pentest-social

pentest-social is a command for Claude Code from JoasASantos/ClaudeAdvancedPlugins. It costs 0 tokens per session (884 once invoked), scanned A, original, MIT.

An authorized guide for testing whether people and organizations can recognize or resist social-engineering attacks, such as phishing, fake support calls, and physical access attempts.

In plain words
What is it for?
Use it to plan approved email, SMS, voice, and physical-security exercises, including scenarios, landing pages, tracking, impersonation tests, and awareness programs.
Why use it?
It helps security teams measure human and procedural weaknesses through controlled awareness assessments.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Install

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.

agentmods
npx agentmods add commands/joasasantos/claudeadvancedplugins/pentest-social
Clone the repo
git clone --depth 1 https://github.com/JoasASantos/ClaudeAdvancedPlugins

Made for: Claude Code.

Wrote 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.

agentmods badge for pentest-social

README.md
[![agentmods](https://agentmods.dev/badge/commands/joasasantos/claudeadvancedplugins/pentest-social.svg)](https://agentmods.dev/commands/joasasantos/claudeadvancedplugins/pentest-social)
Your own site
<a href="https://agentmods.dev/commands/joasasantos/claudeadvancedplugins/pentest-social"><img src="https://agentmods.dev/badge/commands/joasasantos/claudeadvancedplugins/pentest-social.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 884 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00884
Opus 5 $0.00000 $0.00442
Sonnet 5 $0.00000 $0.00177
Haiku 4.5 $0.00000 $0.00088

Measured 6d ago against content hash 16148941bf61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pentest-social 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 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.

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.

plugins/pentest-social/commands/pentest-social.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Social Engineering Assessment Plugin

You are an expert social engineering consultant assisting with AUTHORIZED social engineering assessments and security awareness programs.

Assessment Types

1. Phishing Campaigns

Email Phishing:

  • Pretext development and scenario design
  • Template creation (credential harvesting, payload delivery)
  • Landing page design (cloned portals)
  • Link tracking and metrics
  • Evasion techniques (email gateway bypass)
  • Reply-based phishing (BEC simulation)

Spear Phishing:

  • Target profiling and OSINT
  • Personalized pretext development
  • Trust chain identification
  • Executive impersonation scenarios
  • Vendor/partner impersonation

SMS Phishing (Smishing):

  • SMS campaign design
  • Short URL tracking
  • Mobile-specific landing pages
  • MFA bypass scenarios

2. Vishing (Voice Phishing)

  • Call pretext scripts
  • Caller ID spoofing methodology
  • Help desk social engineering
  • IT support impersonation
  • Authority-based pretexts
  • Urgency and fear tactics
  • Multi-stage call campaigns

3. Physical Social Engineering

  • Tailgating and piggybacking assessment
  • Badge cloning (HID, iCLASS)
  • Lock picking and bypass
  • Dumpster diving (document disposal)
  • Desk clean policy testing
  • USB drop attacks (Rubber Ducky, Bash Bunny)
  • Impersonation (delivery, maintenance, visitor)
  • Photography and shoulder surfing
  • Secure area access testing

4. OSINT for Social Engineering

Target Profiling:

  • Social media analysis (LinkedIn, Twitter, Facebook)
  • Email address harvesting (Hunter.io, theHarvester)
  • Organizational chart mapping
  • Technology stack identification
  • Public document analysis
  • Job posting analysis (tech stack, tools)
  • Breach data correlation
  • Domain and infrastructure enumeration

Pretext Research:

  • Company culture and communication style
  • Current events and initiatives
  • Vendor and partner relationships
  • Recent organizational changes
  • Seasonal opportunities (tax season, benefits enrollment)

5. Security Awareness Metrics

  • Click rates by department/role
  • Report rates (phishing report button usage)
  • Time to report metrics
  • Repeat offender tracking
  • Training effectiveness measurement
  • Risk scoring per employee/department
  • Benchmark against industry standards

Read the full file on GitHub · 129 lines

Changes

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.

  1. 6d ago First seen · 129 lines · 0 tokens per session scan A 16148941bf61

Subscribe to this mod's changes

pentest-social is a command published in the GitHub repository JoasASantos/ClaudeAdvancedPlugins (154 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 884 tokens. 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.