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 hypnguyen1209/offensive-claude --skill keylogger-archgit clone --depth 1 https://github.com/hypnguyen1209/offensive-claudeWrote 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/hypnguyen1209/offensive-claude/keylogger-arch)<a href="https://agentmods.dev/skills/hypnguyen1209/offensive-claude/keylogger-arch"><img src="https://agentmods.dev/badge/skills/hypnguyen1209/offensive-claude/keylogger-arch/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/hypnguyen1209/offensive-claude/keylogger-arch"><img src="https://agentmods.dev/badge/skills/hypnguyen1209/offensive-claude/keylogger-arch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 26 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
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 | $0.00000 | $0.01699 |
| Opus 5 | $0.00000 | $0.00849 |
| Sonnet 5 | $0.00000 | $0.00340 |
| Haiku 4.5 | $0.00000 | $0.00170 |
Grade A, and why
keylogger-arch 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- keylogger-arch — 88% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: keylogger-architecture description: Use when designing or analyzing keystroke/input capture — SetWindowsHookEx, raw input devices, ETW-based capture, kernel drivers, stealth techniques and their IOCs metadata: type: offensive phase: research kill_chain: phase: [install, actions] step: [5, 7] attck_tactics: [TA0003, TA0009] depends_on: [privesc-windows, edr-evasion] feeds_into: [red-team-ops] inputs: [target_os, edr_product] outputs: [keylogger_binary, captured_input]
Keylogger Architecture
When to Activate
- Understanding input capture mechanisms for red team implants
- Analyzing malware keylogging capabilities
- EDR evasion research for input monitoring
- Designing stealthy credential capture
Method 1: SetWindowsHookEx (WH_KEYBOARD_LL)
How It Works
// Install global low-level keyboard hook
HHOOK hHook = SetWindowsHookEx(WH_KEYBOARD_LL, LowLevelKeyboardProc, hInstance, 0);
LRESULT CALLBACK LowLevelKeyboardProc(int nCode, WPARAM wParam, LPARAM lParam) {
if (nCode == HC_ACTION) {
KBDLLHOOKSTRUCT *kb = (KBDLLHOOKSTRUCT*)lParam;
if (wParam == WM_KEYDOWN || wParam == WM_SYSKEYDOWN) {
LogKey(kb->vkCode);
}
}
return CallNextHookEx(NULL, nCode, wParam, lParam);
}
// MUST pump messages — hook won't fire without message loop
MSG msg;
while (GetMessage(&msg, NULL, 0, 0)) {
TranslateMessage(&msg);
DispatchMessage(&msg);
}
Internal Mechanism
SetWindowsHookEx→NtUserSetWindowsHookExin win32k.sys- Kernel creates HOOK structure, inserts at head of global hook chain
- Low-level hooks (WH_KEYBOARD_LL): NO DLL injection — events delivered via internal message to installing process
- Regular hooks (WH_KEYBOARD): DLL injected into every target process via APC
IOCs
- Hook entry visible in
!hookWinDbg command - Installing thread must pump messages (detectable by message queue footprint)
- If regular hook: mapped DLL in every hooked process (VAD artifact)
- EDR can hook
user32!SetWindowsHookExto detect installation
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.
- 12d ago First seen · 204 lines · 0 tokens per session scan A 6c972916a8a5
keylogger-arch is a skill published in the GitHub repository hypnguyen1209/offensive-claude (360 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,699 tokens. 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
bt6-queue-audit
Audit the full pull-request and issue queue of a BT6 research or support repository, classifying readiness, evidence risk, and next action without mutating tracker state.
bt6-issue-steward
Triage and steward issues in BT6 research and support repositories, deciding whether to answer, reproduce, correct evidence, link work, design a feature, route security, implement, or close.
bt6-merge-train
Run an explicitly authorized, conservative BT6 merge train that processes validated pull requests one at a time and reconciles repository, CI, evidence, and issue state after each merge.
bt6-pr-audit
Audit one pull request in a BT6 research or support repository at an exact head SHA, covering correctness, research integrity, security, tests, contracts, and merge readiness.
bt6-provider-review
Audit an external AI/API provider and its integration into a BT6 repository for service reality, independent verification, trust boundaries, secret handling, API/model correctness, completeness, claim traceability, and merge readiness.
xiaohongshu-search-full
Search Xiaohongshu (XHS / RedNote) notes by keyword with full field extraction including body text, topics/tags, image list URLs, video stream URL, publish timestamp, and all engagement stats (likes, collects, comments, shares). Supports all page filter options: sort order (general, latest, most liked, most commented…