thm-claude-kit
CLAUDE.md2 starsChanged 4 months agoMITView on GitHub
In this repository4 other files it gives its agents.
- network-forensicsSkill
- thm-methodologySkill
- thm-trainerSkill
- windows-ad-methodologySkill
The file
We split this CLAUDE.md into the rules it gives an agent
7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
ONLY test the active target IP(s) listed in the current room's notes.md
- Distinctive: line 10
Never scan or touch anything outside the assigned target
- Very specific: line 14
Always save raw tool output to ./scans/<tool>-<timestamp>.txt
- Distinctive: line 15
Keep notes.md updated with findings as we go (open ports, services, creds, flags)
- Distinctive: line 16
After every scan, summarize findings and propose the next 2-3 concrete steps
- Distinctive: line 17
Prefer non-destructive enumeration first.
- Distinctive: line 27
When stuck (repeating actions with no new info), stop and reclassify rather than scanning harder.
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
TryHackMe Attack Machine Context
Environment
- Kali, or any Debian/Ubuntu-based Linux with the offensive tooling installed
- Tools: nmap, ffuf, gobuster, nikto, whatweb, tshark, sqlmap, hydra, netcat, enum4linux, smbclient, john, hashcat
- Connected to THM via OpenVPN (tun0)
Scope & Rules
- ONLY test the active target IP(s) listed in the current room's notes.md
- Never scan or touch anything outside the assigned target
- This is authorized CTF practice on TryHackMe boxes only
Workflow preferences
- Always save raw tool output to ./scans/
<tool>-<timestamp>.txt - Keep notes.md updated with findings as we go (open ports, services, creds, flags)
- After every scan, summarize findings and propose the next 2-3 concrete steps
- Prefer non-destructive enumeration first; ask before anything intrusive (brute force, exploit)
- Wordlists live in /usr/share/wordlists/ (seclists, rockyou.txt)
Output style
- Be terse. Show the command, key findings, next step.
Approach — run the loop
For every room, follow the thm-trainer skill (classify -> observe -> hypothesize -> test -> decide). Classify the room and name the goal BEFORE running any tool. Start a room with /start (paste the room description; do not pass a URL — THM is behind auth). When stuck (repeating actions with no new info), stop and reclassify rather than scanning harder.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

