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/web-recongit 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/web-recon)<a href="https://agentmods.dev/commands/pashki975/thm-claude-kit/web-recon"><img src="https://agentmods.dev/badge/commands/pashki975/thm-claude-kit/web-recon.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 | $0.00016 | $0.00415 |
| Opus 5 | $0.00008 | $0.00208 |
| Sonnet 5 | $0.00003 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
web-recon scanned grade A 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Find the default response size first (curl the IP) and filter with -fs/-fw. Repeat on https. What it actually says
Recon the DNS/vhost surface of: $ARGUMENTS (a domain, or the target IP with a known domain)
The DNS-side complement to /enum-web. Use when the room gives you a domain name, hints at subdomains, or is about subdomain takeover. Goal is usually a hidden host — often the flag lives there, no shell needed.
1. Resolve
- Ensure the domain is in /etc/hosts pointing at the target IP (add with my approval).
2. Virtual-host fuzzing
- ffuf -w /usr/share/seclists/Discovery/DNS/subdomains-top1million-5000.txt
-u http:// -H "Host: FUZZ." -fs - Find the default response size first (curl the IP) and filter with -fs/-fw. Repeat on https.
3. Certificate inspection (subdomains leak in SAN fields)
- openssl s_client -connect :443 </dev/null 2>/dev/null | openssl x509 -noout -text
| grep -A1 "Subject Alternative Name" - Or sslscan . The classic Takeover-style insight.
4. DNS enumeration
- Zone transfer: dig axfr @
- dnsrecon -d -n
5. Subdomain takeover check
- A subdomain whose CNAME points to an unclaimed cloud resource (S3/Azure/GitHub Pages/Heroku) — tell is a NoSuchBucket/404 fingerprint. Flag is often in the redirect URL.
6. Summarize
List every subdomain found and how. Add each to /etc/hosts, note which to investigate, record in notes.md. If the goal was a flag and you found it, stop.
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.
- 6d ago First seen · 35 lines · 16 tokens per session scan A 55d4db034fd8
web-recon is a command published in the GitHub repository pashki975/thm-claude-kit (2 stars, last pushed 23d ago), licensed MIT. It adds 16 tokens to every session and 415 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.