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 metasploitgit 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/metasploit)<a href="https://agentmods.dev/skills/encod3d-sec/torch/metasploit"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/metasploit/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/encod3d-sec/torch/metasploit"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/metasploit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to critical
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 →
- critical YARA Match · line 3 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
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 | $0.00124 | $0.01051 |
| Opus 5.5 | $0.00050 | $0.00420 |
| Sonnet 5.5 | $0.00025 | $0.00210 |
| Haiku 4.5 | $0.00012 | $0.00105 |
Grade A, and why
metasploit 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 1mo 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metasploit: framework driver
Drive msfconsole for recon, exploit, reverse shells, and post-ex. Syntax lives in
[[metasploit]]; this skill is the workflow that strings it together.
Pre-attack wiki query (MANDATORY)
Before firing any exploit module, query the fingerprinted tech/CVE: read [[metasploit]]
directly for syntax, then Skill(arsenal) for the matching module/payload/technique. Never fire
a module from memory when a targeted lookup would confirm the right one/target index.
Setup / DB
msfconsole -q in a named tmux tab, never a blind background job, the operator needs to see
sessions land live. workspace -a <eng> scopes loot to the engagement, db_status confirms the
Postgres backend is up before anything else. Cheatsheet: Setup + Database sections.
Recon via msf
db_nmap writes straight to hosts/services; layer auxiliary/scanner/* (smb/http/ssh
version + vuln checks) on top for anything plain nmap scripts miss. This complements the
ctf-box Phase-1 basics, it does not replace them, run both.
Search / select / verify
search <app> <ver> or search cve:<id>, use, info to read the module's CVE refs and
target list, check before run/exploit whenever the module supports it, a non-destructive
exploitability test beats a blind fire. Cheatsheet: Search and Selection + Options and Running.
Reverse shells
multi/handler catches. Payload choice: meterpreter first
(linux/x64/meterpreter/reverse_tcp / windows/x64/meterpreter/reverse_tcp), fall back to plain
shell_reverse_tcp when meterpreter is blocked or unstable, routine on hardened Windows/EDR.
Delivery via msfvenom (ELF/EXE/ASPX/PHP, cheatsheet's MSFVenom section has every format).
Egress-test the LPORT (80/443/53 before 4444). Background the handler correctly:
set ExitOnSession false; run -j so it keeps catching new sessions. On the VM, scripts/vm-handler.sh <eng> <lhost> [payload] automates the LPORT choice: it reads the VM's listeners and picks the first FREE egress-friendly port (80/443/53/8000/8080), so the handler never fails to bind on a taken port nor silently picks a filtered high port; it launches in the engagement's msf tmux window and prints the LPORT to build the payload with.
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.
- 1mo ago First seen · 63 lines · 124 tokens per session scan A e96b7e846c0c
metasploit is a skill published in the GitHub repository Encod3d-Sec/TORCH (336 stars, last pushed 1mo ago), licensed MIT. It adds 124 tokens to every session and 1,051 once invoked, about $0.0005 per session on Opus 5.5. 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
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…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…