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/wp)<a href="https://agentmods.dev/commands/pashki975/thm-claude-kit/wp"><img src="https://agentmods.dev/badge/commands/pashki975/thm-claude-kit/wp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/pashki975/thm-claude-kit/wp"><img src="https://agentmods.dev/badge/commands/pashki975/thm-claude-kit/wp.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00019 | $0.00757 |
| Opus 5.5 | $0.00008 | $0.00303 |
| Sonnet 5.5 | $0.00004 | $0.00151 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
wp 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 1mo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attack the WordPress site at: $ARGUMENTS (e.g. http://10.10.x.x or http://blog.thm)
WordPress has its own tool (wpscan) and a distinct attack chain, so this is separate from the generic /enum-web path. Same gating discipline: enumerate cheaply, form a hypothesis about the way in (vulnerable plugin? weak creds? exposed config?), THEN run the heavy/noisy steps.
The gate
Before brute-forcing logins or firing an exploit, say a one-line hypothesis from what enum found:
- A specific vulnerable plugin/theme version → that CVE is the way in (don't brute logins).
- A discovered username + a login form → password attack is justified (mind lockout).
- xmlrpc.php enabled → amplified brute or pingback SSRF may fit.
State it, then run only the step that matches. Get a wpscan API token (free) for CVE data:
add
--api-token <token>to enrich plugin/theme vuln output.
1. CHEAP enumeration — always
- Passive + light:
wpscan --url $ARGUMENTS --enumerate vp,vt,u --plugins-detection passive(vp=vuln plugins, vt=vuln themes, u=users) - Read the site: /wp-login.php (version, custom login), /?author=1 (username leak), /readme.html, /wp-content/ listing, robots.txt. Note the WP core version.
- Check xmlrpc.php: is it enabled? (POST to it — 405 vs 200 tells you).
2. Map versions to known vulns (gate the exploit)
- Note core, plugin, and theme versions from enum. For anything flagged, verify the CVE actually
applies to THIS version before chasing it.
searchsploit wordpress <plugin>for local PoCs. - Common wins: outdated plugin with auth-bypass/RCE/LFI/SQLi; a theme with file-upload.
3. Credential attack — only if enum gave a username and no easier path
wpscan --url $ARGUMENTS -U users.txt -P /usr/share/wordlists/rockyou.txt(wpscan brute uses wp-login by default; add--password-attack xmlrpcif xmlrpc is enabled — faster).- Watch for lockout plugins; if present, prefer the CVE path over brute.
4. Authenticated → shell (once you have wp-admin)
- Appearance → Theme Editor: edit 404.php/header.php of an inactive theme to a PHP webshell, then browse to it. (Or Plugins → upload a malicious plugin zip.)
- Set up the catch with /listener first, then trigger the shell.
- Metasploit alt:
wp_admin_shell_uploadif you prefer.
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.
- 1mo ago First seen · 50 lines · 19 tokens per session scan A 1a4424b5a4e0
wp is a command published in the GitHub repository pashki975/thm-claude-kit (2 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 757 once invoked, about $0.0001 per session on Opus 5.5. 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
dewey-classify
Classify a file using the DeweyGraph modular skill toolkit.
dewey-graph
Show the DeweyGraph link graph and heat maps for the current archive.
dewey-scan
Scan a folder with the DeweyGraph modular classifier and synthesise cross-links.
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.