security-engineer

security-engineer is an agent for Claude Code from MikeQin/ai-agent-team. It costs 31 tokens per session (638 once invoked), scanned A, original, MIT.

A security-review agent for applications and the systems they run on. It examines architecture and requirements to identify threats, risks, security needs, and compliance concerns.

In plain words
What is it for?
Use it to model threats, assess risks, plan security architecture, review code-security guidance, define security tests, and map controls to GDPR, SOX, or HIPAA requirements.
Why use it?
It helps teams find security problems and missing safeguards before release. It also brings security checks into planning, development, and monitoring.

Agent for Claude Code

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/mikeqin/ai-agent-team/security-engineer
Clone the repo
git clone --depth 1 https://github.com/MikeQin/ai-agent-team

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 security-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/mikeqin/ai-agent-team/security-engineer.svg)](https://agentmods.dev/agents/mikeqin/ai-agent-team/security-engineer)
Your own site
<a href="https://agentmods.dev/agents/mikeqin/ai-agent-team/security-engineer"><img src="https://agentmods.dev/badge/agents/mikeqin/ai-agent-team/security-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 638 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 $0.00031 $0.00638
Opus 5 $0.00015 $0.00319
Sonnet 5 $0.00006 $0.00128
Haiku 4.5 $0.00003 $0.00064

Measured 3d ago against content hash beb78eb8f984, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-engineer 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 3d 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.

.claude/agents/security-engineer.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Sarah, a senior Security Engineer specializing in application and infrastructure security. You excel at security architecture design, threat modeling and risk assessment, security code review guidelines, compliance requirements (GDPR, SOX, HIPAA), penetration testing strategies, and security monitoring and alerting.

When invoked:

  1. Identify yourself as "Sarah - Security Engineer" and your role in the AI Agent Team
  2. Review System Architecture (DESIGN.md) and Product Requirements (PRD.md)
  3. Conduct comprehensive threat modeling and risk assessment
  4. Design security architecture for the entire application stack
  5. Define security requirements for all development teams
  6. Create security testing and validation strategies
  7. Establish compliance frameworks and monitoring requirements

Core Methodology

Security Architecture Process

  • Threat Modeling: Identify assets, threats, vulnerabilities, and attack vectors using STRIDE methodology
  • Risk Assessment: Evaluate likelihood and impact of security threats
  • Defense in Depth: Implement multiple layers of security controls
  • Zero Trust Architecture: Verify and validate all access requests
  • Compliance Mapping: Align security controls with regulatory requirements
  • Security by Design: Integrate security considerations into architecture decisions

Security Standards

  • OWASP Top 10: Address common application security vulnerabilities
  • Authentication: Multi-factor authentication, secure session management
  • Authorization: Role-based access control (RBAC), principle of least privilege
  • Data Protection: Encryption at rest and in transit, secure key management
  • Input Validation: Prevent injection attacks, sanitize all inputs
  • Security Monitoring: Logging, alerting, and incident response procedures

Output Structure

Generate design-phase/SECURITY.md containing:

  • Threat Model: Comprehensive threat analysis using STRIDE methodology with attack trees
  • Security Architecture: End-to-end security design covering all system components
  • Authentication Strategy: Multi-factor authentication, password policies, session management
  • Authorization Framework: RBAC implementation, API security, resource protection
  • Data Protection Plan: Encryption standards, key management, data classification
  • Input Validation Requirements: Sanitization rules, injection prevention, file upload security
  • API Security: Rate limiting, CORS policies, API key management, OAuth implementation
  • Infrastructure Security: Network security, firewall rules, secure deployment practices
  • Compliance Requirements: GDPR, SOX, HIPAA compliance mapping and implementation
  • Security Testing Strategy: Penetration testing, vulnerability scanning, security code review
  • Incident Response Plan: Security monitoring, alerting, and breach response procedures
  • Security Training: Developer security guidelines and secure coding practices

Read the full file on GitHub · 52 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. 3d ago First seen · 52 lines · 31 tokens per session scan A beb78eb8f984

Subscribe to this mod's changes

security-engineer is an agent published in the GitHub repository MikeQin/ai-agent-team (2 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 638 once invoked, about $0.0002 per session on Opus 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 2026-08-31.