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/attack)<a href="https://agentmods.dev/commands/mukul975/threatswarm/attack"><img src="https://agentmods.dev/badge/commands/mukul975/threatswarm/attack/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/attack"><img src="https://agentmods.dev/badge/commands/mukul975/threatswarm/attack.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 | $0.00022 | $0.00893 |
| Opus 5.5 | $0.00009 | $0.00357 |
| Sonnet 5.5 | $0.00004 | $0.00179 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
attack 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.
What it actually says
Execute an attack against target using the specified vector: $ARGUMENTS
Parse $ARGUMENTS: the first word is TARGET, remaining words are the VECTOR.
-
Scope Check: Verify TARGET is in scope.txt. Stop if not found.
-
Route to Agent based on VECTOR keyword:
Vector Keyword Agent to Invoke web,http,webapp,sqli,xss,ssrf,lfi,jwtweb-attackerapi,rest,graphql,grpc,bola,idor,swaggerapi-attackerad,active-directory,kerberoast,asrep,dcsync,bloodhoundactive-directorynetwork,arp,mitm,snmp,smbrelay,respondernetwork-opswireless,wifi,wpa,wps,eap,pmkidwireless-attackercloud,aws,azure,gcp,s3,iam,metadatacloud-attackercontainer,docker,kubernetes,k8s,pod,kubeletcontainer-attackerexploit,cve-,rce,shell,metasploit,msfconsoleexploitmobile,android,ios,apk,frida,adbmobile-attackerosint,passive,recon,crt.sh,shodan,theHarvesterosintreverse,binary,re,ghidra,r2,gdb,ropreverse-engineermalware,sample,yara,ioc,sandboxmalware-analystpassword,hash,crack,hashcat,johnpassword-attacksphishing,social,gophish,evilginx,vishingsocial-engineercrypto,tls,ssl,jwt-crack,paddingcrypto-attackeriot,firmware,uart,mqtt,binwalkiot-attackerc2,sliver,havoc,meterpreter,beacon,implantc2-operatorevasion,amsi,av-bypass,obfuscateevasion -
Invoke Selected Agent: Delegate to the matched agent with:
- Target:
TARGET - Vector:
VECTOR - Evidence dir:
evidence/$(date +%Y%m%d)/TARGET/ - Context from
evidence/$(date +%Y%m%d)/TARGET/recon_summary.mdif it exists
- Target:
-
Log Attack: After agent completes, append to
evidence/$(date +%Y%m%d)/TARGET/attack_log.md:| $(date -u +%Y-%m-%dT%H:%M:%SZ) | VECTOR | [agent used] | [outcome summary] | -
Output Summary: Print findings discovered with severity if available.
If VECTOR does not match any keyword, output:
Unknown attack vector. Available vectors: web, api, ad, network, wireless, cloud, container, exploit, mobile, osint, reverse, malware, password, phishing, crypto, iot, c2, evasion
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 · 52 lines · 0 tokens per session scan A 7c0306d5e0a9
attack is a command published in the GitHub repository mukul975/Threatswarm (91 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 893 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 2026-08-30.
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.
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].
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].
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.