pentest-attacks

pentest-attacks is a command for Claude Code from Stickman230/claude-pentest. It costs 60 tokens per session (1,802 once invoked), scanned A, original, MIT.

An attack-profile command that lets you choose which security-testing categories and skills an engagement should use. It saves those choices in a project file for the pentest coordinator.

In plain words
What is it for?
Use it to create or update an attack selection before a penetration test, or to keep an existing selection unchanged.
Why use it?
It keeps the testing focused on the areas you selected and preserves the choices for later use. Running it alone does not start a penetration test.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the pentest plugin — 7 skills, 5 commands, 15 agents shipped together

Good fit Use it to create or update an attack selection before a penetration…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/stickman230/claude-pentest/pentest-attacks
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.

Clone the repo
git clone --depth 1 https://github.com/Stickman230/claude-pentest

Made for: Claude Code.

Or install pentest, the plugin that ships this one along with the rest of its 7 skills, 5 commands, 15 agents.

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 pentest-attacks

README.md
[![agentmods](https://agentmods.dev/badge/commands/stickman230/claude-pentest/pentest-attacks.svg)](https://agentmods.dev/commands/stickman230/claude-pentest/pentest-attacks)
Your own site
<a href="https://agentmods.dev/commands/stickman230/claude-pentest/pentest-attacks"><img src="https://agentmods.dev/badge/commands/stickman230/claude-pentest/pentest-attacks.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,802 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 $0.00060 $0.01802
Opus 5 $0.00030 $0.00901
Sonnet 5 $0.00012 $0.00360
Haiku 4.5 $0.00006 $0.00180

Measured 7d ago against content hash 395e431cb7d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pentest-attacks 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 7d 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.

plugins/pentest/commands/pentest-attacks.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Output the following banner verbatim:

============================================================
[ATTACK PROFILE DEFINITION]
============================================================

Step 1 — Check for Existing Attack Profile

Try to Read .pentest-attacks.json.

If the file exists and is valid JSON, extract and store mode and selected_categories, then output:

============================================================
EXISTING ATTACK PROFILE FOUND
============================================================
Mode: {mode}
Categories: {comma-separated list of selected_categories[*].label}
============================================================

Then use AskUserQuestion to ask:

"An attack profile already exists. What would you like to do?"

Present exactly these options:

  • "Update profile — define a new attack selection (replaces existing)"
  • "Keep existing profile — no changes"

If "Keep existing profile", output:

Attack profile unchanged.

Then stop.

If "Update profile", continue to Step 2.

If the file does not exist, continue directly to Step 2.

Step 2 — Mode Selection

Use AskUserQuestion to ask:

"How do you want to configure the attack profile for this engagement?"

Present exactly these options:

  • "Full suite — test all attack categories (default, recommended for thorough engagements)"
  • "Web application profile — injection, client-side, server-side, authentication, API, business logic"
  • "API & cloud profile — API security, cloud & containers, infrastructure, CVE testing, domain recon"
  • "Custom — I will select specific categories"

Store the answer as selected_mode.

If "Full suite", set attack_mode = "full" and skip to Step 4. If "Web application profile", set attack_mode = "web-app" and skip to Step 4. If "API & cloud profile", set attack_mode = "api-cloud" and skip to Step 4. If "Custom", set attack_mode = "custom" and continue to Step 3.

Step 3 — Custom Category Selection (only if attack_mode = "custom")

Read the full file on GitHub · 176 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. 7d ago First seen · 176 lines · 60 tokens per session scan A 395e431cb7d9

Subscribe to this mod's changes

pentest-attacks is a command published in the GitHub repository Stickman230/claude-pentest (99 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 1,802 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 2026-08-30.