threat

threat is a skill for Claude Code, Codex from itsbroken-ai/forge-plugin. It costs 98 tokens per session (3,743 once invoked), scanned A, original, MIT.

A security-design guide for asking what could go wrong in a system before building it. It maps components, data flows, trust boundaries, and entry points, then uses STRIDE, a common threat-modeling method, to identify threats.

In plain words
What is it for?
Use it for threat modeling, security architecture reviews, and planning safer systems before code is written.
Why use it?
It helps uncover attack paths early and connect each threat to a mitigation or an explicitly accepted risk.

Skill for Claude CodeCodex

Part of the forge plugin — 6 skills 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/itsbroken-ai/forge-plugin/threat
Any agent
npx skills add itsbroken-ai/forge-plugin --skill threat
Clone the repo
git clone --depth 1 https://github.com/itsbroken-ai/forge-plugin

Made for: Claude Code, Codex.

Or install forge, the plugin that ships this one along with the rest of its 6 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

README.md
[![agentmods](https://agentmods.dev/badge/skills/itsbroken-ai/forge-plugin/threat.svg)](https://agentmods.dev/skills/itsbroken-ai/forge-plugin/threat)
Your own site
<a href="https://agentmods.dev/skills/itsbroken-ai/forge-plugin/threat"><img src="https://agentmods.dev/badge/skills/itsbroken-ai/forge-plugin/threat.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,743 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 $0.00098 $0.03743
Opus 5 $0.00049 $0.01871
Sonnet 5 $0.00020 $0.00749
Haiku 4.5 $0.00010 $0.00374

Measured 3d ago against content hash 54fce974d253, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

threat 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.

skills/threat/SKILL.md · 332 lines

How it starts

The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.

forge:threat — STRIDE Threat Model

Build a threat model that thinks like an attacker planning an operation, not an auditor filling out a spreadsheet.

A threat model answers one question: "What can go wrong, and what are we doing about it?" If your threat model doesn't change how you build the system, it was a waste of time. This skill produces models that drive real engineering decisions.

How This Works

When invoked, you build a threat model in four phases:

  1. Scope — Define what you're modeling. Draw the boundary. Identify what's in, what's out, and why.
  2. Decompose — Break the system into components, data flows, trust boundaries, and entry points. Understand how the pieces talk to each other.
  3. Threaten — Apply STRIDE to every component and data flow that crosses a trust boundary. Think like the attacker. What would you try?
  4. Decide — Map threats to mitigations. Identify residual risks. Make explicit decisions about what you're accepting and why.

The Threat Modeling Mindset

This is not compliance. This is operational planning.

When you threat model, you are the attacker sitting across the table from the design. Your job is to find the paths through the system that the builders didn't think about. Every assumption is a potential entry point. Every "that would never happen" is a target.

Three principles:

  • Attackers don't follow your architecture diagrams. They follow data flows, trust transitions, and error paths. Model what actually happens, not what the docs say happens.
  • The most dangerous threats are the ones you assumed away. "We trust the internal network." "The admin panel isn't exposed." "Nobody would do that." These are where breaches start.
  • A threat you've decided to accept is better than a threat you never identified. Residual risk is fine. Unknown risk is not. The goal is informed decisions, not zero risk.

STRIDE Categories

STRIDE is the lens. Apply it to every component and every data flow that crosses a trust boundary.

Read the full file on GitHub · 332 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 · 332 lines · 98 tokens per session scan A 54fce974d253

Subscribe to this mod's changes

threat is a skill published in the GitHub repository itsbroken-ai/forge-plugin (11 stars, last pushed 5mo ago), licensed MIT. It adds 98 tokens to every session and 3,743 once invoked, about $0.0005 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

systematic-debugging

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

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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