threat-model-triage

threat-model-triage is a skill for Claude Code from alpha-omega-security/threat-model. It costs 123 tokens per session (2,066 once invoked), scanned A, original, MIT.

A workflow for deciding whether one vulnerability report or security finding matches an existing threat model. A threat model documents what a system protects against and how findings should be classified.

In plain words
What is it for?
Triaging a scanner alert, fuzzer result, inbound vulnerability report, or AI-generated security finding against a completed threat model.
Why use it?
It prevents ad-hoc judgments by applying the threat model’s routing rules and producing one defined disposition with supporting references.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the threat-model plugin — 8 skills shipped together

Good fit Triaging a scanner alert, fuzzer result, inbound vulnerability report, or AI-generated security finding against a completed threat model.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alpha-omega-security/threat-model/threat-model-triage
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.

Any agent
npx skills add alpha-omega-security/threat-model --skill threat-model-triage
Clone the repo
git clone --depth 1 https://github.com/alpha-omega-security/threat-model

Made for: Claude Code.

Or install threat-model, the plugin that ships this one along with the rest of its 8 skills.

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-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/alpha-omega-security/threat-model/threat-model-triage/github.svg)](https://agentmods.dev/skills/alpha-omega-security/threat-model/threat-model-triage)
Your own site
<a href="https://agentmods.dev/skills/alpha-omega-security/threat-model/threat-model-triage"><img src="https://agentmods.dev/badge/skills/alpha-omega-security/threat-model/threat-model-triage/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for threat-model-triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/alpha-omega-security/threat-model/threat-model-triage"><img src="https://agentmods.dev/badge/skills/alpha-omega-security/threat-model/threat-model-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,066 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00123 $0.02066
Opus 5 $0.00062 $0.01033
Sonnet 5 $0.00025 $0.00413
Haiku 4.5 $0.00012 $0.00207

Measured 12d ago against content hash 2cb9d89192fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

threat-model-triage 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 12d 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.

skills/threat-model-triage/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Threat Model — Triage (route one finding)

The consumer side of the model. Given an inbound finding and a finished (or drafted) threat model, assign exactly one disposition from the closed §1.17 set, citing the section that licenses it. The response is "see threat model §X", not ad-hoc prose.

Requires a threat model produced by the threat-model orchestrator (or an equivalent document following output-structure.md). If no such model exists, stop and recommend producing one first.

Route from the prose and the threat-model.yaml sidecar, never from the threat-model.json export. The JSON drops disposition_precedence, disclaimed-property tiers, and known-non-finding component/symptom scope, so a consumer holding only the JSON cannot apply §1.17 first-match ordering or the security-critical floor. It states the contract; it cannot route a report against it.

Routing algorithm (the §1.1 triager quick-start)

  1. Locate the sink → look up its row in the §1.7 input-trust table (or the §1.8 output statement, for findings about what downstream consumers may assume).
  2. Locate the contract dimension → for state corruption, overflow, recursion, callback execution, deserialization, lifecycle, concurrency, or complexity findings, consult the component's contract-dimension row and its routed owning claim in §1.3/§1.5/§1.7/§1.10/§1.11/§1.12 or unresolved question in §1.18. Do not infer failure semantics from the parameter trust row alone.
  3. Check the attacker capability and control kind the finding requires against §1.7/§1.10. Distinguish control of data from control of size, type/class, callback code, object topology, collaborator implementation, or serialized state.
  4. Check the affected component against §1.2/§1.3, and any required build flag against §1.6.
  5. If the root cause lies in a dependency, apply §1.9.
  6. Check §1.15 for an exact known non-finding match: same component or sink, symptom/attack class, and required conditions, with a current stable discharge reference. Textual resemblance is insufficient.
  7. Apply §1.17's first-match precedence and assign exactly one disposition, citing the licensing section and provenance. If none fits, assign MODEL-GAP and trigger §1.16do not improvise.

Read the full file on GitHub · 132 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. 12d ago First seen · 132 lines · 123 tokens per session scan A 2cb9d89192fa

Subscribe to this mod's changes

threat-model-triage is a skill published in the GitHub repository alpha-omega-security/threat-model (54 stars, last pushed 24d ago), licensed MIT. It adds 123 tokens to every session and 2,066 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 skills, from other repositories

ads-linkedin

Audit LinkedIn Ads measurement, Insight Tag and conversions, professional audiences, lead generation, ABM, creative, bidding, budgets, pacing, automation, and policy. Use for LinkedIn Ads, Campaign Manager, Insight Tag, Lead Gen Forms, Thought Leader Ads, ABM campaigns, or B2B paid media.

AgriciDaniel/claude-ads · 68 tokens

ads-youtube

Audit YouTube Ads campaign setup, video and Demand Gen inventory, Shorts, in-stream, CTV, creative, audiences, brand safety, bidding, and measurement. Use for YouTube Ads, video ads, pre-roll, bumper ads, skippable in-stream, Shorts ads, Demand Gen, VAC migration, CTV, or YouTube campaign optimization.

AgriciDaniel/claude-ads · 76 tokens

ads-launch

Draft or explicitly apply a paid-ad campaign launch through Claude Ads capability-gated adapters. Use for campaign creation, launch plans, publishing ads, activating campaigns, uploading creative, or requests to push a campaign live.

AgriciDaniel/claude-ads · 45 tokens

notifications

Send notifications through the unified notification router.

vellum-ai/vellum-assistant · 9 tokens

telegram-setup

Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.

vellum-ai/vellum-assistant · 22 tokens

chat-complex-documents

Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…

vellum-ai/vellum-assistant · 90 tokens