 5 | $0.00015 | $0.00150 |
| Haiku 4.5 | $0.00008 | $0.00075 |
Grade A, and why
hunting-ransomware-precursor-behavior 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 8d ago.
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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting Ransomware Precursor Behavior
When to Use
- You have endpoint process/command telemetry and want to catch the steps ransomware takes before encrypting — deleting shadow copies, disabling recovery, killing security tools, and stopping backup/database services.
- You want early warning to intervene before payload detonation.
Do not use this as a substitute for blocking the encryption itself — it is an early-warning hunt for the preparation phase, not a recovery procedure.
Prerequisites
- Process-creation telemetry (with command line) and optionally service/file telemetry.
Workflow
Step 1: Hunt recovery-inhibition commands
python scripts/analyst.py hunt events.csv
Flags vssadmin delete shadows, wmic shadowcopy delete, wbadmin delete catalog,
bcdedit /set recoveryenabled no / bootstatuspolicy ignoreallfailures, and wevtutil cl.
Step 2: Detect defense and service tampering
Surface stopping/killing of AV/EDR and backup/DB services (net stop, taskkill,
sc stop) targeting veeam, sql, backup, sophos, defender, etc.
Step 3: Correlate and prioritize
A host showing recovery-inhibition + service-stop in a short window is a high-priority pre-encryption signal — escalate immediately.
Step 4: Operationalize
Write a high-severity detection for shadow-copy deletion and recovery disabling.
Validation
- Recovery-inhibition commands are detected with their specific syntax.
- Security/backup service tampering is identified by target service names.
- Findings map to ATT&CK T1490 / T1489 (and precede T1486).
Pitfalls
- Admins occasionally delete shadow copies legitimately — corroborate with co-occurring tampering.
- LOLBin variants (
wmic, PowerShellGet-WmiObject Win32_ShadowCopy | Remove) evadingvssadmin-only rules. - Fast attacks where precursor and encryption are near-simultaneous — alert must be real-time.
References
- See
references/api-reference.mdfor the hunter. - ATT&CK T1490 and T1486 (linked in frontmatter).
What ships with it
3 files 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.
- 8d ago First seen · 90 lines · 76 tokens per session scan A b221dcf86f05
hunting-ransomware-precursor-behavior is a skill published in the GitHub repository meltedinhex/analyst-ai-pack (22 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 749 once invoked, about $0.0004 per session on Opus 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 2026-09-03.
Other skills, from other repositories
analyzing-cobalt-strike-beacon-configuration
Extract and analyze Cobalt Strike beacon configuration from PE files and memory dumps to identify C2 infrastructure, malleable profiles, and operator tradecraft.
analyzing-golang-malware-with-ghidra
Reverse engineer Go-compiled malware in Ghidra by parsing Go buildinfo and pclntab structures, recovering stripped/obfuscated function names (e.g. via GoResolver), and extracting embedded module/dependency strings and types from Go binaries. Use when analyzing a Go-language malware sample, deobfuscating a…
analyzing-malicious-pdf-with-peepdf
Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects. Use when triaging a suspicious PDF attachment from a phishing email, analyzing a PDF-based exploit document, or building detection signatures for weaponized PDF…
analyzing-malicious-pdf-with-peepdf
A Chinese-language skill for examining suspicious PDF files with peepdf, pdfid, and pdf-parser. It is intended for static malware analysis, which studies a file without running it.
yara-rule-writing-malware
Write custom YARA rules to identify and classify malware based on textual and binary patterns. This skill focuses on creating robust signatures using strings, regular expressions, and hexadecimal opcodes extracted during malware analysis for enterprise threat hunting.
analyzing-malicious-pdf-with-peepdf
Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects.