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 Encod3d-Sec/TORCH --skill ctf-categorygit clone --depth 1 https://github.com/Encod3d-Sec/TORCHWrote 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/encod3d-sec/torch/ctf-category)<a href="https://agentmods.dev/skills/encod3d-sec/torch/ctf-category"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/ctf-category.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00061 | $0.00976 |
| Opus 5 | $0.00030 | $0.00488 |
| Sonnet 5 | $0.00012 | $0.00195 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
ctf-category 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 8d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CTF Category Router
Given a challenge file or description, identify the category, then read the matching wiki page and apply its methodology. Always file the artifact and read the prompt before choosing.
Fingerprint -> route
| Signal | Category | Wiki page | First moves / tools |
|---|---|---|---|
| ELF/PE binary + "get a shell" / nc to a port | pwn | [[binary-exploitation]] | checksec; find offset (cyclic); [[pwntools]] template; leak libc |
| Binary + "find the flag" / crackme / no network | rev | [[reverse-engineering]] | file,strings,checksec; [[radare2]]/Ghidra; ltrace; angr |
n,e,c / .pem / cipher / "encrypt" / base-looking blob |
crypto | [[cryptography-attacks]], [[crypto-ctf-workflow]] | identify primitive; RsaCtfTool; padding/XOR/hash-ext; CyberChef |
| .sol file / ABI+bytecode / contract address / web3 RPC endpoint | blockchain | [[smart-contract-web3-attacks]], [[defi-amm-exploitation]] | [[slither]] static analysis; Foundry/Hardhat local fork to reproduce; flash-loan/AMM economic-exploit sims for DeFi |
| .pcap / .raw memory / disk image / .E01 | forensics | [[digital-forensics]] | file,binwalk; [[volatility]] (mem); [[wiki/tools/tshark]]/Wireshark (pcap) |
| Innocuous image/audio / "look closer" | stego | [[steganography]] | exiftool,binwalk,strings; zsteg/steghide/stegseek; spectrogram |
| URL / web app | web | existing hunt skills | auto-triggers (sqli/xss/ssrf/idor/injection...) via triggers.json |
Cloud creds/console (Azure TAP+SP, *.core.windows.net, AWS keys, GCP) - no ports, only a REST/console surface |
cloud | [[cloud-moc]], [[cloud-iam-attacks]] | Skill(hunt-cloud): whoami; enumerate storage/SAS/blob + Key Vault (incl. prior secret versions) / IMDS - NOT the network-box driver |
$hash / NTLM / shadow / zip2john |
hash/crack | [[hash-capture-and-cracking]] | identify (hashid); [[wiki/tools/hashcat]] mode; [[password-cracking]] |
| "find the account/person/leak" / no file | osint | [[persona-tracing]], [[secret-hunting]], [[web-attack-surface]] | person pivots + photo geolocation; [[git-exposure]] for repos |
python >>> jail / restricted shell / filtered interpreter |
misc/jail | [[ctf-jail-escapes]] | builtins/mro recovery, format-string pyjail, GTFOBins rbash escape |
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.
- 8d ago First seen · 37 lines · 61 tokens per session scan A 9ac80d2a97d7
ctf-category is a skill published in the GitHub repository Encod3d-Sec/TORCH (314 stars, last pushed 6d ago), licensed MIT. It adds 61 tokens to every session and 976 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…