threat-model-backtest

threat-model-backtest is a skill for Claude Code from alpha-omega-security/threat-model. It costs 124 tokens per session (2,316 once invoked), scanned A, original, MIT.

A backtesting guide for a threat model, meaning it tests the draft against earlier security reports and findings. It builds a varied review set across project components and risk categories.

In plain words
What is it for?
Use it to assemble historical findings, test coverage across security concerns, group large collections, and check the model's routing decisions.
Why use it?
It shows whether the threat model can correctly classify and route real security reports before approval.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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

Good fit Use it to assemble historical findings, test coverage across security concerns, group large collections, and check the model's routing decisions.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/alpha-omega-security/threat-model/threat-model-backtest"><img src="https://agentmods.dev/badge/skills/alpha-omega-security/threat-model/threat-model-backtest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,316 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 $0.00124 $0.02316
Opus 5 $0.00062 $0.01158
Sonnet 5 $0.00025 $0.00463
Haiku 4.5 $0.00012 $0.00232

Measured 9d ago against content hash 5087e5bd4140, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

threat-model-backtest 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 9d 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-backtest/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Threat Model — Backtest (validate against history)

Phase 3.6. A draft that has never been backtested is untested software. The project's own history is a free test suite; use it before presenting the draft for sign-off. This is a producer-side quality gate — the corpus does not go into the published document (per the leave-out list: CVE history is not the threat model).

Procedure

  1. Assemble a stratified corpus — start with the last 10–30 inbound security findings: published advisories, reports closed as "not a bug" / "by design", issues labeled security, and scanner/fuzzer/AI-analysis output. If a vendored security-context.md is present in the working directory (a runner's pre-fetch of exactly this material), seed the corpus from it before searching elsewhere. Prefer contested items, but do not let recency or controversy leave component families or contract dimensions untested.
    • Cover every in-scope component family.
    • Cover every applicable contract-dimension row: numeric limits, failure atomicity, topology, callbacks, serialization, lifecycle, concurrency, and resource complexity.
    • For a large corpus, cluster by (component, sink, attack class, required attacker capability) and route at least one representative from every cluster. Increase the corpus beyond 30 when necessary to avoid an untested cluster; report both item count and cluster count.
    • Record each item's actual historical outcome where one exists — fixed, wontfix, by-design, out-of-scope, or unknown — with the advisory or issue URL it came from. That label is the ground truth step 3 scores against, and without it the backtest cannot fail. Set the outcome aside while routing (step 2 is blind); compare only afterwards.
    • When no historical record is reachable, say so rather than inventing one. Synthesize cases to exercise the matrix, mark every one synthesized, and write the §1.1 note verbatim: "no historical corpus was available; the backtest routed N synthesized cases only." A self-invented corpus reported as history is worse than no backtest, because it reads as evidence.
  2. Route each item blind — using only the draft (not hindsight knowledge of how it was actually resolved), apply the §1.1 triager quick-start and assign exactly one §1.17 disposition, citing the licensing section. Routing rules and the closed disposition set are in output-structure.md.
  3. Score the routing. The two directions of error are not symmetric. Wrongly closing a real vulnerability is far worse than wrongly escalating a non-finding: an over-escalating model wastes maintainer time, an over-closing one hands a reporter a "not a bug" on a live issue. Score accordingly — this asymmetry decides every fix below.

Read the full file on GitHub · 154 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. 9d ago First seen · 154 lines · 124 tokens per session scan A 5087e5bd4140

Subscribe to this mod's changes

threat-model-backtest is a skill published in the GitHub repository alpha-omega-security/threat-model (54 stars, last pushed 21d ago), licensed MIT. It adds 124 tokens to every session and 2,316 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

copilotkit-contribute

Use when contributing to the CopilotKit open-source project — forking, cloning, setting up the monorepo, creating branches, running tests, and submitting pull requests against CopilotKit/CopilotKit.

CopilotKit/CopilotKit · 49 tokens

voice-agent-test-harness

Drive a fixed suite of spoken tests against a voice agent ("subject") from a co-located machine ("prober"), measure response latency / clarity / accuracy, diff against baseline, and report to the owner over Telegram.

sonichi/sutando · 0 tokens

test-harness

Generates pytest test suites with happy path, edge cases, error conditions, fixture scaffolding, mocks, async patterns. Triggers on: "generate tests", "write tests for", "test this function", "create test suite", "pytest for", "unit tests for", "mock strategy for".

Mathews-Tom/armory · 65 tokens

surrogate-verifier

Generates structured test assertions and failure diagnostics for skill packages from a definition and task prompt. Triggers on: "verify this skill", "generate assertions", "surrogate verification", "diagnose skill failure". NOT for code review, use pr-review.

Mathews-Tom/armory · 56 tokens

ship-workflow

Automated release pipeline: merges main, runs tests, pre-landing review, version bump, changelog, bisectable commits, and PR creation. Triggers on: "ship it", "release this", "prepare for release", "open a PR", "push and PR", "land this", "/ship-workflow".

Mathews-Tom/armory · 71 tokens

api-tester

API testing expert for curl, REST, GraphQL, authentication, and debugging.

RightNow-AI/openfang · 19 tokens