threat-modeling

threat-modeling is a skill for Claude Code from HalidSaglam/saglitzsecure. It costs 60 tokens per session (1,069 once invoked), scanned A, original, MIT.

A planning method for identifying what a system must protect, where trust changes between parts of the system, and which attackers to consider. It is meant for threat modelling, a security exercise done before or during system design rather than after implementation.

In plain words
What is it for?
Use it when starting a project, making an architectural decision, or deciding whether a planned system is secure enough.
Why use it?
It helps teams decide what matters and what needs protection before choosing technical safeguards or starting an audit.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the saglitzsecure plugin — 4 skills, 1 MCP server shipped together

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/halidsaglam/saglitzsecure/threat-modeling
Any agent
npx skills add HalidSaglam/saglitzsecure --skill threat-modeling
Clone the repo
git clone --depth 1 https://github.com/HalidSaglam/saglitzsecure

Made for: Claude Code.

Or install saglitzsecure, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

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-modeling

README.md
[![agentmods](https://agentmods.dev/badge/skills/halidsaglam/saglitzsecure/threat-modeling.svg)](https://agentmods.dev/skills/halidsaglam/saglitzsecure/threat-modeling)
Your own site
<a href="https://agentmods.dev/skills/halidsaglam/saglitzsecure/threat-modeling"><img src="https://agentmods.dev/badge/skills/halidsaglam/saglitzsecure/threat-modeling.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,069 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 $0.00060 $0.01069
Opus 5 $0.00030 $0.00535
Sonnet 5 $0.00012 $0.00214
Haiku 4.5 $0.00006 $0.00107

Measured 5d ago against content hash 6a01749aba67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

threat-modeling 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.

skills/threat-modeling/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Threat modelling

This skill is not an audit but a frame: it settles what the system carries, who can attack it from where, and which target it should be designed against. It comes in before code is written or before an audit starts.

If the user is asking whether code that has been written is secure, the skill in play is security-audit, not this one; if they want the secure default for a specific decision (cookies, CORS, storing a secret) before writing code, secure-by-default is in play. This skill comes before both: it settles which asset matters and which boundary needs protecting, and the other two then work with that.

1. Call threat_model

Give the project's absolute root directory as path. The result carries:

  • assets — the valuable things the system holds (user accounts, server-side secrets, data stored on the device).
  • trustBoundaries — the boundaries where one side does not trust the other (browser ↔ server, app ↔ network).
  • attacker — the attacker types being modelled (an unauthenticated user, an authenticated but unauthorised user, someone who can read the repository).
  • targetLevel — the suggested ASVS level.
  • path — ordered steps to read, each tied to a knowledge section (knowledgeId) and to why it comes at that point in the order (why).

If the project type cannot be detected (kinds comes back empty) the tool still gives a type-independent core model (secrets, authorization, dependencies); the notes field says that this has to be completed by hand with the project's own assets and boundaries — do not skip that note.

2. The level decision is the user's

The tool suggests L2 as the targetLevel because it cannot know the system's real value: L1 is defensible only for low-risk applications that carry no data; L3 is for regulated or high-value systems. Ask the user whether L1 or L3 fits better — they are the one who knows what the system carries, who uses it and which regulation it falls under. Do not accept the tool's L2 without question and make the decision on the user's behalf.

Read the full file on GitHub · 77 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. 5d ago First seen · 77 lines · 60 tokens per session scan A 6a01749aba67

Subscribe to this mod's changes

threat-modeling is a skill published in the GitHub repository HalidSaglam/saglitzsecure (0 stars, last pushed 8d ago), licensed MIT. It adds 60 tokens to every session and 1,069 once invoked, about $0.0003 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens