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/mukul975/ThreatswarmWrote 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/mukul975/threatswarm/pwned)<a href="https://agentmods.dev/commands/mukul975/threatswarm/pwned"><img src="https://agentmods.dev/badge/commands/mukul975/threatswarm/pwned/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/mukul975/threatswarm/pwned"><img src="https://agentmods.dev/badge/commands/mukul975/threatswarm/pwned.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 | $0.00018 | $0.00729 |
| Opus 5 | $0.00009 | $0.00365 |
| Sonnet 5 | $0.00004 | $0.00146 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade C, and why
pwned scanned grade C 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 9d 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- Linux: read /etc/shadow if root, find config files with credentials What it actually says
Run full post-exploitation workflow on: $ARGUMENTS
Parse $ARGUMENTS: first word is TARGET, second word (optional) is SESSION_ID or access level (user/www-data/root/SYSTEM).
-
Scope Check: Verify TARGET is in scope.txt. Stop if not found.
-
Document Current Access:
═══════════════════════════════════════════ POST-EXPLOITATION START Target: TARGET Session ID: SESSION_ID (if provided) Timestamp: $(date -u +%Y-%m-%dT%H:%M:%SZ) ═══════════════════════════════════════════ -
Invoke
post-exAgent for automated privilege escalation:- Detect OS type (Linux vs Windows)
- Run LinPEAS/WinPEAS automated enumeration
- Check SUID binaries, cron, sudo, capabilities (Linux)
- Check SeImpersonatePrivilege, unquoted paths, AlwaysInstallElevated (Windows)
- Document escalation path with ATT&CK TTPs
- Target evidence dir:
evidence/$(date +%Y%m%d)/TARGET/post_ex/
-
Credential Harvesting: After any privilege escalation:
- Linux: read /etc/shadow if root, find config files with credentials
- Windows: invoke
impacket-secretsdumplocally, or mimikatz via Meterpreter - Pass any discovered hashes to
password-attacksagent for cracking - Store: location reference only (NOT plaintext passwords)
-
Domain Check: If target appears domain-joined:
- Check for domain membership:
realm list(Linux) orsysteminfo | findstr /i domain(Windows) - If domain-joined: invoke
active-directoryagent for full domain compromise path - Run BloodHound collection from compromised host
- Check for domain membership:
-
Lateral Movement Mapping:
# SMB sweep for reachable hosts (from compromised machine) crackmapexec smb $INTERNAL_SUBNET/24 \ -u $COMPROMISED_USER -H $NTLM_HASH \ --continue-on-success 2>&1 | \ tee evidence/$(date +%Y%m%d)/$TARGET/lateral/smb_sweep.txt -
Update Findings: Append to
evidence/$(date +%Y%m%d)/TARGET/findings.md:## Post-Exploitation — $(date -u +%Y-%m-%dT%H:%M:%SZ) | Step | Method | ATT&CK | Result | |------|--------|--------|--------| | Privesc | [technique] | [TTP] | [user → root/SYSTEM] | | Lateral | [technique] | T1021 | [hosts reached] | -
Print Summary:
═══ POST-EX RESULTS ════════════════ Privilege Level: [user → root/SYSTEM] Hosts Reached: X Credentials: X hashes (see evidence/) Domain Admin: [YES/NO] ════════════════════════════════════
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.
- 9d ago First seen · 69 lines · 18 tokens per session scan C 82be592deb65
pwned is a command published in the GitHub repository mukul975/Threatswarm (78 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 729 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
recon
Run full recon pipeline on a target — subdomain enum (Chaos API + subfinder), live host discovery (dnsx + httpx), URL crawl (katana + waybackurls + gau), gf pattern classification, nuclei scan. Outputs to recon/ / directory. Usage: /recon target.com.
autopilot
Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo].
hunt
Active vulnerability hunting. Two-track dispatcher — asks Red Team vs WAPT, hands off to hunt-dispatch skill and sibling commands. Usage: /hunt target.com | /hunt .target.com | /hunt targets.txt [--vuln-class X] [--source-code P] [--chrome].
token-scan
Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP lock bypass, authority retention, bonding curve exploits, fake renounce, sandwich amplification). Manual 8-class grep audit (with an optional automated scanner if present). Usage: /token-scan [--chain solana].
triage
Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage.
validate
Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate.