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/allsmog/pwn-claude-pluginWrote 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/allsmog/pwn-claude-plugin/pwn-setup)<a href="https://agentmods.dev/commands/allsmog/pwn-claude-plugin/pwn-setup"><img src="https://agentmods.dev/badge/commands/allsmog/pwn-claude-plugin/pwn-setup.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 | $0.00015 | $0.00680 |
| Opus 5 | $0.00008 | $0.00340 |
| Sonnet 5 | $0.00003 | $0.00136 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
pwn-setup 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PWN Setup - Environment Verification
Verify binary exploitation tools are installed and optionally create a workspace structure.
Execution Steps
Step 1: Check Core Tools
Verify essential tools:
# Python and pwntools
python3 --version
python3 -c "from pwn import *; print(f'pwntools {pwnlib.version.__version__}')"
# GDB
gdb --version
# checksec
checksec --version 2>/dev/null || python3 -c "from pwn import *; print('checksec available via pwntools')"
Step 2: Check Recommended Tools
Check additional tools:
# ROPgadget
python3 -c "import ROPGadget" && echo "ROPgadget: OK" || echo "ROPgadget: MISSING (pip install ROPgadget)"
# ropper
python3 -c "import ropper" && echo "ropper: OK" || echo "ropper: MISSING (pip install ropper)"
# one_gadget
which one_gadget && echo "one_gadget: OK" || echo "one_gadget: MISSING (gem install one_gadget)"
# seccomp-tools
which seccomp-tools && echo "seccomp-tools: OK" || echo "seccomp-tools: MISSING (gem install seccomp-tools)"
Step 3: Check GDB Extensions
# Check for pwndbg
gdb -q -batch -ex "python import pwndbg; print('pwndbg: OK')" 2>/dev/null || echo "pwndbg: NOT DETECTED"
Step 4: Auto-Install (if --install flag)
If --install flag provided and missing tools detected:
# Install Python packages
pip install pwntools ROPgadget ropper
# Ruby gems (inform user, don't auto-run)
echo "For Ruby tools, run: gem install one_gadget seccomp-tools"
Step 5: Create Workspace (Optional)
Ask user if they want to create workspace structure:
mkdir -p challenge/{core,libc}
touch challenge/{exploit.py,notes.md,.gdbinit}
Output Format
## Environment Setup
### Tool Status
| Tool | Status | Version |
|------|--------|---------|
| Python | OK | 3.11.0 |
| pwntools | OK | 4.11.0 |
| GDB | OK | 13.2 |
| pwndbg | OK | - |
| ROPgadget | OK | - |
| ropper | MISSING | - |
| one_gadget | OK | 2.1.0 |
| seccomp-tools | MISSING | - |
### Missing Tools
- ropper: `pip install ropper`
- seccomp-tools: `gem install seccomp-tools`
### Workspace
Not created (use --install to create)
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 · 100 lines · 15 tokens per session scan A 22f31366ec4b
pwn-setup is a command published in the GitHub repository allsmog/pwn-claude-plugin (2 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 680 once invoked, about $0.0001 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.
Other commands, from other repositories
bb-ad
Active Directory enumeration and attack techniques. Includes LDAP enumeration, Kerberos attacks (Kerberoasting, AS-REP Roasting), SMB attacks, and domain privilege escalation. Use this when targeting Windows domain environments.
bb-enum
Service-specific enumeration based on discovered ports. Automatically selects appropriate enumeration techniques for each service. Use after /bb-recon to deeply enumerate discovered services.
bb-crack
Crack password hashes with automatic type detection and wordlist discovery. Supports MD5, SHA, NTLM, bcrypt, and more.
bb-setup
Verify penetration testing environment and tool installation. Use this before starting an HTB machine to ensure all required tools are available.
bb-spray
Credential spraying across discovered services.
bb-web
Comprehensive web application testing for HTTP/HTTPS services. Includes directory fuzzing, vulnerability scanning, technology fingerprinting, and common exploit checks. Use this when a web service is discovered.