Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/akashrpatil/awesome-offensive-security-skillsnpx agentmods add skills/akashrpatil/awesome-offensive-security-skills/windows-prefetch-analysisWrote 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/akashrpatil/awesome-offensive-security-skills/windows-prefetch-analysis)<a href="https://agentmods.dev/skills/akashrpatil/awesome-offensive-security-skills/windows-prefetch-analysis"><img src="https://agentmods.dev/badge/skills/akashrpatil/awesome-offensive-security-skills/windows-prefetch-analysis/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/akashrpatil/awesome-offensive-security-skills/windows-prefetch-analysis"><img src="https://agentmods.dev/badge/skills/akashrpatil/awesome-offensive-security-skills/windows-prefetch-analysis.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 | $0.00055 | $0.01165 |
| Opus 5 | $0.00028 | $0.00583 |
| Sonnet 5 | $0.00011 | $0.00233 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
windows-prefetch-analysis 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 7d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Windows Prefetch Analysis
When to Use
- When investigating a compromised Windows system to answer the question: "Did the attacker actually run this tool/malware?"
- To build a timeline of threat actor activities by examining execution timestamps and accessed files.
- When an attacker has deleted their malware, but the prefetch file remains as evidence.
Prerequisites
- Forensic image or live access to the affected system(s)
- Forensic workstation with analysis tools (Autopsy, Volatility, Timeline Explorer)
- Chain of custody documentation initiated for evidence handling
- Write-blocker for disk forensics or memory acquisition tool (e.g., DumpIt, WinPmem)
Workflow
Phase 1: Locating and Understanding Prefetch Files
Prefetch files are typically located at C:\Windows\Prefetch.
They are named ending with .pf (e.g., CMD.EXE-4A81B364.pf).
Note: Prefetch is enabled by default on Windows Client OS architectures but may be disabled on Windows Servers.
Phase 2: Offline Analysis with PECmd (Eric Zimmerman's Tools)
# Concept: Parse a single prefetch file PECmd.exe -f "C:\Windows\Prefetch\MIMIKATZ.EXE-53D22409.pf"
# PECmd.exe -d "C:\Windows\Prefetch\" -q --csv "C:\Forensics\Output" --csvf "prefetch_timeline.csv"
Phase 3: Interpreting the Output
When examining the parsed output, focus on:
- Run Count: How many times was the binary executed?
- Execution Times: Up to 8 previous execution timestamps (depending on OS version). Last execution time is crucial for timeline building.
- Files/Directories Accessed: The directories and files the program loaded (e.g., DLLs, configuration files, text files the attacker interacted with).
Phase 4: Basic Live System Check (Powershell)
# Get-ChildItem -Path "C:\Windows\Prefetch" | Where-Object { $_.Name -match "MIMIKATZ|PSEXEC|NC.EXE" } | Select-Object Name, LastWriteTime
Decision Point 🔀
flowchart TD
A[Locate Prefetch Folder ] --> B{Prefetch Enabled? ]}
B -->|Yes| C[Extract .pf Files ]
B -->|No| D[Check ShimCache/Amcache ]
C --> E[Parse with PECmd ]
What ships with it
2 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.
- 7d ago First seen · 122 lines · 55 tokens per session scan A e6b0748fbebf
windows-prefetch-analysis is a skill published in the GitHub repository akashrpatil/awesome-offensive-security-skills (4 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,165 once invoked, about $0.0003 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
Incident Response & Digital Forensics
IR playbook execution, evidence collection, forensic timeline analysis, memory forensics, and post-incident reporting following NIST SP 800-61 and SANS PICERL methodology.
performing-cloud-forensics-with-aws-cloudtrail
Perform forensic investigation of AWS environments using CloudTrail logs to reconstruct attacker activity, identify compromised credentials, and analyze API call patterns.
collecting-volatile-evidence-from-compromised-host
Collect volatile forensic evidence from a compromised system following order of volatility, preserving memory, network connections, processes, and system state before they are lost.
agent-artifact-catalog
Research, author, and validate AI agent artifact catalog entries documenting the forensic artifacts AI agents leave on endpoints - install paths, config and credential files, MCP server configs, listening ports, process trees, registry keys, and the Windows event log records that prove a tool ran. Use this skill…
collecting-volatile-evidence-from-a-suspect-host
Collects volatile evidence from a potentially compromised host in correct order of volatility: memory, network state, running processes, logged-on users, and open handles, while preserving integrity and minimizing footprint. Activates for requests to collect volatile evidence, perform live response, or capture host…
forensics-checklist
Guides digital forensic evidence collection following NIST SP 800-86 and RFC 3227 order of volatility. Auto-invoked when the user needs to collect forensic evidence, preserve chain of custody, capture volatile data, create disk images, or handle cloud forensics. Produces an evidence collection plan with…