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 EvilFreelancer/secs --skill investigating-windows-endpointsgit clone --depth 1 https://github.com/EvilFreelancer/secsWrote 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/evilfreelancer/secs/investigating-windows-endpoints)<a href="https://agentmods.dev/skills/evilfreelancer/secs/investigating-windows-endpoints"><img src="https://agentmods.dev/badge/skills/evilfreelancer/secs/investigating-windows-endpoints.svg" alt="Measured on agentmods" 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 | $0.00113 | $0.01735 |
| Opus 5 | $0.00056 | $0.00868 |
| Sonnet 5 | $0.00023 | $0.00347 |
| Haiku 4.5 | $0.00011 | $0.00173 |
Grade A, and why
investigating-windows-endpoints 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigating Windows Endpoints
A Windows host records far more about what ran on it than most operators expect — in the MFT, the registry, execution caches, and shell history — and most of it survives a reboot and a deleted file. The investigator's job is to read those artifacts in the right order, correlate them into one timeline, and separate the adversary's activity from the machine's normal churn. The trap is contamination: every interactive command you run on a live host writes new artifacts and can overwrite the very evidence you came for. Preserve before you poke.
Order of volatility governs the first move: if the host is live and the memory is
worth having, capture RAM before disk (hand it to analyzing-memory-images).
Record what you touch and when, so your own footprint is separable from the
adversary's in the timeline. Confirm the host is in scope per
AGENTS.md before acquisition.
When to Use
- A Windows endpoint is suspected of compromise and needs disk/registry triage
- Reconstructing what executed, when, and by whom from on-disk artifacts
- Finding persistence, lateral-movement, and data-staging evidence on a host
- Confirming or refuting a hunt lead or an alert on a specific machine
- Producing a host timeline for an incident
When NOT to Use
- A memory image / RAM capture — use
analyzing-memory-images; injected code and live process state live there, not on disk - A specific suspicious binary — hand it to
analyzing-malware - Network evidence — use
analyzing-network-traffic - The compromise is in the cloud control plane — use
investigating-aws-incidents,investigating-azure-incidents, orinvestigating-gcp-incidents - Proactive search with no specific host in hand — use
hunting-threats - Running the whole incident (scoping, containment, comms) — use
responding-to-incidents; this skill is the host-artifact deep dive within it
Preserve First (order of volatility)
- If live and warranted: memory, then active processes/connections/services — before disk changes them.
- Triage-image the artifacts rather than working the live filesystem. KAPE collects the standard set fast:
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 · 120 lines · 113 tokens per session scan A 63c012e7414a
investigating-windows-endpoints is a skill published in the GitHub repository EvilFreelancer/secs (10 stars, last pushed 29d ago), licensed Apache-2.0. It adds 113 tokens to every session and 1,735 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
analyzing-slack-space-and-file-system-artifacts
Examine file system slack space, MFT entries, USN journal, and alternate data streams to recover hidden data and reconstruct file activity on NTFS volumes.
analyzing-supply-chain-malware-artifacts
Investigate supply chain attack artifacts including trojanized software updates, compromised build pipelines, and sideloaded dependencies to identify intrusion vectors and scope of compromise.
ctf-rev
Use when solving a CTF reverse engineering challenge — stripped binaries, packed binaries, anti-debug, custom VMs, .NET/Java decomp, Android dex, obfuscated JS, ELF/PE/Mach-O analysis. Provides workflow and tool ordering from the reversing module. Triggers on "ctf rev", "reversing", "reverse engineer", "decompile"…
ctf-pwn
Use when solving binary exploitation / pwn CTF challenges — buffer overflows, ROP, format strings, heap, kernel pwn. Provides a decision tree, exploit primitive catalog, and uses pwntools via the runscript(venv="pwntools") MCP path. Triggers on "ctf pwn", "binary exploit", "rop", "buffer overflow", "format string"…
deobfuscating-powershell-obfuscated-malware
Systematically deobfuscate multi-layer PowerShell malware using AST analysis, dynamic tracing, and tools like PSDecode and PowerDecode to reveal hidden payloads and C2 infrastructure.
analyzing-linux-elf-malware
Analyzes malicious Linux ELF (Executable and Linkable Format) binaries including botnets, cryptominers, ransomware, and rootkits targeting Linux servers, containers, and cloud infrastructure. Covers static analysis, dynamic tracing, and reverse engineering of x8664 and ARM ELF samples. Activates for requests involving…