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 agentmods add commands/pashki975/thm-claude-kit/pcapgit 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/pcap)<a href="https://agentmods.dev/commands/pashki975/thm-claude-kit/pcap"><img src="https://agentmods.dev/badge/commands/pashki975/thm-claude-kit/pcap.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 | $0.00021 | $0.01451 |
| Opus 5 | $0.00010 | $0.00726 |
| Sonnet 5 | $0.00004 | $0.00290 |
| Haiku 4.5 | $0.00002 | $0.00145 |
Grade B, and why
pcap 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 4d 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 tshark -i <interface> -w scans/capture.pcap` (Ctrl-C to stop), then analyze that file. How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze traffic for: $ARGUMENTS Expected: a path to a .pcap/.pcapng file, OR "live " to capture first.
tshark is the CLI of Wireshark, so I can actually drive it. Work the same cheap→heavy way as the
enum commands: get the overview first, form a hypothesis about what the room wants, THEN run the
targeted extraction — don't blindly dump every packet. (The network-forensics skill has the
methodology — how to think about a capture; this command has the tshark mechanics.)
The gate
Before a heavy extraction (carving all files, exporting every object, following hundreds of streams), say a one-line hypothesis about what the room is asking for (a credential? a transferred file? a specific conversation? evidence of an attack?) and let the overview point you at it. The protocol breakdown usually tells you where the answer lives — go there, don't grep the whole capture blindly.
0. Live capture first (only if $ARGUMENTS starts with "live")
sudo tshark -i <interface> -w scans/capture.pcap(Ctrl-C to stop), then analyze that file.- Or capture with a filter:
sudo tshark -i <interface> -f "port 21 or port 80" -w scans/capture.pcap
1. CHEAP overview — always do these first
- Protocol hierarchy (what's even in here):
tshark -r <file> -q -z io,phs - Conversations (who talked to whom, volumes):
tshark -r <file> -q -z conv,ip - Top talkers / endpoints:
tshark -r <file> -q -z endpoints,ip - A quick skim of the first packets:
tshark -r <file> -c 50Read these and form the hypothesis before digging.
2. Credential & data extraction (gate to what the overview suggests)
- Cleartext creds (HTTP/FTP/Telnet/POP/IMAP/SMTP): filter to the protocol and read it, e.g.
tshark -r <file> -Y "http.request.method==POST" -T fields -e http.file_datatshark -r <file> -Y "ftp.request.command==USER || ftp.request.command==PASS" -T fields -e ftp.request.argtshark -r <file> -Y "telnet" -T fields -e telnet.data(creds typed char-by-char — follow the stream)tshark -r <file> -Y "pop.request.parameter || imap || smtp.req.parameter"(mail auth)tshark -r <file> -Y "snmp" -T fields -e snmp.community(SNMP community strings = creds) HTTP Basic-Auth: the Authorization header is base64 — decode it. - Follow a specific TCP/UDP stream once you know which one:
tshark -r <file> -q -z follow,tcp,ascii,<stream-number> - Search everything for a token when you must:
tshark -r <file> -Y 'frame contains "flag"' - DNS queries (exfil / C2 hints):
tshark -r <file> -Y dns -T fields -e dns.qry.name | sort -u - HTTP objects (URLs, user-agents, hosts):
tshark -r <file> -Y http.request -T fields -e http.host -e http.request.uri
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.
- 4d ago First seen · 80 lines · 21 tokens per session scan B 17a1bce4df01
pcap is a command published in the GitHub repository pashki975/thm-claude-kit (2 stars, last pushed 21d ago), licensed MIT. It adds 21 tokens to every session and 1,451 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
send
Send a message to a peer session.
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.
wf-statusline
Set up a lightweight, artifact-only workflow progress statusline.
build
Build it — phase by phase with code review and your approval at each gate.