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/enum-webgit clone --depth 1 https://github.com/pashki975/thm-claude-kitWhat 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 | $0.00017 | $0.00691 |
| Opus 5 | $0.00009 | $0.00345 |
| Sonnet 5 | $0.00003 | $0.00138 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
enum-web 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 2d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enumerate the web service at: $ARGUMENTS (e.g. http://10.10.x.x:80)
The gate (apply this before the heavy steps — it's the whole point)
Enumeration steps split into CHEAP (always worth it) and HEAVY (only when they'll actually tell us something new). Before running any HEAVY step, stop and reason out loud:
- What do we already know from the cheap steps? (page source, JS bundles, whatweb fingerprint)
- Would this heavy scan find anything the cheap steps didn't already hand us?
- If the app is bespoke/single-page (all logic in one JS file, no CMS, no server-rendered dirs), a directory brute-force and a nikto sweep are usually LOW YIELD — the source already reveals the real endpoints. Say so, and suggest the better move instead (read the JS, hit the API endpoints the source names, test those params). State the one-line hypothesis for a heavy step before running it. If the hypothesis is "this probably finds nothing new," skip it and explain why, then offer it as opt-in ("say the word and I'll run the full ffuf/nikto anyway").
CHEAP — always do these first
- Fetch the page and READ THE SOURCE — HTML comments, linked JS bundles, inline config, API paths referenced in the code. On a custom app this often hands you every real endpoint.
whatweb $ARGUMENTS— fingerprint the tech stack (is this a known CMS or a bespoke app?)- If it fingerprints WordPress (wp-content/, wp-login.php,
<meta name="generator" content="WordPress ...">), STOP the generic path and route to/wp $ARGUMENTS— WordPress has its own tool (wpscan) and attack chain; the generic ffuf/nikto sweep is the wrong axis. Note it in notes.md and hand off.
- If it fingerprints WordPress (wp-content/, wp-login.php,
- Check the obvious files: robots.txt, sitemap.xml, /.git/, backups, /api/ paths named in source.
HEAVY — gate each behind the hypothesis above
- Directory/content brute-force — ONLY if the cheap steps left real gaps (server-rendered app,
unknown framework, dirs likely hidden). First verify the wordlist exists:
ls /usr/share/seclists/Discovery/Web-Content/— do NOT guess a filename (CLAUDE.md rule).ffuf -u $ARGUMENTS/FUZZ -w <verified-wordlist> -mc 200,204,301,302,307,401,403 -o scans/ffuf.json nikto -h $ARGUMENTS -o scans/nikto.txt— ONLY if it's a real server-side app where known misconfigs/CVEs are plausible. Skip for a static single-page app.
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.
- 2d ago First seen · 42 lines · 17 tokens per session scan A 60c5324d68e8
enum-web is a command published in the GitHub repository pashki975/thm-claude-kit (2 stars, last pushed 19d ago), licensed MIT. It adds 17 tokens to every session and 691 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other commands, from other repositories
peers
List bridger peers — who is addressable, where, and what they're doing.
ask
Ask a peer session a question and wait for its answer.
monitor
Open the read-only web view of peers, threads and bus health.
register
Register this project directory as a named bridger peer.
send
Send a message to a peer session.
status
Show bridger identity, peers, and unread message counts.