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 trilwu/secskills --skill investigating-windows-endpointsgit clone --depth 1 https://github.com/trilwu/secskillsWrote 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/trilwu/secskills/investigating-windows-endpoints)<a href="https://agentmods.dev/skills/trilwu/secskills/investigating-windows-endpoints"><img src="https://agentmods.dev/badge/skills/trilwu/secskills/investigating-windows-endpoints/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/trilwu/secskills/investigating-windows-endpoints"><img src="https://agentmods.dev/badge/skills/trilwu/secskills/investigating-windows-endpoints.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00186 | $0.05042 |
| Opus 5 | $0.00093 | $0.02521 |
| Sonnet 5 | $0.00037 | $0.01008 |
| Haiku 4.5 | $0.00019 | $0.00504 |
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 11d 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 — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigating Windows Endpoints
Windows records execution, persistence, and access in dozens of artifacts the attacker rarely cleans completely. The event logs are only the surface -- the registry, prefetch, amcache, and the file-system journals corroborate or contradict them. The investigation is cross-referencing independent artifacts into one timeline that no single cleared log can defeat.
When to Use
- Triaging a compromised or suspicious Windows host, live or from an image
- Working through a KAPE, Velociraptor, or EDR triage collection
- Reconstructing what executed on a Windows machine and in what order
- Parsing EVTX / Sysmon / PowerShell logs to reconstruct attacker activity
- Hunting persistence and lateral-movement traces across the endpoint
- Detecting timestomping, log clears, and other on-host anti-forensics
When NOT to Use
- The host is Linux -- use
analyzing-linux-persistence - You need the overall IR process and multi-host coordination -- use
responding-to-incidents; come here when one Windows host is the focus - You have a RAM capture to work -- use
analyzing-memory-images; come here for the on-disk artifacts - The compromise is in cloud identity, not on the endpoint -- use
investigating-m365-entra - Proactive fleet-wide hunting with no specific host -- use
hunting-threats - You are the attacker on the host, not the responder -- use
escalating-windows-privileges
Triage Collection First
Do not analyze the live disk in place. Collect a triage set, hash it, and work on the copy. For most incidents a targeted triage collection answers the question faster than a full image; image only the hosts that matter.
Dead vs. live acquisition. A powered-off host or a mounted disk image is a
dead acquisition -- consistent, but you lose running processes, network state,
and unflushed logs. A live host lets you capture volatile state (memory,
netstat -anob, Get-NetTCPConnection, tasklist /svc) but every action
mutates the disk; record what you touch. Capture memory first if the host is
live and "are they still here" is open, then hand it to analyzing-memory-images.
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.
- 11d ago First seen · 364 lines · 186 tokens per session scan A b29f073364e6
investigating-windows-endpoints is a skill published in the GitHub repository trilwu/secskills (138 stars, last pushed 6d ago), licensed MIT. It adds 186 tokens to every session and 5,042 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…