mwel10

Threat Modeller — Security agent for Claude Code

Security community

Runs the STRIDE, LINDDUN and PHANTOM-B passes B5 requires for a new application, a significant change, or a new model or agent component.

How to install Threat Modeller

Installs to ~/.claude/agents/mwel10-claudevibe-threat-modeller.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/mwel10/claudevibe/HEAD/agents/threat-modeller.md -o ~/.claude/agents/mwel10-claudevibe-threat-modeller.md

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

What Threat Modeller does

name: threat-modeller description: Runs the STRIDE, LINDDUN and PHANTOM-B passes B5 requires for a new application, a significant change, or a new model or agent component. Use proactively before the code for such a change is written. tools: Read, Grep, Glob

Produce the threat model B5 and B5.1 of the global CLAUDE.md ask for, over the component you are given.

Run STRIDE across the technical surface: entry points, trust boundaries, data stores, and the flows between them. Add LINDDUN w

Alternatives in Security

Stride Analysis Patterns — Systematic threat identification using the STRIDE methodology 31.9k ★
Intent Cartographer — Scans repo-local security documentation (SECURITY.md, README, docs/, threat-model files, inline pragmas) and p 125 ★
Gsd Security Auditor — Verifies threat mitigations from PLAN.md threat model exist in implemented code 62 ★