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 gongyijie85/dsh-ecc --skill homelab-wireguard-vpngit clone --depth 1 https://github.com/gongyijie85/dsh-eccWrote 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/gongyijie85/dsh-ecc/homelab-wireguard-vpn)<a href="https://agentmods.dev/skills/gongyijie85/dsh-ecc/homelab-wireguard-vpn"><img src="https://agentmods.dev/badge/skills/gongyijie85/dsh-ecc/homelab-wireguard-vpn/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/gongyijie85/dsh-ecc/homelab-wireguard-vpn"><img src="https://agentmods.dev/badge/skills/gongyijie85/dsh-ecc/homelab-wireguard-vpn.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 | $0.00064 | $0.02835 |
| Opus 5 | $0.00032 | $0.01418 |
| Sonnet 5 | $0.00013 | $0.00567 |
| Haiku 4.5 | $0.00006 | $0.00283 |
Grade B, and why
homelab-wireguard-vpn scanned grade B with 3 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt update && sudo apt install wireguard -y Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl --fail --silent --show-error --max-time 10 \ Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
private = subprocess.check_output(["wg", "genkey"]).decode().strip() This is a copy
86% identical to homelab-wireguard-vpn — 28 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Homelab WireGuard VPN
WireGuard is a fast, modern VPN protocol. It is the right choice for remote access to a home network — simpler to configure than OpenVPN and faster than most alternatives.
All configuration examples show common setups. Review each command — especially the iptables forwarding rules and key file permissions — before applying them to your system, and make changes in a maintenance window.
When to Use
- Setting up WireGuard server on a Raspberry Pi, Linux host, pfSense, or router
- Generating WireGuard keypairs and writing peer config files
- Configuring remote access from a phone or laptop to a home network
- Explaining split tunneling (route only home traffic) vs full tunnel (route all traffic)
- Troubleshooting WireGuard connections that will not come up
- Automating peer configuration generation for multiple clients
How WireGuard Works
Your phone (WireGuard client)
│
│ Encrypted UDP tunnel (port 51820)
│
Your home router (WireGuard server — needs a public IP or DDNS)
│
Your home network (192.168.1.0/24, NAS, Pi, etc.)
Every device has a keypair (public + private key).
The server knows each client's public key.
The client knows the server's public key + endpoint (IP:port).
Traffic is encrypted end-to-end with no central server or certificate authority.
Server Setup (Linux)
# Install WireGuard
sudo apt update && sudo apt install wireguard -y
# Generate server keypair — create files with private permissions from the start
sudo mkdir -p /etc/wireguard
sudo sh -c 'umask 077; wg genkey > /etc/wireguard/server_private.key'
sudo sh -c 'wg pubkey < /etc/wireguard/server_private.key > /etc/wireguard/server_public.key'
# Write server config — substitute the actual private key value
# Do not store private keys in version control or share them
sudo tee /etc/wireguard/wg0.conf << 'EOF'
[Interface]
Address = 10.8.0.1/24 # VPN subnet — server gets .1
ListenPort = 51820
PrivateKey = <paste_server_private_key_here>
# Scoped forwarding rules: allow VPN traffic in/out, not a blanket FORWARD ACCEPT
PostUp = iptables -A FORWARD -i wg0 -o eth0 -j ACCEPT
PostUp = iptables -A FORWARD -i eth0 -o wg0 -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
PostUp = iptables -t nat -A POSTROUTING -o eth0 -j MASQUERADE
PostDown = iptables -D FORWARD -i wg0 -o eth0 -j ACCEPT
PostDown = iptables -D FORWARD -i eth0 -o wg0 -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
PostDown = iptables -t nat -D POSTROUTING -o eth0 -j MASQUERADE
[Peer]
# Phone — replace with the actual phone public key
PublicKey = <phone_public_key>
AllowedIPs = 10.8.0.2/32
[Peer]
# Laptop — replace with the actual laptop public key
PublicKey = <laptop_public_key>
AllowedIPs = 10.8.0.3/32
EOF
sudo chmod 600 /etc/wireguard/wg0.conf
# Replace eth0 with your actual outbound interface name
# Check with: ip route show default
# Enable IP forwarding (required for routing traffic through the server)
echo "net.ipv4.ip_forward=1" | sudo tee /etc/sysctl.d/99-wireguard.conf
sudo sysctl --system
# Start WireGuard and enable on boot
sudo wg-quick up wg0
sudo systemctl enable wg-quick@wg0
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 · 307 lines · 64 tokens per session scan B 38df424e3995
homelab-wireguard-vpn is a skill published in the GitHub repository gongyijie85/dsh-ecc (7 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 2,835 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 3 findings (asks for root, makes network calls, runs shell commands). It is 86% identical to homelab-wireguard-vpn, differing in 28 lines, and is treated as a copy.
Other skills, from other repositories
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
dsh-web-pet-developer
Create a pet for the dsh-pet plugin and integrate it into the dsh web GUI — author a v2 pet.json manifest plus an 8-column x 9-row atlas per the Codex/hatch-pet contract (live2d pets, voice packs and status decorations included), drop it into the pet-center user directory or contribute it as a built-in asset under…
daytona-dev
Daytona development environment overview. Use when the user asks about Daytona setup, Daytona toolbox, dev environment, noVNC, CDP, server sandbox, secrets volume, Electron sandbox, standalone Chrome, validation, or artifacts volume.
dsh-plugin-guide
Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…
xiaohongshu-search
A tool for searching and ranking popular Xiaohongshu posts, a Chinese social content platform. It uses keywords, engagement, relevance, and recency to recommend content and related search directions.
investor-distiller
An analysis tool for studying investment bloggers on WeChat, a Chinese messaging and publishing platform. It collects their articles and builds a structured profile of their trading methods, market views, writing style, topics and audience interaction.