havoc

havoc is a skill for Claude Code from MingyiSecLab/Mingyi-Atlas. It costs 77 tokens per session (1,712 once invoked), scanned A, original, Apache-2.0.

A guide to operating Havoc, an open-source command-and-control system used to manage remote agents during authorised security engagements.

In plain words
What is it for?
Use it to build and run Havoc, configure HTTP communication profiles, manage its operator client and team server, and work with Windows Demon agents.
Why use it?
It provides a way to coordinate commands and communications with test agents while configuring how the system connects and behaves.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to build and run Havoc, configure HTTP communication profiles, manage its operator client and team server, and work with Windows Demon agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mingyiseclab/mingyi-atlas/havoc
Install

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.

Any agent
npx skills add MingyiSecLab/Mingyi-Atlas --skill havoc
Clone the repo
git clone --depth 1 https://github.com/MingyiSecLab/Mingyi-Atlas

Made for: Claude Code.

Wrote 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.

agentmods badge for havoc

README.md
[![agentmods](https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/havoc/github.svg)](https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/havoc)
Your own site
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/havoc"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/havoc/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.

agentmods 80×15 button for havoc

Your own site · 80×15
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/havoc"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/havoc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,712 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.01712
Opus 5 $0.00039 $0.00856
Sonnet 5 $0.00015 $0.00342
Haiku 4.5 $0.00008 $0.00171

Measured 9d ago against content hash 4d7602fb4b62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

havoc 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 9d 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.

src/skills/standard/post-exploit/c2/havoc/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Havoc C2 Operator Skill

Havoc (C5pider) is an open-source, modern C2 framework released 2023. The Demon agent ships with hardened OPSEC defaults (indirect syscalls, sleep obfuscation, no static strings) that make it harder to detect than older OSS frameworks.

Setup

# Build from source (Linux)
git clone https://github.com/HavocFramework/Havoc
cd Havoc
make ts-build
make client-build
make server-build

# Or run via Docker
docker compose up -d

Architecture

   ┌────────────┐       ┌─────────────┐       ┌──────────┐
   │ Operator   │ <───> │ Teamserver  │ <───> │ Demon    │
   │ (Client)   │  TS   │ (Go + gRPC) │  HTTP │ (Implant)│
   └────────────┘       └─────────────┘       └──────────┘
  • Teamserver: Listens on operator port (40056 default) for clients; HTTP listener for demons.
  • Client: Qt-based desktop UI (Material Dark).
  • Demon: Windows x86_64/x86 implant in C with embedded sleep obfuscation + indirect syscalls.

Configure a profile

Havoc uses a profiles.yaotl HCL-like config. Example for a low-OPSEC HTTP listener:

Teamserver {
  Host = "0.0.0.0"
  Port = 40056
  Build {
    Compiler64 = "data/x86_64-w64-mingw32-cross/bin/x86_64-w64-mingw32-gcc"
    Compiler86 = "data/i686-w64-mingw32-cross/bin/i686-w64-mingw32-gcc"
    Nasm = "/usr/bin/nasm"
  }
}

Operators {
  user "op-alice" { Password = "strongpassword" }
}

Listeners {
  Http {
    Name      = "primary-http"
    Hosts     = ["op-server.com"]
    HostBind  = "0.0.0.0"
    PortBind  = 443
    PortConn  = 443
    Secure    = true
    HostRotation = "round-robin"
    Uris      = ["/jquery-3.3.1.min.js", "/jquery-3.3.2.min.js"]   # blend with CDN traffic
    Headers   = ["X-Forwarded-For: 1.2.3.4"]
    UserAgent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
  }
}

Then ./havoc server --profile profiles.yaotl -v.

Build a Demon

In the client UI:

  1. Attack → Payload → Demon
  2. Listener: select your HTTP listener
  3. Arch: x64 / x86
  4. Format: Windows Exe / Windows DLL / Shellcode
  5. Sleep Technique: Ekko (queue user APC ROP chain) / Zilean (timer-based) / FOLIAGE (ROP-based)
  6. Indirect Syscalls: Enable (resolves syscalls at runtime, bypasses static SSN hooks)
  7. Save → drop on target

Read the full file on GitHub · 157 lines

Changes

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.

  1. 9d ago First seen · 157 lines · 77 tokens per session scan A 4d7602fb4b62

Subscribe to this mod's changes

havoc is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,712 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 2026-09-03.