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/ogrodev/fsociety/wpscangit clone --depth 1 https://github.com/ogrodev/fsocietyWhat 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 | $0.00007 | $0.00526 |
| Opus 5 | $0.00003 | $0.00263 |
| Sonnet 5 | $0.00001 | $0.00105 |
| Haiku 4.5 | $0.00001 | $0.00053 |
Grade A, and why
wpscan 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storage Policy: ALL output files MUST be saved in the project directory. NEVER write to
/tmp/or any system temporary directory.
WordPress Security Scan
Target: $ARGUMENTS
Execute WordPress-specific scanning using Hexstrike MCP tools.
Step 1: Load Tools
Use ToolSearch to load:
wpscan_analyze— comprehensive WordPress vulnerability scanningnuclei_scan— template-based scanning with WP-specific templateskatana_crawl— crawl for custom theme/plugin endpoints
Step 2: WPScan Enumeration
Run wpscan_analyze against the target to:
- Detect WordPress version
- Enumerate plugins (aggressive mode if stealth is not required)
- Enumerate themes
- Enumerate users (author ID brute force)
- Check for known vulnerabilities in detected components
- Identify interesting files (readme.html, license.txt, wp-config.php.bak)
Step 3: Nuclei WP Templates
Run nuclei_scan with WordPress-specific template tags:
wordpress,wp-plugin,wp-theme- Severity: critical, high, medium
- This catches vulnerabilities that WPScan's database might miss
Step 4: Custom Endpoint Discovery
Run katana_crawl to discover:
- Custom PHP endpoints in theme directories (
/wp-content/themes/*/) - Custom plugin endpoints
- AJAX handlers (
/wp-admin/admin-ajax.phpactions) - REST API custom routes (
/wp-json/) - Hidden admin tools or utilities
Step 5: Manual Checks
Verify these common WordPress attack vectors:
- XML-RPC enabled? (
/xmlrpc.php— can be used for brute force, SSRF, DoS) - User enumeration via
/?author=1,/?author=2, etc. - Login page accessible? (
/wp-login.php) - WP-Cron accessible? (
/wp-cron.php) - Debug mode enabled? (error messages in responses)
- Directory listing in
/wp-content/uploads/
Step 6: Results
Save findings to wpscan-{target}.md in the project directory, organized by:
- WordPress version and update status
- Vulnerable plugins/themes with CVEs
- Enumerated users
- Accessible sensitive endpoints
- Custom theme/plugin findings
- Recommended exploitation paths
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 · 61 lines · 7 tokens per session scan A 004a0c902836
wpscan is a command published in the GitHub repository ogrodev/fsociety (20 stars, last pushed 5mo ago), licensed MIT. It adds 7 tokens to every session and 526 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
review
Review code changes for Shannon-specific patterns, security, and common mistakes.
debug
Systematically debug errors using context analysis and structured recovery.
engage.c2
Execute Phase 6 - Command and Control Infrastructure Setup.
engage.install
Execute Phase 5 - Installation and Persistence Establishment.
engage.weaponize
Execute Phase 2 - Weaponization and Payload Development.
engage.deliver
Execute Phase 3 - Delivery and Payload Deployment.