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-gdbinit)<a href="https://agentmods.dev/commands/allsmog/pwn-claude-plugin/pwn-gdbinit"><img src="https://agentmods.dev/badge/commands/allsmog/pwn-claude-plugin/pwn-gdbinit/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-gdbinit"><img src="https://agentmods.dev/badge/commands/allsmog/pwn-claude-plugin/pwn-gdbinit.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 | $0.00019 | $0.00844 |
| Opus 5 | $0.00010 | $0.00422 |
| Sonnet 5 | $0.00004 | $0.00169 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
pwn-gdbinit 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 10d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PWN GDBInit - Generate GDB Configuration
Create a project-specific .gdbinit file optimized for pwndbg exploitation.
Execution Steps
Step 1: Analyze Binary
file <binary>
nm <binary> 2>/dev/null | head -20
Identify key functions for breakpoints.
Step 2: Generate .gdbinit
Create .gdbinit in current directory with:
- ASLR disabled
- Common breakpoints
- Useful pwndbg commands
- Custom helpers
Generated .gdbinit
# ===========================================
# PWN Challenge GDB Configuration
# Target: <binary>
# Generated for pwndbg
# ===========================================
# === BASIC SETUP ===
set disable-randomization on
set follow-fork-mode child
set pagination off
# Load target binary
file ./<binary>
# === BREAKPOINTS ===
# Main entry
b main
# Vulnerable function (update as needed)
# b vuln
# b *vuln+0x30 # Before ret
# Library functions
# b *gets@plt
# b *printf@plt
# b *system@plt
# === CUSTOM COMMANDS ===
# Show useful info
define pwn-info
echo \n=== Binary Info ===\n
checksec
echo \n=== Memory Map ===\n
vmmap
echo \n=== GOT Entries ===\n
got
end
# Examine stack around RSP
define pwn-stack
echo \n=== Stack ===\n
telescope $rsp 20
end
# Examine heap (if applicable)
define pwn-heap
echo \n=== Heap ===\n
heap
bins
end
# Find offset from cyclic pattern
define pwn-offset
echo \n=== Cyclic Offset ===\n
cyclic -l $rsp
end
# Run with pattern input
define pwn-pattern
shell python3 -c "from pwn import *; open('/tmp/pattern','wb').write(cyclic(200))"
run < /tmp/pattern
end
# === HOOKS ===
# Show context on every stop
define hook-stop
context
end
# === ALIASES ===
alias pinfo = pwn-info
alias pstack = pwn-stack
alias pheap = pwn-heap
alias poff = pwn-offset
alias ppat = pwn-pattern
# === STARTUP ===
echo \n[*] PWN GDB config loaded\n
echo [*] Commands: pinfo, pstack, pheap, poff, ppat\n
echo [*] Run 'ppat' to test with cyclic pattern\n\n
Usage
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.
- 10d ago First seen · 158 lines · 19 tokens per session scan A 821a9513fe31
pwn-gdbinit is a command published in the GitHub repository allsmog/pwn-claude-plugin (2 stars, last pushed 6mo ago), licensed MIT. It adds 19 tokens to every session and 844 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
linkerd
Linkerd-specific diagnostics — mTLS verification, proxy injection issues, authorization policy debugging, traffic management, and multi-cluster connectivity problems.
debug
Systematic debugging with hypotheses and evidence gathering.
ia-report-bug
Report a bug in the whetstone plugin.
data-flow-analysis
Trace how data flows through the system from input to output.
duck-off
Turn off Rubber Duck mode and answer normally.
bug
Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.