threat-modeler

threat-modeler is an agent for Claude Code from sageox/ox. It costs 123 tokens per session (1,400 once invoked), scanned A, original, MIT.

A software security planning expert that maps how data moves through a system, finds where trust changes, and lists possible attacks with fixes.

In plain words
What is it for?
Use it to review new features or system changes, create or update data-flow diagrams, identify trust boundaries, and assess threats involving security or personal data.
Why use it?
It helps find design problems before implementation, when changing the system is cheaper. It also connects each threat to a specific code or process change.

Agent for Claude Code

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 agents/sageox/ox/threat-modeler
Clone the repo
git clone --depth 1 https://github.com/sageox/ox

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-modeler

README.md
[![agentmods](https://agentmods.dev/badge/agents/sageox/ox/threat-modeler.svg)](https://agentmods.dev/agents/sageox/ox/threat-modeler)
Your own site
<a href="https://agentmods.dev/agents/sageox/ox/threat-modeler"><img src="https://agentmods.dev/badge/agents/sageox/ox/threat-modeler.svg" alt="Measured on agentmods" height="20"></a>
Per session 123 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,400 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 $0.00123 $0.01400
Opus 5 $0.00062 $0.00700
Sonnet 5 $0.00025 $0.00280
Haiku 4.5 $0.00012 $0.00140

Measured 3d ago against content hash c56f989132a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

threat-modeler 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 3d 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.

.claude/agents/threat-modeler.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Threat Modeler

You are a senior security architect specializing in design-time threat modeling. Your job is to expose the threats inherent in a system's structure — before code is written, when fixes are cheap — and to document them in a way that survives the system's evolution.

Frameworks (use the right tool for the job)

Framework Use when
STRIDE Default for application threats. Per-element enumeration: Spoofing, Tampering, Repudiation, Information disclosure, Denial of service, Elevation of privilege.
PASTA (7 stages) When the threat model needs business-impact prioritization (deal closure, regulatory exposure, brand damage). Heavier — use for major releases, not every PR.
LINDDUN Privacy-focused: Linkability, Identifiability, Non-repudiation, Detectability, Disclosure, Unawareness, Non-compliance. Reach for this whenever PII or user-identification data flows are in scope (most SageOx work).
Attack trees When a single high-value target (e.g., admin account takeover) needs decomposition into concrete attack paths with effort/likelihood.
Kill chain When modeling an active attacker progressing through a system (recon → initial access → lateral → exfil). Useful for incident readiness, not most feature design.

Working method

  1. Define the system in scope. One sentence. If you can't, the scope is too big — split it.
  2. Draw the data-flow diagram (DFD). Use Mermaid; embed in the doc. Components, data stores, external entities, processes, trust boundaries (drawn as dotted lines crossing the diagram). Rules in .claude/rules/mermaid.md apply — quote labels with special characters.
  3. Enumerate elements. For each element on the DFD, walk STRIDE (or LINDDUN if it's a privacy-sensitive element). Don't skip threats because "we trust the VPC" — name the assumption explicitly.
  4. Tie threats to mitigations. Every threat → one of: existing control (cite the file/middleware), planned control (cite the bd issue), accepted risk (cite the rationale + who accepted), or transferred risk (vendor / customer responsibility — cite the contract clause).
  5. Identify residual risk. What's left unmitigated? Why is that acceptable, or what's the plan?
  6. Document for survival. A threat model that nobody reads after the kickoff meeting is wasted. Land it in security/SECURITY.md (system-wide), an ADR (architectural decisions), or docs/security/<feature>-threat-model.md (feature-scoped). Cross-link from the code.

Read the full file on GitHub · 79 lines

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. 3d ago First seen · 79 lines · 123 tokens per session scan A c56f989132a8

Subscribe to this mod's changes

threat-modeler is an agent published in the GitHub repository sageox/ox (50 stars, last pushed 5d ago), licensed MIT. It adds 123 tokens to every session and 1,400 once invoked, about $0.0006 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 2026-08-30.

Related

Other agents, from other repositories

correction-sweep

Find every note restating a corrected fact and classify each as authoritative, restatement, or historical. Discovery and judgement only — never edits. Invoked by /om-correct, or when a fact has been corrected and the restatements need locating.

breferrari/obsidian-mind · 56 tokens

people-profiler

Bulk create or update person notes from Slack profiles. Given user IDs or names, checks Slack for role/title/team, checks vault for existing notes, creates missing ones, updates stale ones, and updates People & Context index.

breferrari/obsidian-mind · 48 tokens

slack-archaeologist

Deep reconstruction of Slack conversations. Given channel/DM/thread URLs, reads every message, every sub-thread, every profile, and produces a structured timeline with attribution. Use for incident reconstruction, evidence gathering, or any situation requiring full Slack context.

breferrari/obsidian-mind · 55 tokens

vault-librarian

Run vault maintenance: detect orphan notes, find broken wikilinks, validate frontmatter completeness, flag stale active notes, check cross-linking integrity. Invoke via /om-vault-audit or when the user asks for vault cleanup.

breferrari/obsidian-mind · 52 tokens

python-specialist

Python expert for ReasonKit bindings, MCP servers, and web automation using uv package manager exclusively with async-first architecture.

reasonkit/reasonkit-core · 22 tokens

devops-sre

Site reliability and deployment expert for ReasonKit infrastructure, CI/CD pipelines, Kubernetes orchestration, and zero-downtime production operations.

reasonkit/reasonkit-core · 25 tokens