threat-model-quick

threat-model-quick is a command for Claude Code from RedHatProductSecurity/agentic-threat-modeling. It costs 25 tokens per session (420 once invoked), scanned A, original, Apache-2.0.

A command that automatically creates a full STRIDE threat assessment of the current code repository. STRIDE is a method for classifying security threats such as spoofing and data tampering.

In plain words
What is it for?
It helps discover system architecture, classify data, identify likely attackers, scan for threats, and write a detailed THREAT_MODEL.md report.
Why use it?
It finds threats without requiring an interview first and ties each finding to relevant code locations, making security risks easier to investigate.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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/redhatproductsecurity/agentic-threat-modeling/threat-model-quick
Clone the repo
git clone --depth 1 https://github.com/RedHatProductSecurity/agentic-threat-modeling

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 threat-model-quick

README.md
[![agentmods](https://agentmods.dev/badge/commands/redhatproductsecurity/agentic-threat-modeling/threat-model-quick.svg)](https://agentmods.dev/commands/redhatproductsecurity/agentic-threat-modeling/threat-model-quick)
Your own site
<a href="https://agentmods.dev/commands/redhatproductsecurity/agentic-threat-modeling/threat-model-quick"><img src="https://agentmods.dev/badge/commands/redhatproductsecurity/agentic-threat-modeling/threat-model-quick.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 420 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 5.1 $0.00025 $0.00420
Opus 5 $0.00013 $0.00210
Sonnet 5 $0.00005 $0.00084
Haiku 4.5 $0.00003 $0.00042

Measured 5d ago against content hash 8ef0df478e12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

threat-model-quick 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 5d 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.

module/commands/threat-model-quick.md · 26 lines

What it actually says

Invoke the threat-model skill in quick mode.

Run a full, non-interactive threat assessment — auto-picks all options so the user doesn't have to answer questions:

  1. If context: arguments are provided, ingest them first — these are docs the code scan won't find (architecture write-ups, compliance assessments, prior threat models, SBOMs). Merge with code analysis: prefer external docs for architectural intent, prefer code for implementation reality, flag discrepancies as findings.
  2. Auto-discover system context from code (no interview questions)
  3. Build a data classification table mapping each data type to sensitivity, storage, flows, and regulatory scope
  4. Apply STRIDE framework
  5. Ground every threat in code with file:line citations. For each threat, locate the specific file and line that makes it exploitable. For absence-of-control threats, note where the control should exist.
  6. Auto-detect 2-3 most relevant threat actor personas
  7. Find as many threats as the codebase warrants — do not cap or limit the count
  8. Produce a full THREAT_MODEL.md following the report template, including all sections: executive summary, architecture overview, actor profiles, assets, data classification, attack surface, threats with narratives and code citations, mitigation roadmap, open questions, and provenance

This is the "autopilot" mode — same depth as guided, without the interview. Useful when you want a complete threat model without back-and-forth.

Optional arguments:

  • A file or directory path to focus on (default: entire repo)
  • actors:insider,apt to override auto-detected actor personas
  • context:file,dir/,url for docs the code scan won't find (comma-separated; paths relative to repo root)

Arguments from user: $ARGUMENTS

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. 5d ago First seen · 26 lines · 25 tokens per session scan A 8ef0df478e12

Subscribe to this mod's changes

threat-model-quick is a command published in the GitHub repository RedHatProductSecurity/agentic-threat-modeling (4 stars, last pushed 25d ago), licensed Apache-2.0. It adds 25 tokens to every session and 420 once invoked, about $0.0001 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.