10x-pentest: Skill for Claude Code

.github/skills/pt-threat-model-review/SKILL.md

pt-threat-model-review is a skill for Claude Code, Codex from brovar/10x-pentest. It costs 117 tokens per session (1,962 once invoked), scanned A, original, Apache-2.0.

An independent review of a security threat model, which lists possible attack paths, and its test objectives, which describe what testing should check. It looks for missed risks, weak priorities, and incomplete testing plans, then records findings for discussion.

In plain words
What is it for?
Use it after creating a threat model and before security testing. It helps find missing attack paths, assess the quality of test objectives, and decide how to handle review findings.
Why use it?
A threat model can appear complete while still overlooking important ways an attacker could cause harm. This review provides a separate check before code or live testing begins.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; names the AskUserQuestion tool.

This is brovar/10x-pentest's own configuration. It tells Claude Code and Codex how to work on 10x-pentest itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything 10x-pentest configures →

Reuse

Borrowing it

Nothing to install: this file belongs to brovar/10x-pentest. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/brovar/10x-pentest/main/.github/skills/pt-threat-model-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/brovar/10x-pentest

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 pt-threat-model-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/brovar/10x-pentest/pt-threat-model-review/github.svg)](https://agentmods.dev/skills/brovar/10x-pentest/pt-threat-model-review)
Your own site
<a href="https://agentmods.dev/skills/brovar/10x-pentest/pt-threat-model-review"><img src="https://agentmods.dev/badge/skills/brovar/10x-pentest/pt-threat-model-review/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 pt-threat-model-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/brovar/10x-pentest/pt-threat-model-review"><img src="https://agentmods.dev/badge/skills/brovar/10x-pentest/pt-threat-model-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,962 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.
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 $0.00117 $0.01962
Opus 5 $0.00059 $0.00981
Sonnet 5 $0.00023 $0.00392
Haiku 4.5 $0.00012 $0.00196

Measured 12d ago against content hash c5394f88f1d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pt-threat-model-review 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.

.github/skills/pt-threat-model-review/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pt-threat-model-review — Threat-Model Quality Review

An independent critic for the threat model + objective register. /pt-threat-model's creation gate checks "is every surface item mapped to an objective or excluded?"; this asks "are the objectives deep, correctly prioritized, and complete enough that testing won't miss the real attacks?" — and independently hunts for attack paths the model missed.

Advisory, with triage. It does not hard-block the testing stages; the register's creation gate is the floor. But the objectives drive Stages 3–4, so gaps here become untested vulnerabilities.

When to use, when to skip

  • Use after /pt-threat-model, before code/dynamic testing — the last cheap chance to add a missed attack.
  • Skip only for a re-review you trust. Advisory: proceeding without it is allowed.

Initial Response

  • <engagement-id> → review that engagement's threat model (Step 0).
  • A saved report path (contains <!-- PT-THREAT-MODEL-REVIEW -->) → resume triage (Step 7).
  • Without → print Usage: /pt-threat-model-review <engagement-id>. and STOP.

Inputs

  • threat-model.md + test-objectives.md[blocking] (the subject; the register is the living ledger).
  • target-profile.md + attack-surface.md[blocking] (the surface the model must cover).
  • scope.md[blocking] (asset criticality anchors impact; accounts bound preconditions).
  • foundation/threat-library.md[optional] reference for the abuse-lens hunt.

Process

Step 1: Internal-consistency scan

Read the register against test-objectives-schema, the surface, and scope.md. Flag: a TM row whose surface_ids don't exist; impact not anchored to asset criticality; a priority that doesn't match the impact×likelihood matrix; a both-routed objective that's really static-only; a ## Surface coverage row missing or double-counted.

Step 2: Grounding spot-checks

Verify standard_refs/CWE/ATT&CK on a few objectives are apt (not a mislabeled category); confirm each objective's precondition is satisfiable by the scope's U-NNN accounts.

Read the full file on GitHub · 134 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 · 134 lines · 0 tokens per session scan A c5394f88f1d4

Subscribe to this mod's changes

pt-threat-model-review is a skill published in the GitHub repository brovar/10x-pentest (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 117 tokens to every session and 1,962 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 2026-08-31.

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