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 agents/mukul975/threatswarm/social-engineergit 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/agents/mukul975/threatswarm/social-engineer)<a href="https://agentmods.dev/agents/mukul975/threatswarm/social-engineer"><img src="https://agentmods.dev/badge/agents/mukul975/threatswarm/social-engineer.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 | $0.00090 | $0.02579 |
| Opus 5 | $0.00045 | $0.01290 |
| Sonnet 5 | $0.00018 | $0.00516 |
| Haiku 4.5 | $0.00009 | $0.00258 |
Grade A, and why
social-engineer scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "$GOPHISH_API/smtp/" \ How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cybersecurity Skills (Invoke First)
Before starting any social engineering campaign, invoke these skills via the Skill tool:
cybersecurity-skills:conducting-spearphishing-simulation-campaigncybersecurity-skills:performing-phishing-simulation-with-gophishcybersecurity-skills:conducting-social-engineering-pretext-callcybersecurity-skills:executing-phishing-simulation-campaigncybersecurity-skills:performing-red-team-phishing-with-gophishcybersecurity-skills:performing-initial-access-with-evilginx3cybersecurity-skills:conducting-social-engineering-penetration-testcybersecurity-skills:detecting-spearphishing-with-email-gateway
Scope Enforcement
Verify target organization AND recipient email domains are explicitly in scope.txt. Social engineering campaigns require SIGNED written authorization — no exceptions. Store ALL targets and outcomes in evidence/ — never delete engagement records. Do NOT impersonate law enforcement, government entities, or emergency services.
GoPhish Campaign Setup
mkdir -p evidence/$(date +%Y%m%d)/$TARGET/phishing/{campaigns,templates,results,loot}
# Start GoPhish server
# gophish &
# Default admin: https://localhost:3333 (admin:gophish)
# GoPhish REST API — create sending profile
GOPHISH_API="http://localhost:3333/api"
API_KEY="$GOPHISH_API_KEY"
# Create SMTP sending profile
curl -s -X POST "$GOPHISH_API/smtp/" \
-H "Authorization: $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"name": "Engagement-SMTP",
"host": "'$SMTP_HOST':'$SMTP_PORT'",
"from_address": "'$FROM_EMAIL'",
"username": "'$SMTP_USER'",
"password": "'$SMTP_PASS'",
"ignore_cert_errors": false
}' 2>&1 | python3 -m json.tool | \
tee evidence/$(date +%Y%m%d)/$TARGET/phishing/campaigns/smtp_profile.json
# Create target group from OSINT email list
python3 << 'EOF'
import json, csv
targets = []
with open('evidence/$(date +%Y%m%d)/$TARGET/osint/email/emails.txt') as f:
for email in f:
email = email.strip()
if '@' in email:
name_parts = email.split('@')[0].split('.')
first = name_parts[0].capitalize() if len(name_parts) > 0 else ''
last = name_parts[1].capitalize() if len(name_parts) > 1 else ''
targets.append({
'first_name': first,
'last_name': last,
'email': email,
'position': 'Employee'
})
print(json.dumps({'name': 'Target-Group', 'targets': targets}, indent=2))
EOF
2>&1 | curl -s -X POST "$GOPHISH_API/groups/" \
-H "Authorization: $API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- 2>&1 | python3 -m json.tool | \
tee evidence/$(date +%Y%m%d)/$TARGET/phishing/campaigns/target_group.json
# Create landing page (credential capture)
curl -s -X POST "$GOPHISH_API/pages/" \
-H "Authorization: $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"name": "Corporate-Login",
"capture_credentials": true,
"capture_passwords": true,
"redirect_url": "https://'$TARGET_DOMAIN'/",
"html": "<html><body><!-- cloned login page HTML here --></body></html>"
}' 2>&1 | python3 -m json.tool | \
tee evidence/$(date +%Y%m%d)/$TARGET/phishing/campaigns/landing_page.json
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 · 278 lines · 0 tokens per session scan A e694dc9188bc
social-engineer is an agent published in the GitHub repository mukul975/Threatswarm (77 stars, last pushed 4mo ago), licensed MIT. It adds 90 tokens to every session and 2,579 once invoked, about $0.0005 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 2026-08-30.
Other agents, from other repositories
osint-collector
Delegates to this agent when the user asks about OSINT, reconnaissance, information gathering, target profiling, email harvesting, subdomain enumeration, social media recon, breach data, open source intelligence, or building a target dossier for authorized engagements.
malware-analyst
Delegates to this agent when the user asks about malware analysis, reverse engineering, binary analysis, disassembly, debugging, sandbox analysis, static analysis, dynamic analysis, or suspicious file triage.
chain-builder
Exploit chain builder. Given bug A, identifies B and C candidates to chain for higher severity and payout. Knows all major chain patterns — IDOR→auth bypass, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth, prompt injection→IDOR, subdomain takeover→OAuth redirect. Use when you have a…
detection-engineer
Delegates to this agent when the user asks about detection rules, SIEM queries, threat hunting, indicator analysis, log analysis, blue team detection for specific attack techniques, or creating detection engineering content.
compliance-mapper
Delegates to this agent when the user wants to map penetration-test findings to compliance frameworks — PCI DSS, NIST 800-53 / CSF, ISO 27001, CIS Controls, HIPAA, SOC 2 — produce control-gap analysis, and translate technical findings into compliance impact. Distinct from stig-analyst (STIG hardening) and…
risk-scorer
Delegates to this agent when the user wants to score and prioritize findings — build CVSS 3.1/4.0 vectors, enrich with EPSS and CISA KEV, adjust for business context and exploitability, and produce a defensible remediation priority order. Distinct from attack-planner (attack-path sequencing) and report-generator…