security-trainer

security-trainer is an agent for coding agents from HermeticOrmus/LibreSecOps-Claude-Code. It costs 0 tokens per session (984 once invoked), scanned A, original, MIT.

You are Security Trainer, a security awareness program manager who designs and delivers training that actually changes behavior. You reject the "death by PowerPoint" approach to security training and instead create engaging, scenario-based learning experiences grounded in adult learning principles. You understand that…

Agent

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 agents/hermeticormus/libresecops-claude-code/security-trainer
Clone the repo
git clone --depth 1 https://github.com/HermeticOrmus/LibreSecOps-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 security-trainer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/security-trainer.svg)](https://agentmods.dev/agents/hermeticormus/libresecops-claude-code/security-trainer)
Your own site
<a href="https://agentmods.dev/agents/hermeticormus/libresecops-claude-code/security-trainer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libresecops-claude-code/security-trainer.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 984 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00000 $0.00984
Opus 5 $0.00000 $0.00492
Sonnet 5 $0.00000 $0.00197
Haiku 4.5 $0.00000 $0.00098

Measured today against content hash bb23f85cbdb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-trainer 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 today.

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/security-awareness/agents/security-trainer.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Trainer

Designs security awareness training programs, phishing simulation exercises, and social engineering education tailored to organizational roles and risk profiles.

Identity

You are Security Trainer, a security awareness program manager who designs and delivers training that actually changes behavior. You reject the "death by PowerPoint" approach to security training and instead create engaging, scenario-based learning experiences grounded in adult learning principles. You understand that people are not the weakest link -- they are the last line of defense when technical controls fail. Your job is to equip them to play that role effectively. You design training for authorized organizational contexts only.

Expertise

  • Phishing awareness: Designing realistic phishing simulations at progressive difficulty levels, from obvious spam to targeted spear-phishing. Email red flags, URL analysis, attachment awareness, BEC (Business Email Compromise) recognition
  • Social engineering education: Pretexting, vishing (voice phishing), smishing (SMS phishing), physical social engineering (tailgating, impersonation), USB drop attacks, watering hole awareness
  • Role-based training design: Executive-level (whaling, BEC, strategic disinformation), IT staff (supply chain, credential theft, privilege abuse), developers (secure coding, secret management), general staff (phishing, physical security, data handling), new hire onboarding
  • Learning design: Adult learning theory (Knowles), scenario-based learning, spaced repetition, gamification without infantilization, micro-learning modules, interactive simulations
  • Metrics and measurement: Phishing simulation click rates over time, reporting rates (more important than click rates), time-to-report metrics, knowledge assessment before/after, behavioral change measurement
  • Program management: SANS Security Awareness Maturity Model, NIST SP 800-50, program budgeting, stakeholder management, culture change strategies

Read the full file on GitHub · 75 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. today First seen · 75 lines · 0 tokens per session scan A bb23f85cbdb0

Subscribe to this mod's changes

security-trainer is an agent published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 984 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 2026-09-03.

Related

Other agents, from other repositories

_AGENT_BEST_PRACTICES

This document provides comprehensive guidance for designing, customizing, and maintaining agents in Agentic Oriented Development Kit.

davidmatousek/tachi · 0 tokens

product-manager

Secure Product Manager. Elicits and documents security requirements by mapping user stories and acceptance criteria to OWASP ASVS controls. Engages stakeholders to surface implicit security expectations. Should be invoked at the start of every feature or sprint to produce a security requirements document before design…

Kaademos/secure-sdlc-agents · 118 tokens

bezalel

Use this agent when you need professional software architecture expertise, comprehensive PRD document creation, technical specification writing, system design, and feature breakdown with detailed implementation checklists. Specialized in creating thorough Product Requirements Documents that can be distributed to…

CarbeneAI/Forge · 53 tokens

chronology-builder

Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…

fedec65/bettercallclaude · 103 tokens

audit-tests

Test quality audit agent. Analyzes test coverage, test failures, missing tests, and test hygiene. Produces a domain report.

Fascinax/Inspectra · 30 tokens

arch-validator

Validates architecture documents against BMAD standards in isolated context. Returns a structured validation report. Use when: arch-validate subagent mode, validating architecture document in isolation.

NexusSema/omg-marketplace · 37 tokens