threat-model

threat-model is a skill for Claude Code, Codex from luisalima/agent-policy-kit. It costs 28 tokens per session (593 once invoked), scanned A, original, MIT.

A security planning method for software architecture. It maps trust boundaries, valuable assets, possible attackers and abuse paths, and the safeguards that reduce those risks.

In plain words
What is it for?
Use it before architecture work that changes who can access what, how data crosses systems, how secrets are handled, or how the software is exposed to a network. It produces an actionable security threat model grounded in the project.
Why use it?
It exposes security problems before architectural choices become expensive or difficult to reverse. It focuses attention on areas such as authentication, permissions, secrets, network access, and third-party connections when they are relevant.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

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 skills/luisalima/agent-policy-kit/threat-model
Any agent
npx skills add luisalima/agent-policy-kit --skill threat-model
Clone the repo
git clone --depth 1 https://github.com/luisalima/agent-policy-kit

Made for: Claude Code, Codex.

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/skills/luisalima/agent-policy-kit/threat-model.svg)](https://agentmods.dev/skills/luisalima/agent-policy-kit/threat-model)
Your own site
<a href="https://agentmods.dev/skills/luisalima/agent-policy-kit/threat-model"><img src="https://agentmods.dev/badge/skills/luisalima/agent-policy-kit/threat-model.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 593 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 $0.00028 $0.00593
Opus 5 $0.00014 $0.00296
Sonnet 5 $0.00006 $0.00119
Haiku 4.5 $0.00003 $0.00059

Measured 6d ago against content hash a960dbef69e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

.agents/skills/threat-model/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Threat Model

Use this skill before architecture work, especially before costly or hard-to-reverse decisions that introduce or change trust boundaries, auth, authorization, privileged automation, network exposure, data flows, multi-tenancy, deployment topology, secrets handling, or third-party integrations.

Do not make this a ritual for every task. State why threat modeling is relevant, and let the user decline unless the repo policy makes it a gate.

Goal

Produce an actionable AppSec threat model before the architecture becomes expensive to change.

Workflow

  1. Define scope: repo root, in-scope paths, deployment model, intended users, internet exposure, auth expectations, and sensitive data.
  2. Ground the system model in repository evidence. Identify runtime components, entry points, data stores, external integrations, CI/build tooling, and tests separately.
  3. Enumerate trust boundaries as concrete edges between components. Note protocol, auth, encryption, validation, authorization, and rate limiting when there is evidence.
  4. List assets that drive risk: credentials, PII, customer data, integrity critical state, build artifacts, release permissions, models, config, compute resources, and audit logs.
  5. State realistic attacker capabilities and non-capabilities. Avoid inflated threat assumptions.
  6. Enumerate a small set of abuse paths tied to assets and boundaries.
  7. Prioritize each threat with likelihood, impact, existing controls, and the assumptions that most affect the ranking.
  8. Ask 1-3 targeted questions if missing context materially changes the threat ranking. If the user cannot answer, record the assumption.
  9. Recommend concrete mitigations tied to locations, components, or boundaries.

Output

# Threat Model: <system or path>

## Scope
<in-scope and out-of-scope areas>

## System Model
<components, entry points, data stores, integrations, evidence>

## Trust Boundaries
- <boundary>: <protocol/auth/data/control notes>

## Assets
- <asset>: <why it matters>

## Attacker Capabilities
<capabilities and non-capabilities>

## Threats
### T1. <abuse path>
- Asset: <asset>
- Boundary: <boundary>
- Likelihood: Low | Medium | High
- Impact: Low | Medium | High
- Priority: Low | Medium | High | Critical
- Existing controls: <evidence-backed controls>
- Recommended mitigations: <specific actions>

## Assumptions And Open Questions
- <assumption or question>

Read the full file on GitHub · 80 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. 6d ago First seen · 80 lines · 28 tokens per session scan A a960dbef69e5

Subscribe to this mod's changes

threat-model is a skill published in the GitHub repository luisalima/agent-policy-kit (2 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 593 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens