threat-model

threat-model is a command for coding agents from MilindGaharwar/fettle. It costs 20 tokens per session (243 once invoked), scanned A, a copy of fettle-threat-model, Apache-2.0.

A command that creates a STRIDE threat model for a service. STRIDE is a security checklist covering threats such as impersonation, data tampering, information leaks, and denial of service.

In plain words
What is it for?
Use it to generate a threat-model document, inspect automatically detected components, add missing details, and complete the risk tables with human judgment.
Why use it?
It provides a starting inventory of service entry points, stored data, and authentication so security risks can be reviewed systematically.

Command

Part of the fettle plugin — 34 commands, 4 hooks shipped together

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 commands/milindgaharwar/fettle/threat-model
Clone the repo
git clone --depth 1 https://github.com/MilindGaharwar/fettle

Or install fettle, the plugin that ships this one along with the rest of its 34 commands, 4 hooks.

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 threat-model

README.md
[![agentmods](https://agentmods.dev/badge/commands/milindgaharwar/fettle/threat-model.svg)](https://agentmods.dev/commands/milindgaharwar/fettle/threat-model)
Your own site
<a href="https://agentmods.dev/commands/milindgaharwar/fettle/threat-model"><img src="https://agentmods.dev/badge/commands/milindgaharwar/fettle/threat-model.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 243 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 89% copy Near-identical to another mod 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 $0.00020 $0.00243
Opus 5 $0.00010 $0.00121
Sonnet 5 $0.00004 $0.00049
Haiku 4.5 $0.00002 $0.00024

Measured 4d ago against content hash 0f4ad15ff351, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

threat-model 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 4d 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.

Origin

This is a copy

89% identical to fettle-threat-model — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

commands/threat-model.md · 31 lines

What it actually says

Generate a threat model for the target service.

Procedure

  1. Determine service name. Use $ARGUMENTS if provided, otherwise derive from the workspace directory name.

  2. Run the generator:

    python3 -m fettle.threat_model --name SERVICE --root . --output docs/threat-model-SERVICE.md
    
  3. Present the auto-detected data (entry points, data stores, auth mechanisms) and ask the user to confirm or add missing items.

  4. Help fill STRIDE tables by analyzing the detected components and suggesting threats for each category.

  5. Save the completed model to docs/threat-model-{name}.md.

Notes

  • Auto-detection is best-effort (grep-based), NOT comprehensive
  • The STRIDE tables require human judgment to fill
  • This is a guided template, not a replacement for a security architect
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. 4d ago First seen · 31 lines · 20 tokens per session scan A 0f4ad15ff351

Subscribe to this mod's changes

threat-model is a command published in the GitHub repository MilindGaharwar/fettle (2 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 243 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to fettle-threat-model, differing in 9 lines, and is treated as a copy.