c2-sliver

c2-sliver is a skill for Claude Code from MingyiSecLab/Mingyi-Atlas. It costs 38 tokens per session (3,405 once invoked), scanned A, original, Apache-2.0.

A guide to operating Sliver, an open-source command-and-control framework used for authorized adversary emulation. Command and control is the communication channel between a security operator and software running on a test system.

In plain words
What is it for?
Use it to configure Sliver connections, start HTTPS or other listeners, generate implants, manage sessions, and add post-exploitation extensions.
Why use it?
It explains how to connect to the framework, create listeners and implants, and manage post-compromise sessions in a controlled environment.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to configure Sliver connections, start HTTPS or other listeners, generate implants, manage sessions, and add post-exploitation extensions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mingyiseclab/mingyi-atlas/c2-sliver
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 c2-sliver
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 c2-sliver

README.md
[![agentmods](https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/c2-sliver/github.svg)](https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/c2-sliver)
Your own site
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/c2-sliver"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/c2-sliver/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 c2-sliver

Your own site · 80×15
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/c2-sliver"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/c2-sliver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,405 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 $0.00038 $0.03405
Opus 5 $0.00019 $0.01702
Sonnet 5 $0.00008 $0.00681
Haiku 4.5 $0.00004 $0.00341

Measured 9d ago against content hash 4d7ff4165c67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

c2-sliver 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-sliver/SKILL.md · 411 lines

How it starts

The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sliver C2 Framework

Sliver is an open-source, cross-platform adversary emulation framework by BishopFox. It supports beacon (async) and session (interactive) implants over mTLS, HTTPS, DNS, and WireGuard channels with multi-operator support.

Atlas Setup

Server: c2-sliver container on sandbox-net (daemon mode, gRPC on port 31337) Client: sliver-client pre-installed in sandbox Config: Auto-generated operator config at /workspace/.sliver-configs/atlas.cfg

Connection Procedure (via bash tool)

# 1. Verify C2 reachable
bash(command="nc -z c2-sliver 31337 && echo 'C2_OK' || echo 'C2_DOWN'")

# 2. Import operator config (once — skip if already imported)
bash(command="ls ~/.sliver-client/configs/ 2>/dev/null | grep -q . || sliver-client import /workspace/.sliver-configs/atlas.cfg")

# 3. Start interactive console in dedicated tmux session
bash(command="sliver-client console", session="c2")

# 4. Run Sliver commands interactively
bash(command="https --lhost 0.0.0.0 --lport 443 --domain c2-sliver", is_input=True, session="c2")
bash(command="sessions", is_input=True, session="c2")

IMPORTANT:

  • Do NOT generate operator configs manually — use the pre-generated one at /workspace/.sliver-configs/atlas.cfg
  • Do NOT start sliver-server in sandbox — the server runs in its own container
  • sliver-client console is interactive — MUST use a dedicated session (e.g. session="c2") and send subsequent commands with is_input=True
  • If "multiple configs found": bash(command="sliver-client console --config ~/.sliver-client/configs/atlas_c2-sliver.cfg", session="c2")

1. Listener Configuration

All commands below run inside the Sliver console (session="c2", is_input=True).

HTTPS Listener

# Basic HTTPS listener on 443
https --lhost 0.0.0.0 --lport 443 --domain c2-sliver

# HTTPS with custom certificate (better OPSEC)
https --lhost 0.0.0.0 --lport 443 --domain c2-sliver \
    --cert /workspace/certs/cert.pem \
    --key /workspace/certs/key.pem

# HTTPS with Let's Encrypt (requires DNS control)
https --lhost 0.0.0.0 --lport 443 --domain c2-sliver --lets-encrypt

Read the full file on GitHub · 411 lines

Files

What ships with it

1 file 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.

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 · 411 lines · 38 tokens per session scan A 4d7ff4165c67

Subscribe to this mod's changes

c2-sliver is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 3,405 once invoked, about $0.0002 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.