mjtpena

Feos Security — Security agent for Claude Code

Security community

FEOS security reviewer (read-only).

How to install Feos Security

Installs to ~/.claude/agents/mjtpena-frontier-engineering-os-feos-security.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/mjtpena/frontier-engineering-os/HEAD/.claude/agents/feos-security.md -o ~/.claude/agents/mjtpena-frontier-engineering-os-feos-security.md

Restart Claude Code, or start a new session, for it to be picked up.

What Feos Security does

name: feos-security description: "FEOS security reviewer (read-only). Use in S3 to produce the STRIDE threat model and in S6/G4 to review code, IaC, dependencies, secrets and AI attack surface (prompt injection, tool abuse). Returns findings; never edits code." tools: Read, Grep, Glob, Bash model: opus

FEOS Security (stage S3,S6)

**Mission:** Find what an attacker would find first, rate it honestly, and propose concrete mitigations.

Scope

  • Reads: architecture/, src/, `in

Alternatives in Security

  • Stride Analysis Patterns — Systematic threat identification using the STRIDE methodology 31.9k ★
  • GraphQL Audit — GraphQL API security specialist 812 ★
  • Dr Audit — Sub-agent prompt: audit Decision Records in an implementation-plan.md for canonical form and reference resolut 432 ★

Full documentation available on GitHub

View Source Repository

Related Agents

Lens AI Security — Security agent for Claude Code

Lens AI Security

AI security lens of the production readiness audit. Treats LLM and agent integrations as attack surface - prom

Security community
LLM Sec Review — Security agent for Claude Code

LLM Sec Review

LLM/agent security review specialist — prompt injection, the Agents Rule of Two, tool-call authorization, mode

Security community
Psychodrama Security — Security agent for Claude Code

Psychodrama Security

Use ONLY by psychodrama-protocol skill orchestrator. Evaluates theses through threat model / attack surface /

Security community
Vuln Recon — Security agent for Claude Code

Vuln Recon

Maps a target repository's attack surface, writes a threat model, plans hunt work units, and optionally writes

Security community
Testing Red Team — Security agent for Claude Code

Testing Red Team

💀 Use this agent for authorized application-layer offensive security testing - OWASP Top 10, authentication/a

Security community
Security Testing — Security agent for Claude Code

Security Testing

Security Testing Agent (SSDF PW.8). Read-only w.r.t. product code. Derives tests from requirements + threat mo

Security community

Related Skills

Skill Threat Modeling — Security skill for Claude Code

Skill Threat Modeling

Code-First Deep Risk Analysis Skill for Claude Code - 8-Phase Workflow with Security design review, STRIDE Thr

Security community
Review AI Agent Surface — Security skill for Claude Code

Review AI Agent Surface

Audit the AI and agent attack surface: prompt injection, tool-permission scope, unbounded agent loops, and uns

Security community
/recon — Data skill for Claude Code

/recon

Run the full recon pipeline on a target and produce a prioritized attack surface.

Data community