# Threat Model Generator

A set of [agent skills](https://agentskills.io/) for producing threat models for open-source projects, including an orchestrator and independently invocable specialists.

The output is a document describing the implicit security contract between a project and its downstream users: what the project assumes about its environment and inputs, which security properties it claims, which it explicitly disclaims, and which threats are left to the integrator. It is written to serve two readers at once: the downstream integrator deciding what they are now responsible for, and the maintainer or triager deciding whether an inbound vulnerability report is valid, out of model, or by design.

This is not a vulnerability scanner or audit tool. It produces a contract, not findings.

New to security threat modeling? The [glossary](./skills/threat-model/references/glossary.md) defines the jargon — dispositions, sinks, disclaimed properties, provenance tags — in plain language for maintainers coming at this fresh.

## Install

### Claude Code

``` /plugin marketplace add alpha-omega-security/threat-model /plugin install threat-model@threat-model ```

### Other agents

Any [agentskills.io-compatible](https://agentskills.io/clients) agent can load these skills directly from `skills/`. Clone the repo and point your agent's skill path at that directory, or copy its contents into your project's `.claude/skills/` (or equivalent). Keep the skill folders as siblings — the specialists share the references under `threat-model/references/` via relative paths.

## Usage

Point the agent at a project checkout and invoke the skill:

``` /threat-model:threat-model ```

or ask naturally:

``` Produce a threat model for this project. Is this vulnerability report in scope for our threat model? Draft a SECURITY.md scope section. ```

The skill runs draft-first by default: it orients on the codebase and existing docs, writes a provisional model with every claim tagged documented