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 Encod3d-Sec/TORCH --skill hunt-windowsgit clone --depth 1 https://github.com/Encod3d-Sec/TORCHWrote 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/encod3d-sec/torch/hunt-windows)<a href="https://agentmods.dev/skills/encod3d-sec/torch/hunt-windows"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/hunt-windows/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/encod3d-sec/torch/hunt-windows"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/hunt-windows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high YARA Match · line 23 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00117 | $0.01830 |
| Opus 5.5 | $0.00047 | $0.00732 |
| Sonnet 5.5 | $0.00023 | $0.00366 |
| Haiku 4.5 | $0.00012 | $0.00183 |
Grade A, and why
hunt-windows 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 1mo 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunt: Windows (local privilege escalation)
Assumes hunt-core for the scope gate, two-account rule, confirmation gate, enumeration limits, stop conditions, wiki protocol, FIND output, and Deadends. Do not re-derive any of that here.
Scope of this skill vs hunt-ad: this is LOCAL privesc on ONE Windows host - a standalone/workgroup box, or getting from a low-priv user to SYSTEM on a domain member. DOMAIN escalation (user enum, AS-REP/Kerberoast, delegation, ADCS, DCSync, BloodHound) is Skill(hunt-ad). Tell them apart from the SMB/enum banner: a single-label domain: that equals the hostname (e.g. domain:PRIVESC) or WORKGROUP = standalone -> this skill; a dotted FQDN realm (domain:corp.local) or a DC (kerberos/88) = AD -> hunt-ad. On a domain member both can apply (local SYSTEM here, domain moves there).
Wiki
qmd_query "Windows local privilege escalation service misconfig unquoted path SeImpersonate potato AlwaysInstallElevated autologon scheduled task DLL hijack UAC bypass" via wiki-search MCP
Primary page: [[windows-privesc]] (the full checklist + commands + Defender-evasion-at-the-loader). Enumeration: [[windows-enumeration]]. Kernel-LPE / Potato fallback arsenal: [[privesc-exploit-arsenal]].
Tool anchor: [[netexec]] (the full nxc map). Even on a standalone box nxc is the remote-side workhorse: --local-auth credential checks across the subnet, --shares/--dir/-M spider_plus, --sam/--lsa/--dpapi looting, -M enum_av before you drop a payload, --tasklist/--qwinsta instead of noisy -x equivalents, and the loot modules (winscp, putty, rdcman, mremoteng, keepass, notepad, eventlog_creds) that beat manual hunting for stored creds.
Exec channel (read this before driving a shell)
Windows footholds are usually RDP or a reverse shell, rarely WinRM (unless the user is in Remote Management Users). Drive a PowerShell reverse shell with bash scripts/win-rsh.sh <eng> '<one command>' and follow docs/shell-interaction.md: ONE command per call, NO injected markers, type $env:/$_ plainly (it escapes for the bridge). RDP-only, non-admin, non-WinRM user -> headless xfreerdp + an in-memory PS cradle (see [[network-services]]). Defender is often live: a dropped RunasCs.exe/winPEASx64.exe gets quarantined - deliver in-memory (IEX(New-Object Net.WebClient).DownloadString(...)), or a freshly-compiled (unsigned-but-unknown) stager, or a Microsoft-signed tool (accesschk). Solve evasion once at the loader ([[windows-privesc]]).
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.
- 1mo ago First seen · 55 lines · 117 tokens per session scan A 36499a4fca33
hunt-windows is a skill published in the GitHub repository Encod3d-Sec/TORCH (336 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 1,830 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…