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 a2ure123/ctf-pwn-skill --skill ctf-pwngit clone --depth 1 https://github.com/a2ure123/ctf-pwn-skillWrote 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/a2ure123/ctf-pwn-skill/ctf-pwn)<a href="https://agentmods.dev/skills/a2ure123/ctf-pwn-skill/ctf-pwn"><img src="https://agentmods.dev/badge/skills/a2ure123/ctf-pwn-skill/ctf-pwn/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/skills/a2ure123/ctf-pwn-skill/ctf-pwn"><img src="https://agentmods.dev/badge/skills/a2ure123/ctf-pwn-skill/ctf-pwn.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 | $0.00084 | $0.05629 |
| Opus 5 | $0.00042 | $0.02815 |
| Sonnet 5 | $0.00017 | $0.01126 |
| Haiku 4.5 | $0.00008 | $0.00563 |
Grade A, and why
ctf-pwn 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 11d 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 — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CTF Pwn
This skill follows the portable SKILL.md convention and runs unchanged under Codex (~/.codex/skills/ctf-pwn), Claude Code (~/.claude/skills/ctf-pwn or project ./.claude/skills/ctf-pwn), and any other agent that loads SKILL.md skills. Reference files under references/ are loaded on demand; read them when the topic matches.
Use this skill for local or remote CTF pwn challenges. Work like a pwn player: reproduce the remote runtime, reverse the binary, wrap the protocol/menu, then prove the vulnerability with a persistent GDB/pwndbg session before committing to an exploit route. For live debugging the primary path is a persistent GDB driven through plain tmux CLI from Bash (tmux send-keys to issue commands, tmux capture-pane -p -S - to read the full output), so you can step, inspect, and decide the next command adaptively — no MCP server required. Keep GDB, normal shell, and inferior stdin/stdout in separate tmux panes, feed the inferior through its TTY, and inspect state after each meaningful step. Use one-shot/batch GDB only to verify a known hypothesis.
Mandatory References
Read these reference files when the topic is relevant:
references/ctf-workflow.md: end-to-end solve order, state tracking, environment matching, reverse engineering, and debug loop.references/tmux-debugging.md: tmux-CLI persistent-GDB pane layout (plus batch-GDB for verification), inferior-tty setup, step debugging loop, and stdin redirection discipline.references/exploit-templates.md: pwntools skeletons, menu wrappers, GDB attach patterns, and state notes.references/technique-index.md: stack, format string, shellcode, seccomp, IO_FILE, reverse/protocol, and special trick routing.references/glibc-heap-version-map.md: heap exploitation choices by glibc version, allocator protection, primitive, and challenge limits. Read this first for any heap challenge.references/house-of-techniques.md: the full "House of" catalog (and modern FSOP foundation) — applicable versions, preconditions, core idea, target, and how to drive each one, current through glibc 2.43. Read this whenever a heap route involves a House-of, FILE/FSOP, largebin, or_rtld_globaltechnique.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 298 B
- references/ctf-workflow.md 6.0 KB
- references/exploit-templates.md 4.5 KB
- references/glibc-heap-version-map.md 18 KB
- references/house-of-techniques.md 25 KB
- references/technique-index.md 8.7 KB
- references/tmux-debugging.md 10.0 KB
- templates/exp.py 1.3 KB runs code
- templates/solve-state.md 1.1 KB
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.
- 11d ago First seen · 355 lines · 0 tokens per session scan A 293514f6e7f7
ctf-pwn is a skill published in the GitHub repository a2ure123/ctf-pwn-skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 84 tokens to every session and 5,629 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 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.