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.
git clone --depth 1 https://github.com/Stickman230/claude-pentestWrote 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.
[](https://agentmods.dev/commands/stickman230/claude-pentest/pentest-attacks)<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>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.
| Model | Per session | Once 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 |
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.
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")
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.
- 7d ago First seen · 176 lines · 60 tokens per session scan A 395e431cb7d9
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.
Other commands, from other repositories
unpack
Detect and remove binary packing/protection.
dashboard
Show running scans, system health, and engagement status.
apiscan
API security audit — REST, GraphQL, JWT analysis, parameter discovery.
bruteforce
Password brute force and hash cracking against target services.
payload
AI-powered payload generation for XSS, SQLi, LFI, command injection, and more.
recon
Full reconnaissance workflow — subdomain enum, tech detection, WAF fingerprinting, crawling.