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 skills add fatihkan/badi --skill pentest-ctfgit clone --depth 1 https://github.com/fatihkan/badiWrote 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/skills/fatihkan/badi/pentest-ctf)<a href="https://agentmods.dev/skills/fatihkan/badi/pentest-ctf"><img src="https://agentmods.dev/badge/skills/fatihkan/badi/pentest-ctf.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 66 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00084 | $0.01488 |
| Opus 5 | $0.00042 | $0.00744 |
| Sonnet 5 | $0.00017 | $0.00298 |
| Haiku 4.5 | $0.00008 | $0.00149 |
Grade A, and why
pentest-ctf 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 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.
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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pentest-ctf
CTF (Capture the Flag) challenge solving. Authorization: CTF platforms authorize attacks on their own platforms (in HackTheBox, THM, etc. ROEs). Use against any other platform counts as a violation.
Triggers
- "HackTheBox machine"
- "TryHackMe room"
- "PicoCTF challenge"
- "pwn challenge"
- "reverse engineering challenge"
- "crypto challenge"
- "stego challenge"
Category-Based Approach
Web
# Typical flag: HTB{...}, picoCTF{...}, flag.txt
# Approach:
1. Nmap full TCP (-p-)
2. HTTP banner + tech detect (whatweb)
3. Content discovery (ffuf / gobuster)
4. Parameter discovery (paramspider, Arjun)
5. SQL injection (sqlmap test but LOUD)
6. SSRF / XXE / SSTI / template injection
7. Source code reveal (.git, .env, backup files)
Pwn (Binary Exploitation)
# Typical: ELF binary + nc <host> <port>
# Approach:
1. `file ./challenge` + checksec
2. Strings + disassemble the main function (Ghidra)
3. Detect the vulnerability class:
- Buffer overflow (stack)
- Format string
- Use-after-free
- Heap overflow / off-by-one
4. ROP gadget search (ROPgadget / rp++)
5. Write the exploit (pwntools)
6. Local test -> remote
# Pwntools template
from pwn import *
context.arch = 'amd64'
context.log_level = 'debug'
# Local vs remote
local = True
if local:
p = process('./challenge')
else:
p = remote('host', port)
# Exploit
payload = b'A'*40 + p64(0xdeadbeef)
p.sendline(payload)
p.interactive()
Reverse Engineering
# Approach:
1. `file ./binary`
2. Strings (ascii + utf16)
3. Ghidra / IDA Free / Cutter
4. Anti-debug bypass (gdb scripts)
5. Decompile + analyze the main algorithm
6. Trace it to produce the output flag
# Standart RE tools
ghidra ./binary
r2 -A ./binary # radare2
gdb-peda ./binary # gdb + PEDA / pwndbg
strace -f ./binary # syscall trace
ltrace ./binary # library call trace
Crypto
# Common attack categories:
# - RSA: small e, common factor, common modulus
# - ECC: weak curve, invalid curve attack
# - AES: ECB pattern, CBC bit flipping, padding oracle
# - Stream: key reuse XOR
# - Hash: length extension, collision
# RSA small e
from Crypto.Util.number import long_to_bytes
import gmpy2
c, e, n = ..., 3, ...
m, exact = gmpy2.iroot(c, e)
if exact: print(long_to_bytes(int(m)))
# XOR cribdrag
from pwn import xor
plaintext_known = b'flag{'
c1, c2 = ..., ...
# c1 XOR c2 = m1 XOR m2 — crib drag with the known plaintext
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 · 216 lines · 84 tokens per session scan A bdb099157182
pentest-ctf is a skill published in the GitHub repository fatihkan/badi (7 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 1,488 once invoked, about $0.0004 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 2026-09-06.
Other skills, from other repositories
talk-stage3-concepts
Builds a numbered, categorized concept catalogue from the talk summary and timeline, scoring each concept HIGH / MEDIUM / LOW for talk potential with optional repo enrichment. Use when you need a structured inventory of concepts before choosing a talk angle, or when assessing which ideas have the strongest…
talk-stage6-revision
Produces revision sheets with quick navigation by act, a master concept-to-URL table, Q&A cheat-sheet with 6-10 anticipated questions, glossary, and external resources list. Use when preparing for a talk with Q&A, creating shareable reference material for attendees, or building a safety-net glossary for live delivery.
explain
Explain code, concepts, or system behavior with adjustable depth levels.
explaining-code
Explains code with diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when asked "how does this work?".
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…